%0 Conference Paper %1 beel2015comparison %A Beel, Joeran %A Langer, Stefan %B Research and Advanced Technology for Digital Libraries %C Cham %D 2015 %E Kapidakis, Sarantos %E Mazurek, Cezary %E Werla, Marcin %I Springer International Publishing %K offline online recommender system %P 153--168 %T A Comparison of Offline Evaluations, Online Evaluations, and User Studies in the Context of Research-Paper Recommender Systems %X The evaluation of recommender systems is key to the successful application of recommender systems in practice. However, recommender-systems evaluation has received too little attention in the recommender-system community, in particular in the community of research-paper recommender systems. In this paper, we examine and discuss the appropriateness of different evaluation methods, i.e. offline evaluations, online evaluations, and user studies, in the context of research-paper recommender systems. We implemented different content-based filtering approaches in the research-paper recommender system of Docear. The approaches differed by the features to utilize (terms or citations), by user model size, whether stop-words were removed, and several other factors. The evaluations show that results from offline evaluations sometimes contradict results from online evaluations and user studies. We discuss potential reasons for the non-predictive power of offline evaluations, and discuss whether results of offline evaluations might have some inherent value. In the latter case, results of offline evaluations were worth to be published, even if they contradict results of user studies and online evaluations. However, although offline evaluations theoretically might have some inherent value, we conclude that in practice, offline evaluations are probably not suitable to evaluate recommender systems, particularly in the domain of research paper recommendations. We further analyze and discuss the appropriateness of several online evaluation metrics such as click-through rate, link-through rate, and cite-through rate. %@ 978-3-319-24592-8

@inproceedings{beel2015comparison, abstract = {The evaluation of recommender systems is key to the successful application of recommender systems in practice. However, recommender-systems evaluation has received too little attention in the recommender-system community, in particular in the community of research-paper recommender systems. In this paper, we examine and discuss the appropriateness of different evaluation methods, i.e. offline evaluations, online evaluations, and user studies, in the context of research-paper recommender systems. We implemented different content-based filtering approaches in the research-paper recommender system of Docear. The approaches differed by the features to utilize (terms or citations), by user model size, whether stop-words were removed, and several other factors. The evaluations show that results from offline evaluations sometimes contradict results from online evaluations and user studies. We discuss potential reasons for the non-predictive power of offline evaluations, and discuss whether results of offline evaluations might have some inherent value. In the latter case, results of offline evaluations were worth to be published, even if they contradict results of user studies and online evaluations. However, although offline evaluations theoretically might have some inherent value, we conclude that in practice, offline evaluations are probably not suitable to evaluate recommender systems, particularly in the domain of research paper recommendations. We further analyze and discuss the appropriateness of several online evaluation metrics such as click-through rate, link-through rate, and cite-through rate.}, added-at = {2021-04-30T12:09:53.000+0200}, address = {Cham}, author = {Beel, Joeran and Langer, Stefan}, biburl = {https://www.bibsonomy.org/bibtex/2e3aa6ea70936cb0734449c49cbf591e9/nosebrain}, booktitle = {Research and Advanced Technology for Digital Libraries}, description = {A Comparison of Offline Evaluations, Online Evaluations, and User Studies in the Context of Research-Paper Recommender Systems | SpringerLink}, editor = {Kapidakis, Sarantos and Mazurek, Cezary and Werla, Marcin}, interhash = {bbf2c6f4d9658828c9c1fdee93830216}, intrahash = {e3aa6ea70936cb0734449c49cbf591e9}, isbn = {978-3-319-24592-8}, keywords = {offline online recommender system}, pages = {153--168}, publisher = {Springer International Publishing}, timestamp = {2021-04-30T12:09:53.000+0200}, title = {A Comparison of Offline Evaluations, Online Evaluations, and User Studies in the Context of Research-Paper Recommender Systems}, year = 2015 }