Stereotype and Most-Popular Recommendations in the Digital Library Sowiport

Abstract

Stereotype and most-popular recommendations are widely neglected in the research-paper recommender-system and digital-library community. In other domains such as movie recommendations and hotel search, however, these recommendation approaches have proven their effectiveness. We were interested to find out how stereotype and most-popular recommendations would perform in the scenario of a digital library. Therefore, we implemented the two approaches in the recommender system of GESIS’ digital library Sowiport, in cooperation with the recommendations-as-a-service provider Mr. DLib. We measured the effectiveness of most-popular and stereotype recommendations with click-through rate (CTR) based on 28 million delivered recommendations. Most-popular recommendations achieved a CTR of 0.11%, and stereotype recommendations achieved a CTR of 0.124%. Compared to a “random recommendations” baseline (CTR 0.12%), and a contentbased filtering baseline (CTR 0.145%), the results are discouraging. However, for reasons explained in the paper, we concluded that more research is In: M. Gäde/V. Trkulja/V. Petras (Eds.): Everything Changes, Everything Stays the Same? Understanding Information Spaces. Proceedings of the 15 International Symposium of Information Science (ISI 2017), Berlin, 13—15 March 2017. Glückstadt: Verlag Werner Hülsbusch, pp. 96—108. Stereotype and Most-Popular Recommendations ... 97 necessary about the effectiveness of stereotype and most-popular recommendations in digital libraries.