A Live-User Study of Opinionated Explanations for Recommender Systems
Khalil Muhammad, Aonghus Lawlor, Barry Smyth · 2016
This paper describes an approach for generating rich and compelling explanations in recommender systems, based on opinions mined from user-generated reviews. The explanations highlight the features of a recommended item that matter most to the user and also relate them to other recommendation alternatives and the user's past activities to provide a context.