Popularity Bias in Collaborative Filtering-Based Multimedia Recommender Systems

Dominik Kowald*, Emanuel Lacic

*Korrespondierende/r Autor/-in für diese Arbeit

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung


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., LastFm, 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.
TitelAdvances in Bias and Fairness in Information Retrieval - 3rd International Workshop, BIAS 2022, Revised Selected Papers
UntertitelThird International Workshop, BIAS 2022, Stavanger, Norway, April 10, 2022, Revised Selected Papers
Redakteure/-innenLudovico Boratto, Mirko Marras, Stefano Faralli, Giovanni Stilo
ISBN (elektronisch)978-3-031-09316-6
PublikationsstatusVeröffentlicht - 2022
Veranstaltung44th European Conference on Information Retrieval: ECIR 2022 - Stavanger, Norwegen
Dauer: 10 Apr. 202214 Apr. 2022


NameCommunications in Computer and Information Science
Band1610 CCIS
ISSN (Print)1865-0929
ISSN (elektronisch)1865-0937


Konferenz44th European Conference on Information Retrieval
KurztitelECIR 2022


  • recommender systems
  • Popularity bias
  • Multimedia recommendations

ASJC Scopus subject areas

  • Mathematik (insg.)
  • Informatik (insg.)


Untersuchen Sie die Forschungsthemen von „Popularity Bias in Collaborative Filtering-Based Multimedia Recommender Systems“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren