Socially-responsible recommender systems


Involved faculty members:

Alan Hanjalic Elvin Isufi C.C.S. Liem J. Urbano H. Wang


The Multimedia Computing Group has built up a rich track record in the field of recommender systems over the past decade, marked by numerous and impactful publications in the major conference and journal venues in this field. These venues include the ACM Recommender Systems (RecSys) conference, ACM SIGIR conference, User Modeling, Adaptation and Personalization (UMAP) conference, ACM Transactions on Intelligent Systems and Technology and ACM Computing Surveys. Our widely cited publications, awards and our longstanding involvement in the recommender systems community through organization and program committees, have brought the MMC group at the forefront of the RecSys field, culminating in the success of bringing the ACM RecSys conference to the Netherlands in 2021. While our contribution to the field in the past focused mainly on improving the methodological and algorithmic foundations of learning to rank, context-aware and cross-domain recommendation, over the past years, our research shifted towards addressing the societal consequences of deploying recommender systems in user communities, including the biases and the emergence of filter bubbles and echo chambers. Since these are the phenomena that characterize networked user community, we have been increasingly approaching the development of recommender systems solutions by deploying the expertise from (complex) network science and graph signal processing. In addition, we have been looking deeper into the link between user interests and user’s personal values in order to improve the quality, but also the trustworthiness of the generated recommendations.

Representative publications

  1. Y Shi, A Karatzoglou, L Baltrunas, M Larson, N Oliver, A Hanjalic: CLiMF: learning to maximize reciprocal rank with collaborative less-is-more filtering, ACM RecSys conference, 2012 (Best Paper Award)
  2. Y Shi, M Larson, A Hanjalic: Collaborative filtering beyond the user-item matrix: A survey of the state of the art and future challenges, ACM Computing Surveys (CSUR) 47 (1), 2014
  3. B Loni, Y Shi, M Larson, A Hanjalic: Cross-domain collaborative filtering with factorization machines, European conference on information retrieval (ECIR), 2014
  4. S Manolios, A Hanjalic, CCS Liem: The influence of personal values on music taste: towards value-based music recommendations, ACM RecSYs conference, 2019
  5. E Isufi, M Pocchiari , A Hanjalic: Accuracy-Diversity Trade-off in Recommender Systems via Graph Convolutions, Information Processing and Management, to appear, 2021
  6. Z Li, J Urbano, A. Hanjalic: Leave No User Behind: Towards Improving the Utility of Recommender Systems for Non-mainstream Users, ACM International Conference on Web Search and Data Mining (WSDM), to appear, 2021
/* */