Publications

@inproceedings{Beel2025,

title = {Checky, the Paper-Submission Checklist Generator for Authors, Reviewers and LLMs},

author = {Joeran Beel and Bela Gipp and Dietmar Jannach and Alan Said and Lukas Wegmeth and Tobias Vente},

url = {http://isg.beel.org/pubs/2025-Checky-Checklist-Generator-ECIR-Beel-et-al.pdf},

year  = {2025},

date = {2025-01-01},

booktitle = {47th European Conference on Information Retrieval (ECIR)},

pages = {10–15},

publisher = {Springer},

series = {LNCS},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2024d,

title = {A Call for Evidence-based Best-Practices for Recommender Systems Evaluations},

author = {Joeran Beel},

editor = {Christine Bauer and Alan Said and Eva Zangerle},

url = {https://isg.beel.org/pubs/2024_Call_for_Evidence_Based_RecSys_Evaluation__Pre_Print_.pdf},

doi = {10.31219/osf.io/djuac},

year  = {2024},

date = {2024-01-01},

booktitle = {Report from Dagstuhl Seminar 24211: Evaluation Perspectives of Recommender Systems: Driving Research and Education},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2024,

title = {Best-Practices for Offline Evaluations of Recommender Systems},

author = {Joeran Beel and Dietmar Jannach and Alan Said and Guy Shani and Tobias Vente and Lukas Wegmeth},

editor = {Christine Bauer and Alan Said and Eva Zangerle},

year  = {2024},

date = {2024-01-01},

booktitle = {Report from Dagstuhl Seminar 24211 – Evaluation Perspectives of Recommender Systems: Driving Research and Education},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Baumgart2024,

title = {e-Fold Cross-Validation for Recommender-System Evaluation},

author = {Moritz Baumgart and Lukas Wegmeth and Tobias Vente and Joeran Beel},

url = {https://isg.beel.org/pubs/2024-e-folds-recsys-baumgart.pdf},

year  = {2024},

date = {2024-01-01},

booktitle = {International Workshop on Recommender Systems for Sustainability and Social Good (RecSoGood) at the 18th ACM Conference on Recommender Systems (ACM RecSys)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Wegmeth2024a,

title = {EMERS: Energy Meter for Recommender Systems},

author = {Lukas Wegmeth and Tobias Vente and Alan Said and Joeran Beel},

url = {https://arxiv.org/pdf/2409.15060},

year  = {2024},

date = {2024-01-01},

booktitle = {International Workshop on Recommender Systems for Sustainability and Social Good (RecSoGood) at the 18th ACM Conference on Recommender Systems (ACM RecSys)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Vente2024a,

title = {From Clicks to Carbon: The Environmental Toll of Recommender Systems},

author = {Tobias Vente and Lukas Wegmeth and Alan Said and Joeran Beel},

url = {https://arxiv.org/abs/2408.08203},

doi = {10.1145/3640457.3688074},

isbn = {9798400705052},

year  = {2024},

date = {2024-01-01},

booktitle = {Proceedings of the 18th ACM Conference on Recommender Systems},

pages = {580–590},

publisher = {Association for Computing Machinery},

address = {Bari, Italy},

series = {RecSys '24},

abstract = {As global warming soars, the need to assess the environmental impact of research is becoming increasingly urgent. Despite this, few recommender systems research papers address their environmental impact. In this study, we estimate the environmental impact of recommender systems research by reproducing typical experimental pipelines. Our analysis spans 79 full papers from the 2013 and 2023 ACM RecSys conferences, comparing traditional “good old-fashioned AI’’ algorithms with modern deep learning algorithms. We designed and reproduced representative experimental pipelines for both years, measuring energy consumption with a hardware energy meter and converting it to CO2 equivalents. Our results show that papers using deep learning algorithms emit approximately 42 times more CO2 equivalents than papers using traditional methods. On average, a single deep learning-based paper generates 3,297 kilograms of CO2 equivalents—more than the carbon emissions of one person flying from New York City to Melbourne or the amount of CO2 one tree sequesters over 300 years.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Mahlich2024,

title = {From Theory to Practice: Implementing and Evaluating e-Fold Cross-Validation},

author = {Christopher Mahlich and Tobias Vente and Joeran Beel},

url = {https://isg.beel.org/blog/2024/09/16/e-fold-cross-validation/},

year  = {2024},

date = {2024-01-01},

booktitle = {International Conference on Artificial Intelligence and Machine Learning Research (CAIMLR)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Vente2024b,

title = {Greedy Ensemble Selection for Top-N Recommendations},

author = {Tobias Vente and Zainil Mehta and Lukas Wegmeth and Joeran Beel},

year  = {2024},

date = {2024-01-01},

booktitle = {RobustRecSys Workshop at the 18th ACM Conference on Recommender Systems (ACM RecSys)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Arabzadeh2024,

title = {Green Recommender Systems: Optimizing Dataset Size for Energy-Efficient Algorithm Performance},

author = {Ardalan Arabzadeh and Tobias Vente and Joeran Beel},

url = {https://isg.beel.org/pubs/2024-Green-RecSys-Dataset-Sampling-Ardalan.pdf},

year  = {2024},

date = {2024-01-01},

booktitle = {International Workshop on Recommender Systems for Sustainability and Social Good (RecSoGood) at the 18th ACM Conference on Recommender Systems (ACM RecSys)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2024b,

title = {Informed Dataset Selection with ‘Algorithm Performance Spaces’},

author = {Joeran Beel and Lukas Wegmeth and Lien Michiels and Steffen Schulz},

url = {https://doi.org/10.1145/3640457.3691704 

https://isg.beel.org/blog/2024/09/01/informed-dataset-selection-with-algorithm-performance-spaces/},

doi = {10.1145/3640457.3691704},

isbn = {9798400705052},

year  = {2024},

date = {2024-01-01},

booktitle = {18th ACM Conference on Recommender Systems},

pages = {1085–1090},

publisher = {Association for Computing Machinery},

address = {Bari, Italy},

series = {RecSys '24},

abstract = {When designing recommender-systems experiments, a key question that has been largely overlooked is the choice of datasets. In a brief survey of ACM RecSys papers, we found that authors typically justified their dataset choices by labelling them as public, benchmark, or ‘real-world’ without further explanation. We propose the Algorithm Performance Space (APS) as a novel method for informed dataset selection. The APS is an n-dimensional space where each dimension represents the performance of a different algorithm. Each dataset is depicted as an n-dimensional vector, with greater distances indicating higher diversity. In our experiment, we ran 29 algorithms on 95 datasets to construct an actual APS. Our findings show that many datasets, including most Amazon datasets, are clustered closely in the APS, i.e. they are not diverse. However, other datasets, such as MovieLens and Docear, are more dispersed. The APS also enables the grouping of datasets based on the solvability of the underlying problem. Datasets in the top right corner of the APS are considered ’solved problems’ because all algorithms perform well on them. Conversely, datasets in the bottom left corner lack well-performing algorithms, making them ideal candidates for new recommender-system research due to the challenges they present.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2024a,

title = {Our use of AI-tools for writing research papers},

author = {Joeran Beel},

url = {https://isg.beel.org/blog/2024/08/19/our-use-of-ai-tools-for-writing-research-papers/},

year  = {2024},

date = {2024-01-01},

booktitle = {Intelligent Systems Group, Blog},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Wegmeth2024,

title = {Recommender Systems Algorithm Selection for Ranking Prediction on Implicit Feedback Datasets},

author = {Lukas Wegmeth and Tobias Vente and Joeran Beel},

url = {https://arxiv.org/pdf/2409.05461},

year  = {2024},

date = {2024-01-01},

booktitle = {18th ACM Conference on Recommender Systems (ACM RecSys)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Meister2024,

title = {Removing Bad Influence: Identifying and Pruning Detrimental Users in Collaborative Filtering Recommender Systems},

author = {Philipp Meister and Lukas Wegmeth and Tobias Vente and Joeran Beel},

year  = {2024},

date = {2024-01-01},

booktitle = {RobustRecSys Workshop at the 18th ACM Conference on Recommender Systems (ACM RecSys)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Wegmeth2024b,

title = {Revealing the Hidden Impact of Top-N Metrics on Optimization in Recommender Systems},

author = {Lukas Wegmeth and Tobias Vente and Lennart Purucker},

editor = {Nazli Goharian and Nicola Tonellotto and Yulan He and Aldo Lipani and Graham McDonald and Craig Macdonald and Iadh Ounis},

url = {https://link.springer.com/chapter/10.1007/978-3-031-56027-9_9 

https://arxiv.org/pdf/2401.08444},

doi = {10.1007/978-3-031-56027-9_9},

isbn = {978-3-031-56027-9},

year  = {2024},

date = {2024-01-01},

booktitle = {46th European Conference on Information Retrieval (ECIR)},

pages = {140–156},

publisher = {Springer Nature Switzerland},

address = {Cham},

abstract = {The hyperparameters of recommender systems for top-n predictions are typically optimized to enhance the predictive performance of algorithms. Thereby, the optimization algorithm, e.g., grid search or random search, searches for the best hyperparameter configuration according to an optimization-target metric, like nDCG or Precision. In contrast, the optimized algorithm, e.g., Alternating Least Squares Matrix Factorization or Bayesian Personalized Ranking, internally optimizes a different loss function during training, like squared error or cross-entropy. To tackle this discrepancy, recent work focused on generating loss functions better suited for recommender systems. Yet, when evaluating an algorithm using a top-n metric during optimization, another discrepancy between the optimization-target metric and the training loss has so far been ignored. During optimization, the top-n items are selected for computing a top-n metric; ignoring that the top-n items are selected from the recommendations of a model trained with an entirely different loss function. Item recommendations suitable for optimization-target metrics could be outside the top-n recommended items; hiddenly impacting the optimization performance. Therefore, we were motivated to analyze whether the top-n items are optimal for optimization-target top-n metrics. In pursuit of an answer, we exhaustively evaluate the predictive performance of 250 selection strategies besides selecting the top-n. We extensively evaluate each selection strategy over twelve implicit feedback and eight explicit feedback data sets with eleven recommender systems algorithms. Our results show that there exist selection strategies other than top-n that increase predictive performance for various algorithms and recommendation domains. However, the performance of the top $$backslashsim 43backslash%$$∼43%of selection strategies is not significantly different. We discuss the impact of our findings on optimization and re-ranking in recommender systems and feasible solutions. The implementation of our study is publicly available.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Purucker2023a,

title = {A first Look at Meta-Learning Algorithm Selection for Post Hoc Ensembling in AutoML},

author = {Lennart Purucker and Joeran Beel},

year  = {2023},

date = {2023-01-01},

booktitle = {Poster Track of the COSEAL Workshop},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Vente2023,

title = {Advancing Automation of Design Decisions in Recommender System Pipelines},

author = {Tobias Vente},

doi = {https://dl.acm.org/doi/10.1145/3604915.3608886},

year  = {2023},

date = {2023-01-01},

booktitle = {Proceedings of the 17th ACM Conference on Recommender Systems},

pages = {1355-1360},

abstract = {Recommender systems have become essential in domains like streaming services, social media platforms, and e-commerce websites. However, the development of a recommender system involves a complex pipeline with preprocessing, data splitting, algorithm and model selection, and postprocessing stages. Every stage of the recommender systems pipeline requires design decisions that influence the performance of the recommender system. To ease design decisions, automated machine learning (AutoML) techniques have been adapted to the field of recommender systems, resulting in various AutoRecSys libraries. Nevertheless, these libraries limit flexibility in integrating automation techniques. In response, our research aims to enhance the usability of AutoML techniques for design decisions in recommender system pipelines. We focus on developing flexible and library-independent automation techniques for algorithm selection, model selection, and postprocessing steps. By enabling developers to make informed choices and ease the recommender system development process, we decrease the developer’s effort while improving the performance of the recommender systems. Moreover, we want to analyze the cost-to-benefit ratio of automation techniques in recommender systems, evaluating the computational overhead and the resulting improvements in predictive performance. Our objective is to leverage AutoML concepts to automate design decisions in recommender system pipelines, reduce manual effort, and enhance the overall performance and usability of recommender systems.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Purucker2023,

title = {CMA-ES for Post Hoc Ensembling in AutoML: A Great Success and Salvageable Failure},

author = {Lennart Purucker and Joeran Beel},

url = {https://openreview.net/pdf?id=MeCwOxob8jfl},

year  = {2023},

date = {2023-01-01},

booktitle = {2nd International Conference on Automated Machine Learning (AutoML)},

pages = {1–23},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Wegmeth2023a,

title = {Improving Recommender Systems Through the Automation of Design Decisions},

author = {Lukas Wegmeth},

url = {https://dl.acm.org/doi/pdf/10.1145/3604915.3608877},

year  = {2023},

date = {2023-01-01},

booktitle = {Proceedings of the 17th ACM Conference on Recommender Systems},

pages = {1332-1338},

abstract = {Recommender systems developers are constantly faced with difficult design decisions. Additionally, the number of options that a recommender systems developer has to consider continually grows over time with new innovations. The machine learning community is in a similar situation and has come together to tackle the problem. They invented concepts and tools to make machine learning development both easier and faster. These developments are categorized as automated machine learning (AutoML). As a result, the AutoML community formed and continuously innovates new approaches. Inspired by AutoML, the recommender systems community has recently understood the need for automation and sparsely introduced AutoRecSys. The goal of AutoRecSys is not to replace recommender systems developers but to improve performance through the automation of design decisions. With AutoRecSys, recommender systems engineers do not have to focus on easy but time-consuming tasks and are free to pursue difficult engineering tasks instead. Additionally, AutoRecSys enables easier access to recommender systems for beginners as it reduces the amount of knowledge required to get started with the development of recommender systems. AutoRecSys, like AutoML, is still early in its development and does not yet cover the whole development pipeline. Additionally, it is not yet clear, under which circumstances AutoML approaches can be transferred to recommender systems. Our research intends to close this gap by improving AutoRecSys both with regard to the transfer of AutoML and novel approaches. Furthermore, we focus specifically on the development of novel automation approaches for data processing and training. We note that the realization of AutoRecSys is going to be a community effort. Our part in this effort is to research AutoRecSys fundamentals, build practical tools for the community, raise awareness of the advantages of automation, and catalyze AutoRecSys development.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Vente2023a,

title = {Introducing LensKit-Auto, an Experimental Automated Recommender System (AutoRecSys) Toolkit},

author = {Tobias Vente and Michael Ekstrand and Joeran Beel},

url = {https://dl.acm.org/doi/10.1145/3604915.3610656},

year  = {2023},

date = {2023-01-01},

booktitle = {Proceedings of the 17th ACM Conference on Recommender Systems},

pages = {1212-1216},

abstract = {LensKit is one of the first and most popular Recommender System libraries. While LensKit offers a wide variety of features, it does not include any optimization strategies or guidelines on how to select and tune LensKit algorithms. LensKit developers have to manually include third-party libraries into their experimental setup or implement optimization strategies by hand to optimize hyperparameters. We found that 63.6% (21 out of 33) of papers using LensKit algorithms for their experiments did not select algorithms or tune hyperparameters. Non-optimized models represent poor baselines and produce less meaningful research results. This demo introduces LensKit-Auto. LensKit-Auto automates the entire Recommender System pipeline and enables LensKit developers to automatically select, optimize, and ensemble LensKit algorithms.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Purucker2023b,

title = {Q(D)O-ES: Population-based Quality (Diversity) Optimisation for Post Hoc Ensemble Selection in AutoML},

author = {Lennart Purucker and Lennart Schneider and Marie Anastacio and Joeran Beel and Bernd Bischl and Hoos Holger},

url = {https://openreview.net/pdf?id=zvV7hemQmtLl},

year  = {2023},

date = {2023-01-01},

booktitle = {2nd International Conference on Automated Machine Learning (AutoML)},

pages = {1–34},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2023,

title = {Results-blind Reviewing},

author = {Joeran Beel and Timo Breuer and Anita Crescenzi and Norbert Fuhr and Meije Li},

editor = {Christine Bauer and Ben Carterette and Nicola Ferro and Norbert Fuhr and Guglielmos Faggioli},

url = {https://isg.beel.org/pubs/2023-Results-Blind-Reviewing-Beel-et-al.pdf},

doi = {10.4230/DagRep.13.1.68},

year  = {2023},

date = {2023-01-01},

booktitle = {Frontiers of Information Access Experimentation for Research and Education (Dagstuhl Seminar 23031)},

volume = {13},

number = {1},

pages = {68-154},

publisher = {Schloss Dagstuhl - Leibniz-Zentrum für Informatik},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Wegmeth2023,

title = {The Effect of Random Seeds for Data Splitting on Recommendation Accuracy},

author = {Lukas Wegmeth and Tobias Vente and Lennart Purucker and Joeran Beel},

url = {https://ceur-ws.org/Vol-3476/paper4.pdf},

year  = {2023},

date = {2023-01-01},

booktitle = {Proceedings of the 3rd Perspectives on the Evaluation of Recommender Systems Workshop},

abstract = {The evaluation of recommender system algorithms depends on randomness, e.g., during randomly splitting data into training and testing data. We suspect that failing to account for randomness in this scenario may lead to misrepresenting the predictive accuracy of recommendation algorithms. To understand the community’s view of the importance of randomness, we conducted a paper study on 39 full papers published at the ACM RecSys 2022 conference. We found that the authors of 26 papers used some variation of a holdout split that requires a random seed. However, only five papers explicitly repeated experiments and averaged their results over different random seeds. This potentially problematic research practice motivated us to analyze the effect of data split random seeds on recommendation accuracy. Therefore, we train three common algorithms on nine public data sets with 20 data split random seeds, evaluate them on two ranking metrics with three different ranking cutoff values k, and compare the results. In the extreme case with k = 1, we show that depending on the data split random seed, the accuracy with traditional recommendation algorithms deviates by up to ∼6.3% from the mean accuracy achieved on the data set. Hence, we show that an algorithm may significantly over- or under-perform when maliciously or negligently selecting a random seed for splitting the data. To showcase a mitigation strategy and better research practice, we compare holdout to cross-validation and show that, again, for k = 1, the accuracy of algorithms evaluated with cross-validation deviates only up to ∼2.3% from the mean accuracy achieved on the data set. Furthermore, we found that the deviation becomes smaller the higher the value of k for both holdout and cross-validation.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Purucker2022,

title = {Assembled-OpenML: Creating Efficient Benchmarks for Ensembles in AutoML with OpenML},

author = {Lennart Oswald Purucker and Joeran Beel},

url = {https://2022.automl.cc/wp-content/uploads/2022/08/assembled_openml_creating_effi-Main-Paper-And-Supplementary-Material.pdf},

year  = {2022},

date = {2022-01-01},

booktitle = {International Conference on Automated Machine Learning, Late-Breaking Results Track},

pages = {1–18},

abstract = {Automated Machine Learning (AutoML) frameworks regularly use ensembles. Developers need to compare different ensemble techniques to select appropriate techniques for an AutoML framework from the many potential techniques. So far, the comparison of ensemble techniques is often computationally expensive, because many base models must be trained and evaluated one or multiple times. Therefore, we present Assembled-OpenML. Assembled-OpenML is a Python tool, which builds meta-datasets for ensembles using OpenML. A meta-dataset, called Metatask, consists of the data of an OpenML task, the task's dataset, and prediction data from model evaluations for the task. We can make the comparison of ensemble techniques computationally cheaper by using the predictions stored in a metatask instead of training and evaluating base models. To introduce Assembled-OpenML, we describe the first version of our tool. Moreover, we present an example of using Assembled-OpenML to compare a set of ensemble techniques. For this example comparison, we built a benchmark using Assembled-OpenML and implemented ensemble techniques expecting predictions instead of base models as input. In our example comparison, we gathered the prediction data of 1523 base models for 31 datasets. Obtaining the prediction data for all base models using Assembled-OpenML took ∼1 hour in total. In comparison, obtaining the prediction data by training and evaluating just one base model on the most computationally expensive dataset took ∼37 minutes.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Wegmeth2022,

title = {CaMeLS: Cooperative Meta-Learning Service for Recommender Systems},

author = {Lukas Wegmeth and Joeran Beel},

url = {https://ceur-ws.org/Vol-3228/paper2.pdf},

year  = {2022},

date = {2022-01-01},

booktitle = {Proceedings of the 2nd Perspectives on the Evaluation of Recommender Systems Workshop},

abstract = {We present CaMeLS, a proof of concept of a cooperative meta-learning service for recommender systems. CaMeLS leverages the computing power of recommender systems users by uploading their metadata and algorithm evaluation scores to a centralized environment. Through the resulting database, CaMeLS then offers meta-learning services for everyone. Additionally, users may access evaluations of common data sets immediately to know the best-performing algorithms for those data sets. The metadata table may also be used for other purposes, eg, to perform benchmarks. In the initial version discussed in this paper, CaMeLS implements automatic algorithm selection through meta-learning over two recommender systems libraries. Automatic algorithm selection saves users time and computing power and does not require expertise, as the best algorithm is automatically found over multiple libraries. The CaMeLS database contains 20 metadata sets by default. We show that the automatic algorithm selection service is already on par with the single best algorithm in this default scenario. CaMeLS only requires a few seconds to predict a suitable algorithm, rather than potentially hours or days if performed manually, depending on the data set. The code is publicly available on our GitHub https://camels. recommender-systems.com.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Wegmeth2022b,

title = {The Impact of Feature Quantity on Recommendation Algorithm Performance: A Movielens-100K Case Study},

author = {Lukas Wegmeth},

url = {https://arxiv.org/pdf/2207.08713.pdf},

year  = {2022},

date = {2022-01-01},

booktitle = {arXiv:2207.08713},

abstract = {Recent model-based Recommender Systems (RecSys) algorithms emphasize on the use of features, also called side information, in their design similar to algorithms in Machine Learning (ML). In contrast, some of the most popular and traditional algorithms for RecSys solely focus on a given user-item-rating relation without including side information. An important category of these is matrix factorization-based algorithms, e.g., Singular Value Decomposition and Alternating Least Squares, which are known to have high performance on RecSys data sets. The goal of this case study is to provide a performance comparison and assessment of RecSys and ML algorithms when side information is included. We chose the Movielens-100K data set since it is a standard for comparing RecSys algorithms. We compared six different feature sets with varying quantities of features which were generated from the baseline data and evaluated on a total of 19 RecSys algorithms, baseline ML algorithms, Automated Machine Learning (AutoML) pipelines, and state-of-the-art RecSys algorithms that incorporate side information. The results show that additional features benefit all algorithms we evaluated. However, the correlation between feature quantity and performance is not monotonous for AutoML and RecSys. In these categories, an analysis of feature importance revealed that the quality of features matters more than quantity. Throughout our experiments, the average performance on the feature set with the lowest number of features is ∼6% worse compared to that with the highest in terms of the Root Mean Squared Error. An interesting observation is that AutoML outperforms matrix factorization-based RecSys algorithms when additional features are used. Almost all algorithms that can include side information have higher performance when using the highest quantity of features. In the other cases, the performance difference is negligible (<1%). The results show a clear positive trend for the effect of feature quantity as well as the important effects of feature quality on the evaluated algorithms.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{AlRawi2021a,

title = {Probabilistic Color Modelling of Clothing Items},

author = {Mohammed Al-Rawi and Joeran Beel},

editor = {Jaradat N. Dokoohaki},

url = {https://link.springer.com/chapter/10.1007/978-3-030-66103-8_2},

doi = {10.1007/978-3-030-66103-8_2},

year  = {2021},

date = {2021-01-01},

booktitle = {Recommender Systems in Fashion and Retail},

volume = {734},

pages = {21–40},

publisher = {Springer},

series = {Lecture Notes in Electrical Engineering book series},

abstract = {Color modelling and extraction is an important topic in fashion. It can help build a wide range of applications, for example, recommender systems, color-based retrieval, fashion design, etc. We aim to develop and test models that can extract the dominant colors of clothing and accessory items. The approach we propose has three stages: (1) Mask-RCNN to segment the clothing items, (2) cluster the colors into a predefined number of groups, and (3) combine the detected colors based on the hue scores and the probability of each score. We use Clothing Co-Parsing and ModaNet datasets for evaluation. We also scrape fashion images from the WWW and use our models to discover the fashion color trend. Subjectively, we were able to extract colors even when clothing items have multiple colors. Moreover, we are able to extract colors along with the probability of them appearing in clothes. The method can provide the color baseline drive for more advanced fashion systems.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2021,

title = {The ‘Unreasonable’ Effectiveness of Graphical User Interfaces for Recommender Systems},

author = {Joeran Beel and Haley Dixon},

url = {https://dl.acm.org/doi/fullHtml/10.1145/3450614.3461682 

https://www.um.org/umap2021/12-posters/25-the-unreasonable-effectiveness-of-graphical-user-interfaces-for-recommender-systems.html 

https://www.researchgate.net/publication/352672485_The_'Unreasonable'_Effectiveness_of_Graphical_User_Interfaces_for_Recommender_Systems},

doi = {10.1145/3450614.3461682},

isbn = {9781450383677},

year  = {2021},

date = {2021-01-01},

booktitle = {Adjunct Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization},

pages = {22–28},

publisher = {Association for Computing Machinery},

address = {New York, NY, USA},

abstract = {The impact of Graphical User Interfaces (GUI) for recommender systems is a little explored area. Therefore, we conduct an empirical study in which we create, deploy, and evaluate seven different GUI variations. We use these variations to display 68.260 related-blog-post recommendations to 10.595 unique visitors of our blog. The study shows that the GUIs have a strong effect on the recommender systems’ performance, measured in click-through rate (CTR). The best performing GUI achieved a 66% higher CTR than the worst performing GUI (statist. significant with p<0.05). In other words, with a few days of work to develop different GUIs, a recommender-system operator could increase CTR notably – maybe even more than by tuning the recommendation algorithm. In analogy to the ‘unreasonable effectiveness of data’ discussion by Google and others, we conclude that the effectiveness of graphical user interfaces for recommender systems is equally ‘unreasonable’. Hence, the recommender system community should spend more time on researching GUIs for recommender systems. In addition, we conduct a survey and find that the ACM Recommender Systems Conference has a strong focus on algorithms – 81% of all short and full papers published in 2019 and 2020 relate to algorithm development, and none to GUIs for recommender systems. We also surveyed the recommender systems of 50 blogs. While most displayed a thumbnail (86%) and had a mouseover interaction (62%) other design elements were rare. Only few highlighted top recommendations (8%), displayed rankings or relevance scores (6%), or offered a ‘view more’ option (4%).},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Scheidt2021,

title = {Time-dependent Evaluation of Recommender Systems},

author = {Teresa Scheidt and Joeran Beel},

url = {https://ceur-ws.org/Vol-2955/paper10.pdf},

year  = {2021},

date = {2021-01-01},

booktitle = {Perspectives on the Evaluation of Recommender Systems Workshop, ACM RecSys Conference},

abstract = {Evaluation of recommender systems is an actively discussed topic in the recommender system community. However, some aspects of evaluation have received little to no attention, one of them being whether evaluating recommender system algorithms with single-number metrics is sufficient. When presenting results as a single number, the only possible assumption is a stable performance over time regardless of changes in the datasets, while it intuitively seems more likely that the performance changes over time. We suggest presenting results over time, making it possible to identify trends and changes in performance as the dataset grows and changes. In this paper, we conduct an analysis of 6 algorithms on 10 datasets over time to identify the need for a time-dependent evaluation. To enable this evaluation over time, we split the datasets based on the provided timesteps into smaller subsets. At every tested timepoint we use all available data up to this timepoint, simulating a growing dataset as encountered in the realworld. Our results show that for 90% of the datasets the performance changes over time and in 60% even the ranking of algorithms changes over time.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Grennan2020,

title = {Synthetic vs. Real Reference Strings for Citation Parsing, and the Importance of Re-training and Out-Of-Sample Data for Meaningful Evaluations: Experiments with GROBID, GIANT and CORA},

author = {Mark Grennan and Joeran Beel},

url = {https://aclanthology.org/2020.wosp-1.4.pdf 

https://www.aclweb.org/anthology/2020.wosp-1.4},

year  = {2020},

date = {2020-08-01},

booktitle = {Proceedings of the 8th International Workshop on Mining Scientific Publications},

pages = {27–35},

publisher = {Association for Computational Linguistics},

address = {Wuhan, China},

abstract = {Citation parsing, particularly with deep neural networks, suffers 

	from a lack of training data as available datasets typically contain 

	only a few thousand training instances. Manually labelling citation 

	strings is very time-consuming, hence synthetically created training 

	data could be a solution. However, as of now, it is unknown if synthetically 

	created reference-strings are suitable to train machine learning 

	algorithms for citation parsing. To find out, we train Grobid, which 

	uses Conditional Random Fields, with a) human-labelled reference 

	strings from `real' bibliographies and b) synthetically created 

	reference strings from the GIANT dataset. We find that both synthetic 

	and organic reference strings are equally suited for training Grobid (F1 = 0.74). We additionally find that retraining Grobid has a notable 

	impact on its performance, for both synthetic and real data (+30% 

	in F1). Having as many types of labelled fields as possible during 

	training also improves effectiveness, even if these fields are not 

	available in the evaluation data (+13.5% F1). We conclude that 

	synthetic data is suitable for training (deep) citation parsing models. 

	We further suggest that in future evaluations of reference parsers 

	both evaluation data similar and dissimilar to the training data 

	should be used for more meaningful evaluations.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Marwah2020,

title = {Term-Recency for TF-IDF, BM25 and USE Term Weighting},

author = {Divyanshu Marwah and Joeran Beel},

url = {https://aclanthology.org/2020.wosp-1.5.pdf 

https://www.aclweb.org/anthology/2020.wosp-1.5},

year  = {2020},

date = {2020-08-01},

booktitle = {Proceedings of the 8th International Workshop on Mining Scientific Publications},

pages = {36–41},

publisher = {Association for Computational Linguistics},

address = {Wuhan, China},

abstract = {Effectiveness of a recommendation in an Information Retrieval (IR) 

	system is determined by relevancy scores of retrieved results. Term 

	weighting is responsible for computing the relevance scores and consequently 

	differentiating between the terms in a document. However, the current 

	term weighting formula (TF-IDF, for instance), weighs terms only 

	based on term frequency and inverse document frequency irrespective 

	of other important factors. This results in ambiguity in cases when 

	both TF and IDF values the same for more than one document, hence 

	resulting in same TF-IDF values. In this paper, we propose a modification 

	of TF-IDF and other term-weighting schemes that weighs the terms 

	based on the recency and the usage in the corpus. We have tested 

	the performance of our algorithm with existing term weighting schemes; 

	TF-IDF, BM25 and USE text embedding model. We have indexed three 

	different datasets with different domains to validate the premises 

	for our algorithm. On evaluating the algorithms using Precision, 

	Recall, F1 score, and NDCG, we found that time normalized TF-IDF 

	outperformed the classic TF-IDF with a significant difference in 

	all the metrics and datasets. Time-based USE model performed better 

	than the standard USE model in two out of three datasets. But the 

	time-based BM25 model did not perform well in some of the input queries 

	as compared to standard BM25 model.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Molloy2020,

title = {Virtual Citation Proximity (VCP): Empowering Document Recommender Systems by Learning a Hypothetical In-Text Citation-Proximity Metric for Uncited Documents},

author = {Paul Molloy and Joeran Beel and Akiko Aizawa},

url = {https://www.aclweb.org/anthology/2020.wosp-1.1},

year  = {2020},

date = {2020-08-01},

booktitle = {Proceedings of the 8th International Workshop on Mining Scientific Publications},

pages = {1–8},

publisher = {Association for Computational Linguistics},

address = {Wuhan, China},

abstract = {The relatedness of research articles, patents, court rulings, web 

	pages, and other document types is often calculated with citation 

	or hyperlink-based approaches like co-citation (proximity) analysis. 

	The main limitation of citation-based approaches is that they cannot 

	be used for documents that receive little or no citations. We propose 

	Virtual Citation Proximity (VCP), a Siamese Neural Network architecture, 

	which combines the advantages of co-citation proximity analysis (diverse 

	notions of relatedness / high recommendation performance), with the 

	advantage of content-based filtering (high coverage). VCP is trained 

	on a corpus of documents with textual features, and with real citation 

	proximity as ground truth. VCP then predicts for any two documents, 

	based on their title and abstract, in what proximity the two documents 

	would be co-cited, if they were indeed co-cited. The prediction can 

	be used in the same way as real citation proximity to calculate document 

	relatedness, even for uncited documents. In our evaluation with 2 

	million co-citations from Wikipedia articles, VCP achieves an MAE 

	of 0.0055, i.e. an improvement of 20% over the baseline, though 

	the learning curve suggests that more work is needed.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Tyrrell2020,

title = {‘Algorithm-Performance Personas’ for Siamese Meta-Learning and Automated Algorithm Selection},

author = {Bryan Tyrrell and Edward Bergman and Gareth Jones and Joeran Beel},

url = {https://www.automl.org/wp-content/uploads/2020/07/AutoML_2020_paper_48.pdf},

year  = {2020},

date = {2020-01-01},

booktitle = {7th ICML Workshop on Automated Machine Learning},

pages = {1–16},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Anand2020,

title = {Auto-Surprise: An Automated Recommender-System (AutoRecSys) Library with Tree of Parzens Estimator (TPE) Optimization},

author = {Rohan Anand and Joeran Beel},

url = {https://arxiv.org/abs/2008.13532},

year  = {2020},

date = {2020-01-01},

booktitle = {14th ACM Conference on Recommender Systems (RecSys)},

pages = {1–4},

abstract = {We introduce Auto-Surprise, an Automated Recommender System library. Auto-Surprise is an extension of the Surprise recommender system library and eases the algorithm selection and configuration process. Compared to out-of-the-box Surprise library, Auto-Surprise performs better when evaluated with MovieLens, Book Crossing and Jester Datasets. It may also result in the selection of an algorithm with significantly lower runtime. Compared to Surprise's grid search, Auto-Surprise performs equally well or slightly better in terms of RMSE, and is notably faster in finding the optimum hyperparameters.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Arambakam2020,

title = {Federated Meta-Learning: Democratizing Algorithm Selection Across Disciplines and Software Libraries},

author = {Mukesh Arambakam and Joeran Beel},

url = {https://www.automl.org/wp-content/uploads/2020/07/AutoML_2020_paper_39.pdf},

year  = {2020},

date = {2020-01-01},

booktitle = {7th ICML Workshop on Automated Machine Learning},

pages = {1–8},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Collins2019a,

title = {A First Analysis of Meta-Learned Per-Instance Algorithm Selection in Scholarly Recommender Systems},

author = {Andrew Collins and Joeran Beel},

year  = {2019},

date = {2019-01-01},

booktitle = {Workshop on Recommendation in Complex Scenarios, 13th ACM Conference on Recommender Systems (RecSys)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Scharpf2019,

title = {AnnoMathTeX - a Formula Annotation Recommender System for STEM Documents},

author = {Philipp Scharpf and Ian Mackerracher and Moritz Schubotz and Joeran Beel and Corinna Breitinger and Bela Gipp},

year  = {2019},

date = {2019-01-01},

booktitle = {13th ACM Conference on Recommender Systems (RecSys)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Edenhofer2019,

title = {Augmenting the DonorsChoose.org Corpus for Meta-Learning},

author = {Gordian Edenhofer and Andrew Collins and Akiko Aizawa and Joeran Beel},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of The 1st Interdisciplinary Workshop on Algorithm Selection and Meta-Learning in Information Retrieval (AMIR)},

pages = {32–38},

publisher = {CEUR-WS},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Hassan2019,

title = {BERT, ELMo, USE and InferSent Sentence Encoders: The Panacea for Research-Paper Recommendation?},

author = {Hebatallah A. Mohamed Hassan and Giuseppe Sansonetti and Fabio Gasparetti and Alessandro Micarelli and Joeran Beel},

year  = {2019},

date = {2019-01-01},

booktitle = {13th ACM Conference on Recommender Systems (RecSys)},

volume = {2431},

pages = {6–10},

publisher = {CEUR-WS},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Tunstead2019,

title = {Combating Stagnation in Reinforcement Learning Through 'Guided Learning' With 'Taught-Response Memory'},

author = {Keith Tunstead and Joeran Beel},

year  = {2019},

date = {2019-01-01},

booktitle = {3rd International Tutorial & Workshop on Interactive Adaptive Learning (IAL2019) at the ECML PKDD Conference},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2019b,

title = {Darwin & Goliath: Recommendations-As-a-Service with Automated Algorithm-Selection and White-Labels},

author = {Joeran Beel and Alan Griffin and Conor O'Shey},

editor = {Leif Azzopardi and Benno Stein and Norbert Fuhr and Philipp Mayr and Claudia Hauff and Djoerd Hiemstra},

doi = {10.1007/978-3-030-15719-7_27},

year  = {2019},

date = {2019-01-01},

booktitle = {13th ACM Conference on Recommender Systems (RecSys)},

volume = {11438},

pages = {213–219},

series = {Lecture Notes in Computer Science},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2019d,

title = {Data Pruning in Recommender Systems Research: Best-Practice or Malpractice?},

author = {Joeran Beel and Victor Brunel},

year  = {2019},

date = {2019-01-01},

booktitle = {13th ACM Conference on Recommender Systems (RecSys)},

volume = {2431},

pages = {26–30},

publisher = {CEUR-WS},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Collins2019,

title = {Document Embeddings vs. Keyphrases vs. Terms: A Large-Scale Online Evaluation in Digital Library Recommender Systems},

author = {Andrew Collins and Joeran Beel},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the ACM/IEEE-CS Joint Conference on Digital Libraries (JCDL)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Grennan2019,

title = {GIANT: The 1-Billion Annotated Synthetic Bibliographic-Reference-String Dataset for Deep Citation Parsing},

author = {Mark Grennan and Martin Schibel and Andrew Collins and Joeran Beel},

year  = {2019},

date = {2019-01-01},

booktitle = {27th AIAI Irish Conference on Artificial Intelligence and Cognitive Science},

pages = {101–112},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Collier2019,

title = {Memory-Augmented Neural Networks for Machine Translation},

author = {Mark Collier and Joeran Beel},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the Machine Translation (MT) Summit},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Bonello2019,

title = {Multi-stream Data Analytics for Enhanced Performance Prediction in Fantasy Football},

author = {Nicholas Bonello and Jeremy Debattista and Joeran Beel and Seamus Lawless},

year  = {2019},

date = {2019-01-01},

booktitle = {27th AIAI Irish Conference on Artificial Intelligence and Cognitive Science},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Tkaczyk2019,

title = {NaïveRole: Author-Contribution Extraction from Biomedical Publications},

author = {Dominika Tkaczyk and Andrew Collins and Joeran Beel},

year  = {2019},

date = {2019-01-01},

booktitle = {27th AIAI Irish Conference on Artificial Intelligence and Cognitive Science},

abstract = {Information about the contributions of individual authors to scientific publications is important for assessing authors' achievements. Some biomedical publications have a short section that describes authors' roles and contributions. It is usually written in natural language and hence author contributions cannot be trivially extracted in a machine-readable format. In this paper, we present 1) A statistical analysis of roles in author contributions sections, and 2) NaïveRole, a novel approach to extract structured authors' roles from author contribution sections. For the first part, we used co-clustering techniques, as well as Open Information Extraction, to semi-automatically discover the popular roles within a corpus of 2,000 contributions sections from PubMed Central. The discovered roles were used to automatically build a training set for NaïveRole, our role extractor approach, based on Naïve Bayes. NaïveRole extracts roles with a micro-averaged precision of 0.68, recall of 0.48 and F1 of 0.57. It is, to the best of our knowledge, the first attempt to automatically extract author roles from research papers. This paper is an extended version of a previous poster published at JCDL 2018.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{OSullivan2019,

title = {Predicting the Outcome of Judicial Decisions made by the European Court of Human Rights},

author = {Conor O'Sullivan and Joeran Beel},

year  = {2019},

date = {2019-01-01},

booktitle = {27th AIAI Irish Conference on Artificial Intelligence and Cognitive Science},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2019a,

title = {Preface: The 1st Interdisciplinary Workshop on Algorithm Selection and Meta-Learning in Information Retrieval (AMIR)},

author = {Joeran Beel and Lars Kotthoff},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceddings of The 1st Interdisciplinary Workshop on Algorithm Selection and Meta-Learning in Information Retrieval (AMIR)},

pages = {1–9},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2019c,

title = {Proposal for the 1st Interdisciplinary Workshop on Algorithm Selection and Meta-Learning in Information Retrieval (AMIR)},

author = {Joeran Beel and Lars Kotthoff},

editor = {L. Azzopardi and B. Stein and N. Fuhr and P. Mayr and C. Hauff and D. Hiemstra},

doi = {10.1007/978-3-030-15719-7_53},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the 41st European Conference on Information Retrieval (ECIR)},

volume = {11438},

pages = {383–388},

publisher = {Springer},

series = {Lecture Notes in Computer Science book series (LNCS)},

abstract = {The algorithm selection problem describes the challenge of identifying 

	the best algorithm for a given problem space. In many domains, particularly 

	artificial intelligence, the algorithm selection problem is well 

	studied, and various approaches and tools exist to tackle it in practice. 

	Especially through meta-learning impressive performance improvements 

	have been achieved. The information retrieval (IR) community, however, 

	has paid little attention to the algorithm selection problem, although 

	the problem is highly relevant in information retrieval. This workshop 

	will bring together researchers from the fields of algorithm selection 

	and meta-learning as well as information retrieval. We aim to raise 

	the awareness in the IR community of the algorithm selection problem; 

	identify the potential for automatic algorithm selection in information 

	retrieval; and explore possible solutions for this context. In particular, 

	we will explore to what extent existing solutions to the algorithm 

	selection problem from other domains can be applied in information 

	retrieval, and also how techniques from IR can be used for automated 

	algorithm selection and meta-learning.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2019e,

title = {RARD II: The 94 Million Related-Article Recommendation Dataset},

author = {Joeran Beel and Barry Smyth and Andrew Collins},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the 1st Interdisciplinary Workshop on Algorithm Selection and Meta-Learning in Information Retrieval (AMIR)},

pages = {39–55},

publisher = {CEUR-WS},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Collins2018a,

title = {A Novel Approach to Recommendation Algorithm Selection using Meta-Learning},

author = {Andrew Collins and Dominika Tkaczyk and Joeran Beel},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of the 26th Irish Conference on Artificial Intelligence and Cognitive Science (AICS)},

volume = {2259},

pages = {210–219},

publisher = {CEUR-WS},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Collier2018a,

title = {An Empirical Comparison of Syllabuses for Curriculum Learning},

author = {Mark Collier and Joeran Beel},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of the 26th Irish Conference on Artificial Intelligence and Cognitive Science (AICS)},

volume = {2259},

pages = {150–161},

publisher = {CEUR-WS},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Collier2018,

title = {Implementing Neural Turing Machines},

author = {Mark Collier and Joeran Beel},

editor = {Věra Kůrková and Yannis Manolopoulos and Barbara Hammer and Lazaros Iliadis and Ilias Maglogiannis},

doi = {10.1007/978-3-030-01424-7_10},

isbn = {978-3-030-01424-7},

year  = {2018},

date = {2018-01-01},

booktitle = {27th International Conference on Artificial Neural Networks (ICANN)},

pages = {94–104},

publisher = {Springer International Publishing},

address = {Cham},

series = {Lecture Notes in Computer Science},

abstract = {Neural Turing Machines (NTMs) are an instance of Memory Augmented 

	Neural Networks, a new class of recurrent neural networks which decouple 

	computation from memory by introducing an external memory unit. NTMs 

	have demonstrated superior performance over Long Short-Term Memory 

	Cells in several sequence learning tasks. A number of open source 

	implementations of NTMs exist but are unstable during training and/or 

	fail to replicate the reported performance of NTMs. This paper presents 

	the details of our successful implementation of a NTM. Our implementation 

	learns to solve three sequential learning tasks from the original 

	NTM paper. We find that the choice of memory contents initialization 

	scheme is crucial in successfully implementing a NTM. Networks with 

	memory contents initialized to small constant values converge on 

	average 2 times faster than the next best memory contents initialization 

	scheme.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Tkaczyk2018a,

title = {Machine Learning vs. Rules and Out-of-the-Box vs. Retrained: An Evaluation of Open-Source Bibliographic Reference and Citation Parsers},

author = {Dominika Tkaczyk and Andrew Collins and Paraic Sheridan and Joeran Beel},

url = {http://doi.acm.org/10.1145/3197026.3197048},

doi = {10.1145/3197026.3197048},

isbn = {978-1-4503-5178-2},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries},

pages = {99–108},

publisher = {ACM},

address = {Fort Worth, Texas, USA},

series = {JCDL '18},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Collins2018b,

title = {One-at-a-time: A Meta-Learning Recommender-System for Recommendation-Algorithm Selection on Micro Level},

author = {Andrew Collins and Dominika Tkaczyk and Joeran Beel},

year  = {2018},

date = {2018-01-01},

booktitle = {arXiv:1805.12118},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Tkaczyk2018,

title = {ParsRec: A Meta-Learning Recommender System for Bibliographic Reference Parsing Tools},

author = {Dominika Tkaczyk and Paraic Sheridan and Joeran Beel},

url = {http://doi.acm.org/10.1145/3197026.3203907},

doi = {10.1145/3197026.3203907},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of the 12th ACM Conference on Recommender Systems (RecSys)},

pages = {387–388},

publisher = {ACM},

address = {Fort Worth, Texas, USA},

series = {JCDL '18},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Tkaczyk2018b,

title = {ParsRec: A Novel Meta-Learning Approach to Recommending Bibliographic Reference Parsers},

author = {Dominika Tkaczyk and Rohit Gupta and Riccardo Cinti and Joeran Beel},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of the 26th Irish Conference on Artificial Intelligence and Cognitive Science (AICS)},

volume = {2259},

number = {1},

pages = {162–173},

publisher = {CEUR-WS},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Collins2018,

title = {Position Bias in Recommender Systems for Digital Libraries},

author = {Andrew Collins and Dominika Tkaczyk and Akiko Aizawa and Joeran Beel},

doi = {10.1007/978-3-319-78105-1_37},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of the iConference},

volume = {10766},

pages = {335-344},

publisher = {Springer},

series = {Lecture Notes on Computer Science (LNCS)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Brennan2018,

title = {Preface: The 26th AIAI Irish Conference on Artificial Intelligence and Cognitive Science (AICS 2018)},

author = {Rob Brennan and Joeran Beel and Ruth Byrne and Jeremy Debattista},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of the 26th Irish Conference on Artificial Intelligence and Cognitive Science (AICS)},

volume = {2259},

pages = {1–7},

publisher = {CEUR-WS},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2018,

title = {The Architecture of Mr. DLib’s Scientific Recommender-System API},

author = {Joeran Beel and Andrew Collins and Akiko Aizawa},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of the 26th Irish Conference on Artificial Intelligence and Cognitive Science (AICS)},

volume = {2259},

pages = {78–89},

publisher = {CEUR-WS},

abstract = {Recommender systems in academia are not widely available. This may 

	be in part due to the difficulty and cost of developing and maintaining 

	recommender systems. Many operators of academic products such as 

	digital libraries and reference managers avoid this effort, although 

	a recommender system could provide significant benefits to their 

	users. In this paper, we introduce Mr. DLib’s “Recommendations as-a-Service" 

	(RaaS) API that allows operators of academic products to easily integrate 

	a scientific recommender system into their products. Mr. DLib generates 

	recommendations for research articles but in the future, recommendations 

	may include call for papers, grants, etc. Operators of academic products 

	can request recommendations from Mr. DLib and display these recommendations 

	to their users. Mr. DLib can be integrated in just a few hours or 

	days; creating an equivalent recommender system from scratch would 

	require several months for an academic operator. Mr. DLib has been 

	used by GESIS´ Sowiport and by the reference manager JabRef. Mr. 

	DLib is open source and its goal is to facilitate the application 

	of, and research on, scientific recommender systems. In this paper, 

	we present the motivation for Mr. DLib, the architecture and details 

	about the effectiveness. Mr. DLib has delivered 94m recommendations 

	over a span of two years with an average click-through rate of 0.12%.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Langer2017,

title = {Apache Lucene as Content-Based-Filtering Recommender System: 3 Lessons Learned},

author = {Stefan Langer and Joeran Beel},

year  = {2017},

date = {2017-01-01},

booktitle = {5th International Workshop on Bibliometric-enhanced Information Retrieval (BIR) at the 39th European Conference on Information Retrieval (ECIR)},

pages = {85-92},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2017,

title = {Evaluating the CC-IDF citation-weighting scheme: How effectively can 'Inverse Document Frequency' (IDF) be applied to references?},

author = {Joeran Beel and Corinna Breitinger and Stefan Langer},

year  = {2017},

date = {2017-01-01},

booktitle = {Proceedings of the 12th iConference},

abstract = {In the domain of academic search engines and research-paper recommender 

	systems, CC-IDF is a common citation-weighting scheme that is used 

	to calculate semantic relatedness between documents. CC-IDF adopts 

	the principles of the popular term-weighting scheme TF-IDF and assumes 

	that if a rare academic citation is shared by two documents then 

	this occurrence should receive a higher weight than if the citation 

	is shared among a large number of documents. Although CC-IDF is in 

	common use, we found no empirical evaluation and comparison of CC-IDF 

	with plain citation weight (CC-Only). Therefore, we conducted such 

	an evaluation and present the results in this paper. The evaluation 

	was conducted with real users of the recommender system Docear. The 

	effectiveness of CC-IDF and CC-Only was measured using click-through 

	rate (CTR). For 238,681 delivered recommendations, CC-IDF had about 

	the same effectiveness as CC-Only (CTR of 6.15% vs. 6.23%). In other 

	words, CC-IDF was not more effective than CC-Only, which is a surprising 

	result. We provide a number of potential reasons and suggest to conduct 

	further research to understand the principles of CC-IDF in more detail.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beierle2017,

title = {Exploring Choice Overload in Related-Article Recommendations in Digital Libraries},

author = {Felix Beierle and Akiko Aizawa and Joeran Beel},

year  = {2017},

date = {2017-01-01},

booktitle = {5th International Workshop on Bibliometric-enhanced Information Retrieval (BIR) at the 39th European Conference on Information Retrieval (ECIR)},

pages = {51–61},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Feyer2017,

title = {Integration of the Scientific Recommender System Mr. DLib into the Reference Manager JabRef},

author = {Stefan Feyer and Sophie Siebert and Bela Gipp and Akiko Aizawa and Joeran Beel},

year  = {2017},

date = {2017-01-01},

booktitle = {Proceedings of the 39th European Conference on Information Retrieval (ECIR)},

pages = {770–774},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2017c,

title = {Mr. DLib: Recommendations-as-a-service (RaaS) for Academia},

author = {Joeran Beel and Akiko Aizawa and Corinna Breitinger and Bela Gipp},

url = {http://dl.acm.org/citation.cfm?id=3200334.3200389},

isbn = {978-1-5386-3861-3},

year  = {2017},

date = {2017-01-01},

booktitle = {Proceedings of the 17th ACM/IEEE Joint Conference on Digital Libraries},

pages = {313–314},

publisher = {IEEE Press},

address = {Toronto, Ontario, Canada},

series = {JCDL '17},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2017e,

title = {Real-World Recommender Systems for Academia: The Gain and Pain in Developing, Operating, and Researching them},

author = {Joeran Beel and Siddharth Dinesh},

editor = {Philipp Mayr and Ingo Frommholz and Guillaume Cabanac},

url = {http://ceur-ws.org/Vol-1823/paper1.pdf},

year  = {2017},

date = {2017-01-01},

booktitle = {Proceedings of the Fifth Workshop on Bibliometric-enhanced Information Retrieval (BIR) co-located with the 39th European Conference on Information Retrieval (ECIR 2017)},

volume = {1823},

pages = {6-17},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2017f,

title = {Real-World Recommender Systems for Academia: The Gain and Pain in Developing, Operating, and Researching them [Long Version]},

author = {Joeran Beel and Siddharth Dinesh},

url = {http://dx.doi.org/10.7910/DVN/HFIV1A},

doi = {10.7910/DVN/HFIV1A},

year  = {2017},

date = {2017-01-01},

booktitle = {arxiv pre-print. https://arxiv.org/abs/1704.00156},

publisher = {Harvard Dataverse},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2017d,

title = {Stereotype and Most-Popular Recommendations in the Digital Library Sowiport},

author = {Joeran Beel and Siddharth Dinesh and Philipp Mayr and Zeljko Carevic and Jain Raghvendra},

year  = {2017},

date = {2017-01-01},

booktitle = {Proceedings of the 15th International Symposium of Information Science (ISI)},

volume = {23},

number = {7/8},

pages = {96–108},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2017a,

title = {TF-IDuF: A Novel Term-Weighting Scheme for User Modeling based on Users' Personal Document Collections},

author = {Joeran Beel and Stefan Langer and Bela Gipp},

doi = {10.13140/RG.2.2.18759.39842},

year  = {2017},

date = {2017-01-01},

booktitle = {Proceedings of the 12th iConference},

abstract = {TF-IDF is one of the most popular term-weighting schemes, and is applied 

	by search engines, recommender systems, and user modeling engines. 

	With regard to user modeling and recommender systems, we see two 

	shortcomings of TF-IDF. First, calculating IDF requires access to 

	the document corpus from which recommendations are made. Such access 

	is not always given in a user-modeling or recommender system. Second, 

	TF-IDF ignores information from a user’s personal document 

	collection, which could – so we hypothesize – enhance 

	the user modeling process. In this paper, we introduce TF-IDuF as 

	a term-weighting scheme that does not require access to the general 

	document corpus and that considers information from the users’ 

	personal document collections. We evaluated the effectiveness of 

	TF-IDuF compared to TF-IDF and TF-Only and found that TF-IDF and 

	TF-IDuF perform similarly (click-through rates (CTR) of 5.09% vs. 

	5.14%), and both are around 25% more effective than TF-Only (CTR 

	of 4.06%) for recommending research papers. Consequently, we conclude 

	that TF-IDuF could be a promising term-weighting scheme, especially 

	when access to the document corpus for recommendations is not possible, 

	and thus classic IDF cannot be computed. It is also notable that 

	TF-IDuF and TF-IDF are not exclusive, so that both metrics may be 

	combined to a more effective term-weighting scheme.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2015a,

title = {A Comparison of Offline Evaluations, Online Evaluations, and User Studies in the Context of Research-Paper Recommender Systems},

author = {Joeran Beel and Stefan Langer},

editor = {Sarantos Kapidakis and Cezary Mazurek and Marcin Werla},

doi = {10.1007/978-3-319-24592-8_12},

year  = {2015},

date = {2015-01-01},

booktitle = {Proceedings of the 19th International Conference on Theory and Practice of Digital Libraries (TPDL)},

volume = {9316},

pages = {153-168},

series = {Lecture Notes in Computer Science},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2015b,

title = {Exploring the Potential of User Modeling based on Mind Maps},

author = {Joeran Beel and Stefan Langer and Georgia M. Kapitsaki and Corinna Breitinger and Bela Gipp},

editor = {Francesco Ricci and Kalina Bontcheva and Owen Conlan and Séamus Lawless},

doi = {10.1007/978-3-319-20267-9_1},

year  = {2015},

date = {2015-01-01},

booktitle = {Proceedings of the 23rd Conference on User Modelling, Adaptation and Personalization (UMAP)},

volume = {9146},

pages = {3-17},

publisher = {Springer},

series = {Lecture Notes of Computer Science},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Langer2014,

title = {The Comparability of Recommender System Evaluations and Characteristics of Docear's Users},

author = {Stefan Langer and Joeran Beel},

year  = {2014},

date = {2014-01-01},

booktitle = {Proceedings of the Workshop on Recommender Systems Evaluation: Dimensions and Design (REDD) at the 2014 ACM Conference Series on Recommender Systems (RecSys)},

pages = {1–6},

publisher = {CEUR-WS},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2014a,

title = {Utilizing Mind-Maps for Information Retrieval and User Modelling},

author = {Joeran Beel and Stefan Langer and Marcel Genzmehr and Bela Gipp},

editor = {Vania Dimitrova and Tsvi Kuflik and David Chin and Francesco Ricci and Peter Dolog and Geert-Jan Houben},

doi = {10.1007/978-3-319-08786-3_26},

year  = {2014},

date = {2014-01-01},

booktitle = {Proceedings of the 22nd Conference on User Modelling, Adaption, and Personalization (UMAP)},

volume = {8538},

pages = {301-313},

publisher = {Springer},

series = {Lecture Notes in Computer Science},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2013e,

title = {Persistence in Recommender Systems: Giving the Same Recommendations to the Same Users Multiple Times},

author = {Joeran Beel and Stefan Langer and Marcel Genzmehr and Andreas Nürnberger},

editor = {Trond Aalberg and Milena Dobreva and Christos Papatheodorou and Giannis Tsakonas and Charles Farrugia},

year  = {2013},

date = {2013-09-01},

booktitle = {Proceedings of the 17th International Conference on Theory and Practice of Digital Libraries (TPDL 2013)},

volume = {8092},

pages = {390–394},

publisher = {Springer},

address = {Valletta, Malta},

series = {Lecture Notes of Computer Science (LNCS)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2013a,

title = {Sponsored vs. Organic (Research Paper) Recommendations and the Impact of Labeling},

author = {Joeran Beel and Stefan Langer and Marcel Genzmehr},

editor = {Trond Aalberg and Milena Dobreva and Christos Papatheodorou and Giannis Tsakonas and Charles Farrugia},

year  = {2013},

date = {2013-09-01},

booktitle = {Proceedings of the 17th International Conference on Theory and Practice of Digital Libraries (TPDL 2013)},

pages = {395–399},

address = {Valletta, Malta},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2013f,

title = {The Impact of Demographics (Age and Gender) and Other User Characteristics on Evaluating Recommender Systems},

author = {Joeran Beel and Stefan Langer and Andreas Nuenberger and Marcel Genzmehr},

editor = {Trond Aalberg and Milena Dobreva and Christos Papatheodorou and Giannis Tsakonas and Charles Farrugia},

year  = {2013},

date = {2013-09-01},

booktitle = {Proceedings of the 17th International Conference on Theory and Practice of Digital Libraries (TPDL 2013)},

pages = {400–404},

publisher = {Springer},

address = {Valletta, Malta},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2013d,

title = {A Comparative Analysis of Offline and Online Evaluations and Discussion of Research Paper Recommender System Evaluation},

author = {Joeran Beel and Stefan Langer and Marcel Genzmehr and Bela Gipp and Andreas Nürnberger},

doi = {10.1145/2532508.2532511},

year  = {2013},

date = {2013-01-01},

booktitle = {Proceedings of the Workshop on Reproducibility and Replication in Recommender Systems Evaluation (RepSys) at the ACM Recommender System Conference (RecSys)},

pages = {7-14},

series = {ACM International Conference Proceedings Series (ICPS)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2013b,

title = {Docears PDF Inspector: Title Extraction from PDF files},

author = {Joeran Beel and Stefan Langer and Marcel Genzmehr and Christoph Müller},

doi = {10.1145/2467696.2467789},

year  = {2013},

date = {2013-01-01},

booktitle = {Proceedings of the 13th ACM/IEEE-CS Joint Conference on Digital Libraries (JCDL'13)},

pages = {443-444},

publisher = {ACM},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Lipinski2013,

title = {Evaluation of Header Metadata Extraction Approaches and Tools for Scientific PDF Documents},

author = {Mario Lipinski and Kevin Yao and Corinna Breitinger and Joeran Beel and Bela Gipp},

year  = {2013},

date = {2013-01-01},

booktitle = {Proceedings of the 13th ACM/IEEE-CS joint conference on Digital libraries (JCDL'13)},

pages = {385-386},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2013c,

title = {Introducing Docear's Research Paper Recommender System},

author = {Joeran Beel and Stefan Langer and Marcel Genzmehr and Andreas Nuernberger},

doi = {10.1145/2467696.2467786},

year  = {2013},

date = {2013-01-01},

booktitle = {Proceedings of the 13th ACM/IEEE-CS Joint Conference on Digital Libraries (JCDL'13)},

pages = {459-460},

publisher = {ACM},

series = {ACM International Conference Proceedings Series (ICPS)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2011d,

title = {An Exploratory Analysis of Mind Maps},

author = {Joeran Beel and Stefan Langer},

doi = {10.1145/2034691.2034709},

year  = {2011},

date = {2011-01-01},

booktitle = {Proceedings of the 11th ACM Symposium on Document Engineering (DocEng'11)},

pages = {81-84},

publisher = {ACM},

note = {Available at http://docear.org},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Gipp2011a,

title = {Comparative Evaluation of Text- and Citation-based Plagiarism Detection Approaches using GuttenPlag},

author = {Bela Gipp and Norman Meuschke and Joeran Beel},

doi = {10.1145/1998076.1998124},

year  = {2011},

date = {2011-01-01},

booktitle = {Proceedings of 11th ACM/IEEE-CS Joint Conference on Digital Libraries (JCDL'11)},

pages = {255–258},

publisher = {ACM},

address = {Ottawa, Canada},

abstract = {Various approaches for plagiarism detection exist. All are based on 

	more or less sophisticated text analysis methods such as string matching, 

	fingerprinting or style comparison. In this paper a new approach 

	called Citation-based Plagiarism Detection is evaluated using a doctoral 

	thesis, in which a volunteer crowd-sourcing project called GuttenPlag 

	identified substantial amounts of plagiarism through careful manual 

	inspection. This new approach is able to identify similar and plagiarized 

	documents based on the citations used in the text. It is shown that 

	citation-based plagiarism detection performs significantly better 

	than text-based procedures in identifying strong paraphrasing, translation 

	and some idea plagiarism. Detection rates can be improved by combining 

	citation-based with text-based plagiarism detection.},

note = {Available at: url http://sciplore.org/pub},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2011b,

title = {Introducing Mr. DLib, a Machine-readable Digital Library},

author = {Joeran Beel and Bela Gipp and Stefan Langer and Marcel Genzmehr and Erik Wilde and Andreas Nuernberger and Jim Pitman},

doi = {10.1145/1998076.1998187},

year  = {2011},

date = {2011-01-01},

booktitle = {Proceedings of the 11th ACM/IEEE Joint Conference on Digital Libraries (JCDL`11)},

pages = {463–464},

publisher = {ACM},

series = {JCDL '11},

note = {Available at http://docear.org},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Gipp2010b,

title = {Link Proximity Analysis - Clustering Websites by Examining Link Proximity},

author = {Bela Gipp and Adriana Taylor and Joeran Beel},

editor = {M. Lalmas and J. Jose and A. Rauber and F. Sebastiani and I. Frommholz},

year  = {2010},

date = {2010-09-01},

booktitle = {Proceedings of the 14th European Conference on Digital Libraries (ECDL'10): Research and Advanced Technology for Digital Libraries},

volume = {6273},

pages = {449–452},

publisher = {Springer},

series = {Lecture Notes of Computer Science (LNCS)},

note = {Available at: url http://sciplore.org/pub},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2010g,

title = {SciPlore Xtract: Extracting Titles from Scientific PDF Documents by Analyzing Style Information (Font Size)},

author = {Joeran Beel and Bela Gipp and Ammar Shaker and Nick Friedrich},

editor = {M. Lalmas and J. Jose and A. Rauber and F. Sebastiani and I. Frommholz},

year  = {2010},

date = {2010-09-01},

booktitle = {Research and Advanced Technology for Digital Libraries, Proceedings of the 14th European Conference on Digital Libraries (ECDL'10)},

volume = {6273},

pages = {413–416},

publisher = {Springer},

address = {Glasgow (UK)},

series = {Lecture Notes of Computer Science (LNCS)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2010e,

title = {Enhancing search applications by utilizing mind maps},

author = {Joeran Beel and Bela Gipp},

year  = {2010},

date = {2010-06-01},

booktitle = {Proceedings of the 21st ACM Conference on Hypertext and Hypermedia (HT'10)},

pages = {303–304},

publisher = {ACM},

address = {Toronto (CA)},

note = {Available at http://docear.org},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2010a,

title = {On the Robustness of Google Scholar Against Spam},

author = {Joeran Beel and Bela Gipp},

doi = {10.1145/1810617.1810683},

year  = {2010},

date = {2010-06-01},

booktitle = {Proceedings of the 21st ACM Conference on Hypertext and Hypermedia (HT'10)},

pages = {297–298},

publisher = {ACM},

address = {Toronto (CA)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Gipp2010a,

title = {Citation Based Plagiarism Detection - a New Approach to Identify Plagiarized Work Language Independently},

author = {Bela Gipp and Joeran Beel},

doi = {10.1145/1810617.1810671},

year  = {2010},

date = {2010-01-01},

booktitle = {Proceedings of the 21st ACM Conference on Hypertext and Hypermedia},

pages = {273–274},

publisher = {ACM},

address = {Toronto, Ontario, Canada},

note = {Available at: url http://sciplore.org/pub},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Gipp2010,

title = {Integrating Citation Proximity Analysis into Google Books and Google Scholar},

author = {Bela Gipp and Joeran Beel},

year  = {2010},

date = {2010-01-01},

address = {Mountain View (USA)},

organization = {Google Inc.},

note = {Invited Talk.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2010b,

title = {Link analysis in mind maps: a new approach to determining document relatedness},

author = {Joeran Beel and Bela. Gipp},

editor = {M Lalmas and J Jose and A Rauber and R Sebastiani and I Frommholz},

year  = {2010},

date = {2010-01-01},

booktitle = {Proceedings of the 4th International Conference on Ubiquitous Information Management and Communication (ICUIMC '10)},

volume = {6273},

pages = {38:1–38:5},

publisher = {Springer},

address = {Glasgow (UK)},

organization = {ACM},

series = {Lecture Notes of Computer Science (LNCS)},

note = {Doctoral Consortium},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2010c,

title = {Mind Maps, Information Retrieval, and SciPlore MinṂapping},

author = {Joeran Beel},

year  = {2010},

date = {2010-01-01},

booktitle = {Seminar on Information Access},

address = {Berkeley (USA)},

organization = {School of Information, University of California Berkeley},

note = {Invited Talk.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2009f,

title = {Information Retrieval on Mind Maps - What could it be good for?},

author = {Joeran Beel and Bela Gipp and Jan-Olaf Stiller},

url = {https://ieeexplore.ieee.org/abstract/document/5364172 

https://isg.beel.org/pubs/Information Retrieval on Mind Maps - What could it be good for –preprint.pdf},

year  = {2009},

date = {2009-11-01},

booktitle = {Proceedings of the 5th International Conference on Collaborative Computing: Networking, Applications and Worksharing (CollaborateCom'09)},

pages = {1–4},

publisher = {IEEE},

address = {Washington (USA)},

abstract = {Mind maps are used by millions of people. In this paper we present how information retrieval on mind maps could be used to enhance expert search, document summarization, keyword based search engines, document recommender systems and determining word relatedness. For instance, words in a mind map could be used for creating a skill profile of the mind maps' author and hence enhance expert search. This paper is a research-in-progress paper which means no research results are presented but only ideas.},

note = {Available at http://docear.org},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2009e,

title = {Could Mind Maps Be Used To Improve Academic Search Engines?},

author = {Joeran Beel and Bela Gipp and Jan-Olaf Stiller},

editor = {S. I. Ao and C. Douglas and W. S. Grundfest and J. Burgstone},

url = {http://www.iaeng.org/publication/WCECS2009/WCECS2009_pp832-834.pdf},

year  = {2009},

date = {2009-10-01},

booktitle = {International Conference on Machine Learning and Data Analysis (ICMLDA'09)},

volume = {2},

pages = {832–834},

publisher = {Newswood Limited},

address = {Berkeley (USA)},

organization = {International Association of Engineers (IAENG)},

series = {Lecture Notes in Engineering and Computer Science},

abstract = {In this paper the idea of mind map mining is presented. We propose that information retrieved from mind maps could improve academic search engines. The basic idea is that from a mind map’s text, keywords can be retrieved to describe research articles referenced by the mind map. So far, we have not conducted any research on mind map mining. Therefore this paper should only be seen as an early research in progress paper, outlining the ideas and aiming to stimulate a discussion. We start the discussion in this paper by presenting some challenges that mind map mining is likely to face.},

note = {Available at http://docear.org},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Gipp2009,

title = {Identifying Related Documents For Research Paper Recommender By CPA And COA},

author = {Bela Gipp and Joeran Beel},

editor = {S. I. Ao and C. Douglas and W. S. Grundfest and J. Burgstone},

url = {https://www.iaeng.org/publication/WCECS2009/WCECS2009_pp636-639.pdf},

isbn = {978-988-17012-6-8},

year  = {2009},

date = {2009-10-01},

booktitle = {Proceedings of The World Congress on Engineering and Computer Science 2009},

volume = {1},

pages = {636–639},

publisher = {Newswood Limited},

address = {Berkeley (USA)},

organization = {International Association of Engineers (IAENG)},

series = {Lecture Notes in Engineering and Computer Science},

abstract = {This work-in-progress paper introduces two new approaches called Citation Proximity Analysis (CPA) and Citation Order Analysis (COA). They can be applied to identify related documents for the purpose of research paper recommender systems. CPA is a variant of co-citation analysis that additionally considers the proximity of citations to each other within an article’s full-text. The underlying idea is that the closer citations are to each other in a document, the more likely it is that the cited documents are related. For example, citations listed in the same sentence are more likely to express related thoughts than citations listed only in the same section. In COA, the order of citations are considered, allowing the identification of a text similar to one that has been translated from language A to language B, as the citations would still occur in the same order. However, it is also shown that CPA and COA cannot replace text analysis and existing citation analysis approaches for research paper recommender systems since they all have their own strengths and weaknesses.},

note = {Available at: url http://sciplore.org/pub},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2009,

title = {Information Retrieval in Mind Maps zum Verbessern von Suchapplikationen},

author = {Joeran Beel},

editor = {H. -K. Arndt and H. Krcmar},

year  = {2009},

date = {2009-10-01},

booktitle = {Very Large Business Applications (VLBA): Systemlandschaften der Zukunft},

volume = {3},

pages = {139–152},

publisher = {Shaker Verlag},

address = {Magdeburg},

series = {Workshop des Centers for Very Large Business Applications (CVLBA)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Gipp2009a,

title = {Citation Proximity Analysis (CPA) - A new approach for identifying related work based on Co-Citation Analysis},

author = {Bela Gipp and Joeran Beel},

editor = {Birger Larsen and Jacqueline Leta},

year  = {2009},

date = {2009-07-01},

booktitle = {Proceedings of the 12th International Conference on Scientometrics and Informetrics (ISSI'09)},

volume = {2},

pages = {571–575},

publisher = {International Society for Scientometrics and Informetrics},

address = {Rio de Janeiro (Brazil)},

note = {ISSN 2175-1935. Available at: url http://sciplore.org/pub},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2009b,

title = {Google Scholar's Ranking Algorithm: An Introductory Overview},

author = {Joeran Beel and Bela Gipp},

editor = {Birger Larsen and Jacqueline Leta},

url = {https://isg.beel.org/pubs/Google Scholar's Ranking Algorithm – An Introductory Overview – preprint.pdf},

year  = {2009},

date = {2009-07-01},

booktitle = {Proceedings of the 12th International Conference on Scientometrics and Informetrics (ISSI'09)},

volume = {1},

pages = {230–241},

publisher = {International Society for Scientometrics and Informetrics},

address = {Rio de Janeiro (Brazil)},

abstract = {Google Scholar is one of the major academic search engines but its ranking algorithm for academic articles is unknown. We performed the first steps to reverse-engineering Google Scholar’s ranking algorithm and present the results in this research-in-progress paper. The results are: Citation counts is the highest weighed factor in Google Scholar’s ranking algorithm. Therefore, highly cited articles are found significantly more often in higher positions than articles that have been cited less often. As a consequence, Google Scholar seems to be more suitable for finding standard literature than gems or articles by authors advancing a new or different view from the mainstream. However, interesting exceptions for some search queries occurred. Moreover, the occurrence of a search term in an article’s title seems to have a strong impact on the article’s ranking. The impact of search term frequencies in an article’s full text is weak. That means it makes no difference in an article’s ranking if the article contains the query terms only once or multiple times. It was further researched whether the name of an author or journal has an impact on the ranking and whether differences exist between the ranking algorithms of different search modes that Google Scholar offers. The answer in both of these cases was "yes". The results of our research may help authors to optimize their articles for Google Scholar and enable researchers to estimate the usefulness of Google Scholar with respect to their search intention and hence the need to use further academic search engines or databases.},

note = {Available at http://docear.org},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2009c,

title = {Google Scholar's Ranking Algorithm: The Impact of Articles' Age (An Empirical Study)},

author = {Joeran Beel and Bela Gipp},

editor = {Shahram Latifi},

url = {https://ieeexplore.ieee.org/abstract/document/5070610 

https://isg.beel.org/pubs/Google Scholar's Ranking Algorithm - The Impact of Articles' Age (An Empirical Study) – preprint.pdf},

doi = {10.1109/ITNG.2009.317},

year  = {2009},

date = {2009-04-01},

booktitle = {Proceedings of the 6th International Conference on Information Technology: New Generations (ITNG'09)},

pages = {160–164},

publisher = {IEEE},

address = {Las Vegas (USA)},

abstract = {Google Scholar is one of the major academic search engines but its ranking algorithm for academic articles is unknown. In recent studies we partly reverse-engineered the algorithm. This paper presents the results of our third study. While the first study provided a broad overview and the second study focused on researching the impact of citation counts, the current study focused on analyzing the correlation of an articlepsilas age and its ranking in Google Scholar. In other words, it was analyzed if older/recent published articles are more/less likely to appear in a top position in Google Scholarpsilas result lists. For our study, age and rankings of 1,099,749 articles retrieved via 2,100 search queries were analyzed. The analysis revealed that an articlepsilas age seems to play no significant role in Google Scholarpsilas ranking algorithm. It is also discussed why this might lead to a suboptimal ranking.},

note = {Available at http://docear.org},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2009a,

title = {Google Scholar's Ranking Algorithm: The Impact of Citation Counts (An Empirical Study)},

author = {Joeran Beel and Bela Gipp},

url = {https://ieeexplore.ieee.org/document/5089308 

https://isg.beel.org/pubs/Google Scholar's Ranking Algorithm - The Impact of Articles' Age (An Empirical Study) – preprint.pdf},

doi = {10.1109/RCIS.2009.5089308},

year  = {2009},

date = {2009-04-01},

booktitle = {Proceedings of the 3rd IEEE International Conference on Research Challenges in Information Science (RCIS'09)},

pages = {439–446},

publisher = {IEEE},

address = {Fez (Morocco)},

abstract = {Google Scholar is one of the major academic search engines but its ranking algorithm for academic articles is unknown. In a recent study we partly reverse-engineered the algorithm. This paper presents the results of our second study. While the previous study provided a broad overview, the current study focused on analyzing the correlation of an article's citation count and its ranking in Google Scholar. For this study, citation counts and rankings of 1,364,757 articles were analyzed. Some results of our first study were confirmed: Citation counts is the highest weighed factor in Google Scholar's ranking algorithm. Highly cited articles are found significantly more often in higher positions than articles that are cited less often. Therefore, Google Scholar seems to be more suitable for searching standard literature than for gems or articles by authors advancing a view different from the mainstream. However, interesting exceptions for some search queries occurred. In some cases no correlation existed; in others bizarre patterns were recognizable, suggesting that citation counts sometimes have no impact at all on articles' rankings.},

note = {Available at http://docear.org},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Gipp2009b,

title = {Scienstein: A Research Paper Recommender System},

author = {Bela Gipp and Joeran Beel and Christian Hentschel},

year  = {2009},

date = {2009-01-01},

booktitle = {Proceedings of the International Conference on Emerging Trends in Computing (ICETiC'09)},

pages = {309–315},

publisher = {IEEE},

address = {Virudhunagar (India)},

organization = {Kamaraj College of Engineering and Technology India},

note = {Available at: url http://sciplore.org/pub},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Beel2008,

title = {The Potential of Collaborative Document Evaluation for Science},

author = {Joeran Beel and Bela Gipp},

editor = {George Buchanan and Masood Masoodian and Sally Jo Cunningham},

url = {https://link.springer.com/chapter/10.1007/978-3-540-89533-6_48 

https://isg.beel.org/pubs/The Potential of Collaborative Document Evaluation for Science - public preprint.pdf},

doi = {10.1007/978-3-540-89533-6},

isbn = {978-3-540-89532-9},

year  = {2008},

date = {2008-12-01},

booktitle = {11th International Conference on Asia-Pacific Digital Libraries (ICADL'08) Proceedings},

volume = {5362},

pages = {375–378},

publisher = {Springer},

address = {Heidelberg (Germany)},

series = {Lecture Notes in Computer Science (LNCS)},

abstract = {Peer review and citation analysis are the two most common approaches for quality evaluations of scientific publications, although they are subject to criticism for various reasons. This paper outlines the problems of citation analysis and peer review and introduces Collaborative Document Evaluation as a supplement or possibly even a substitute. Collaborative Document Evaluation aims to enable the readers of publications to act as peer reviewers and share their evaluations in the form of ratings, annotations, links and classifications via the internet. In addition, Collaborative Document Evaluation might well enhance the search for publications. In this paper the implications of Collaborative Document Evaluation for the scientific community are discussed and questions are asked as to how to create incentives for scientists to participate.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Alcala2004,

title = {UbiLoc: A System for Locating Mobile Devices using Mobile Devices},

author = {Felix Alcala and Joeran Beel and Arne Frenkel and Bela Gipp and Johannes Luelf and Hagen Hoepfner},

editor = {K. Kyamakya},

url = {https://amok.am/_joeran/existing paper, exchanged and invisible keywords, many additional reference/UbiLoc A System for Locating Mobile Devices using Mobile Devices - IMPROVED.pdf},

year  = {2004},

date = {2004-01-01},

booktitle = {Proceedings of 1st Workshop on Positioning, Navigation and Communication 2004 (WPNC 04)},

pages = {43–48},

publisher = {University of Hanover},

note = {Also available on http://beel.org},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Alcala2003,

title = {Ortung von mobilen Geraeten fuer die Realisierung lokationsbasierter Dienste},

author = {Felix Alcala and Joeran Beel and Arne Frenkel and Bela Gipp and Johannes Luelf and Hagen Hoepfner},

editor = {Can Tuerker},

url = {https://www.amok.am/_joeran/_real papers/Ortung von mobilen Geraeten fuer die Realisierung/Einzelbeitrag_mDBIS03_2.pdf},

year  = {2003},

date = {2003-10-01},

booktitle = {Mobilitaet und Informationssysteme - Workshop des GI-Arbeitskreises "Mobile Datenbanken und Informationssysteme"},

publisher = {ETH Zuerich},

address = {Zuerich},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}