Artificial Intelligence

Bias, Fairness, and More in Recommender Systems

Friday, November 20, 2020, 11:00am - 12:00pm PSTiCal
This event is open to the public.
AI Seminar
James Caverlee

Recommender systems are ubiquitous: they connect us to jobs, news, media, and friends, fundamentally shaping our experiences. And yet, these important systems can preserve and sometimes augment bias, leading to negative impacts on users, items, the recommendation platform, and ultimately society. In this talk, I will highlight recent work in my lab examining bias and fairness issues in recommendation, including: (*) under-recommendation bias, wherein one or more groups of items are systematically under-recommended; (*) popularity-opportunity bias, a new perspective on the classic popularity bias problem, wherein the rich-get-richer; and (*) distortion bias, wherein the distribution of who is targeted by the recommender is biased. I'll conclude with thoughts on important challenges and next steps.

James Caverlee is Professor and Lynn '84 and Bill Crane '83 Faculty Fellow at Texas A&M University in the Department of Computer Science and Engineering. His research targets topics from recommender systems, social media, information retrieval, data mining, and emerging networked information systems. His group has been supported by NSF, DARPA, AFOSR, Amazon, Google, among others. Caverlee serves as an associate editor for IEEE Transactions on Knowledge and Data Engineering (TKDE), IEEE Intelligent Systems, and Social Network Analysis and Mining (SNAM). He was general co-chair of the 13th ACM International Conference on Web Search and Data Mining (WSDM 2020), and has been a senior program committee member of venues like KDD, SIGIR, SDM, WSDM, CIKM, and ICWSM.

« Return to Events