Generating and Understanding Personalized Explanations in Hybrid Recommender Systems

Abstract

Recommender systems are ubiquitous and shape the way users access information and make decisions. As these systems become more complex, there is a growing need for transparency and interpretability. In this article, we study the problem of generating and visualizing personalized explanations for recommender systems that incorporate signals from many different data sources. We use a flexible, extendable probabilistic programming approach and show how we can generate real-time personalized recommendations. We then turn these personalized recommendations into explanations. We perform an extensive user study to evaluate the benefits of explanations for hybrid recommender systems. We conduct a crowd-sourced user study where our system generates personalized recommendations and explanations for real users of the last.fm music platform. First, we evaluate the performance of the recommendations in terms of perceived accuracy and novelty. Next, we experiment with (1) different explanation styles (e.g., user-based, item-based), (2) manipulating the number of explanation styles presented, and (3) manipulating the presentation format (e.g., textual vs. visual). We also apply a mixed-model statistical analysis to consider user personality traits as a control variable and demonstrate the usefulness of our approach in creating personalized hybrid explanations with different style, number, and format. Finally, we perform a post analysis that shows different preferences for explanation styles between experienced and novice last.fm users.

A survey on effects of adding explanations to recommender systems

“…In Reference 60, Zhang et al generate explanations as to “why” or “why not” an item is not recommended and consequently proposed a framework that does not recommend an item that the system considers not worth buying, thus gaining the user's trust and helping the user to take a more informed purchasing decision. The recent study 61 proposes the evaluation of the effects of explanations on user preferences. The authors studied personalized recommendations and explanations for real users on a music platform.…”

Justification of recommender systems results: a service-based approach

“… 2021 ; Kouki et al. 2020 ), (ii) those that fuse recommendation and explanation in the same process (Dong and Smyth 2017 ; Lu et al. 2018 ; Rana et al.…”

“…2022 ; Kouki et al. 2019 , 2020 ), this suggests that, to support all users in an informed item selection, we should extend service-based justification of results with the personalization of the user interface to the user’s characteristics.…”

Graph Inductive Inference of Personalized Content for Out-of-matrix Users Via Content Baskets

“…When there are multiple categories of items or an underlying context for recommending items to the users, we can form multiple user content baskets or introduce attention [30] for accurate and explainable recommendations [17]. Lastly, our framework can also be adapted to similar recommendationrelated tasks that have reasons to restrict access to personal user info, e.g.…”