TY - GEN
T1 - Popularity Bias in Collaborative Filtering-Based Multimedia Recommender Systems
AU - Kowald, Dominik
AU - Lacic, Emanuel
PY - 2022
Y1 - 2022
N2 - Multimedia recommender systems suggest media items, e.g., songs, (digital) books and movies, to users by utilizing concepts of traditional recommender systems such as collaborative filtering. In this paper, we investigate a potential issue of such collaborative-filtering based multimedia recommender systems, namely popularity bias that leads to the underrepresentation of unpopular items in the recommendation lists. Therefore, we study four multimedia datasets, i.e., Last.fm, MovieLens, BookCrossing and MyAnimeList, that we each split into three user groups differing in their inclination to popularity, i.e., LowPop, MedPop and HighPop. Using these user groups, we evaluate four collaborative filtering-based algorithms with respect to popularity bias on the item and the user level. Our findings are three-fold: firstly, we show that users with little interest into popular items tend to have large user profiles and thus, are important data sources for multimedia recommender systems. Secondly, we find that popular items are recommended more frequently than unpopular ones. Thirdly, we find that users with little interest into popular items receive significantly worse recommendations than users with medium or high interest into popularity.
AB - Multimedia recommender systems suggest media items, e.g., songs, (digital) books and movies, to users by utilizing concepts of traditional recommender systems such as collaborative filtering. In this paper, we investigate a potential issue of such collaborative-filtering based multimedia recommender systems, namely popularity bias that leads to the underrepresentation of unpopular items in the recommendation lists. Therefore, we study four multimedia datasets, i.e., Last.fm, MovieLens, BookCrossing and MyAnimeList, that we each split into three user groups differing in their inclination to popularity, i.e., LowPop, MedPop and HighPop. Using these user groups, we evaluate four collaborative filtering-based algorithms with respect to popularity bias on the item and the user level. Our findings are three-fold: firstly, we show that users with little interest into popular items tend to have large user profiles and thus, are important data sources for multimedia recommender systems. Secondly, we find that popular items are recommended more frequently than unpopular ones. Thirdly, we find that users with little interest into popular items receive significantly worse recommendations than users with medium or high interest into popularity.
KW - cs.IR
KW - cs.AI
KW - collaborative filtering
KW - multimedia recommender systems
KW - algorithmic fairness
KW - popularity bias
KW - recommender systems
KW - Popularity bias
KW - Multimedia recommendations
UR - http://www.scopus.com/inward/record.url?scp=85134293596&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-09316-6_1
DO - 10.1007/978-3-031-09316-6_1
M3 - Conference paper
SN - 978-3-031-09315-9
T3 - Communications in Computer and Information Science
SP - 1
EP - 11
BT - Advances in Bias and Fairness in Information Retrieval - 3rd International Workshop, BIAS 2022, Revised Selected Papers
A2 - Boratto, Ludovico
A2 - Marras, Mirko
A2 - Faralli, Stefano
A2 - Stilo, Giovanni
T2 - 44th European Conference on Information Retrieval
Y2 - 10 April 2022 through 14 April 2022
ER -