Fair Multi-Stakeholder News Recommender System with Hypergraph ranking

Recommender systems are typically designed to fulfill end user needs. However, in some domains the users are not the only stakeholders in the system. For instance, in a news aggregator website users, authors, magazines as well as the platform itself are potential stakeholders. Most of the collaborative filtering recommender systems suffer from popularity bias. Therefore, if the recommender system only considers users' preferences, presumably it over-represents popular providers and under-represents less popular providers. To address this issue one should consider other stakeholders in the generated ranked lists. In this paper we demonstrate that hypergraph learning has the natural capability of handling a multi-stakeholder recommendation task. A hypergraph can model high order relations between different types of objects and therefore is naturally inclined to generate recommendation lists considering multiple stakeholders. We form the recommendations in time-wise rounds and learn to adapt the weights of stakeholders to increase the coverage of low-covered stakeholders over time. The results show that the proposed approach counters popularity bias and produces fairer recommendations with respect to authors in two news datasets, at a low cost in precision.

[1]  Constantine Kotropoulos,et al.  Simultaneous image tagging and geo-location prediction within hypergraph ranking framework , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  Neil J. Hurley,et al.  Incorporating Diversity in a Learning to Rank Recommender System , 2016, FLAIRS.

[3]  James Caverlee,et al.  Next-item Recommendation with Sequential Hypergraphs , 2020, SIGIR.

[4]  Himan Abdollahpouri,et al.  Popularity Bias in Ranking and Recommendation , 2019, AIES.

[5]  Nasim Sonboli,et al.  Balanced Neighborhoods for Multi-sided Fairness in Recommendation , 2018, FAT.

[6]  Angela Carrillo Ramos,et al.  XPLODIV: An Exploitation-Exploration Aware Diversification Approach for Recommender Systems , 2015, FLAIRS Conference.

[7]  Saul Vargas,et al.  Improving sales diversity by recommending users to items , 2014, RecSys '14.

[8]  Toniann Pitassi,et al.  Fairness through awareness , 2011, ITCS '12.

[9]  Jie Lu,et al.  Multiobjective e-commerce recommendations based on hypergraph ranking , 2019, Inf. Sci..

[10]  Constantine Kotropoulos,et al.  Weight estimation in hypergraph learning , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[11]  Maksims Volkovs,et al.  Learning to rank with multiple objective functions , 2011, WWW.

[12]  Chun Chen,et al.  Music recommendation by unified hypergraph: combining social media information and music content , 2010, ACM Multimedia.

[13]  Yong Yu,et al.  Set-oriented personalized ranking for diversified top-n recommendation , 2013, RecSys.

[14]  Tao Li,et al.  News recommendation via hypergraph learning: encapsulation of user behavior and news content , 2013, WSDM.

[15]  C. Vens,et al.  Multi-stakeholder News Recommendation Using Hypergraph Learning , 2020, PKDD/ECML Workshops.

[16]  Robin D. Burke,et al.  Multistakeholder recommendation with provider constraints , 2018, RecSys.

[17]  Saul Vargas,et al.  Intent-oriented diversity in recommender systems , 2011, SIGIR.

[18]  Jun Wang,et al.  Adaptive diversification of recommendation results via latent factor portfolio , 2012, SIGIR '12.

[19]  Robin Burke,et al.  Addressing the Multistakeholder Impact of Popularity Bias in Recommendation Through Calibration , 2020, ArXiv.

[20]  Robin D. Burke,et al.  Evaluating the dynamic properties of recommendation algorithms , 2010, RecSys '10.

[21]  Alexander Tuzhilin,et al.  The long tail of recommender systems and how to leverage it , 2008, RecSys '08.

[22]  Fernando Diaz,et al.  Towards a Fair Marketplace: Counterfactual Evaluation of the trade-off between Relevance, Fairness & Satisfaction in Recommendation Systems , 2018, CIKM.

[23]  Robert M. Sanders.  THE PARETO PRINCIPLE: ITS USE AND ABUSE , 1987 .

[24]  Bamshad Mobasher,et al.  Towards Multi-Stakeholder Utility Evaluation of Recommender Systems , 2016, UMAP.

[25]  Christopher C. Johnson.  Logistic Matrix Factorization for Implicit Feedback Data , 2014 .

[26]  M. Barber,et al.  Diversity , 2010, The Fairchild Books Dictionary of Fashion.

[27]  Himan Abdollahpouri.  Incorporating System-Level Objectives into Recommender Systems , 2019, WWW.

[28]  Jade Goldstein-Stewart,et al.  The use of MMR, diversity-based reranking for reordering documents and producing summaries , 1998, SIGIR '98.

[29]  Derek Bridge,et al.  Diversity, Serendipity, Novelty, and Coverage , 2016, ACM Trans. Interact. Intell. Syst..

[30]  Jon Atle Gulla,et al.  The Adressa dataset for news recommendation , 2017, WI.

[31]  Yifan Hu,et al.  Collaborative Filtering for Implicit Feedback Datasets , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[32]  Gianni Fenu,et al.  Interplay between Upsampling and Regularization for Provider Fairness in Recommender Systems , 2020, ArXiv.

[33]  Bernhard Schölkopf,et al.  Learning with Hypergraphs: Clustering, Classification, and Embedding , 2006, NIPS.

[34]  Dietmar Jannach,et al.  Contextual Hybrid Session-Based News Recommendation With Recurrent Neural Networks , 2019, IEEE Access.

[35]  Jun Wang,et al.  Optimizing multiple objectives in collaborative filtering , 2010, RecSys '10.

[36]  Yong Zheng.  Preference corrections: capturing student and instructor perceptions in educational recommendations , 2019, Smart Learning Environments.