Contextualizing Recommendation Explanations with LLMs: A User Study

TL;DR

This study investigates how different LLM-generated explanations for movie recommendations impact user perceptions and behaviors, highlighting that contextualized explanations improve trust and intention but have limited effects on emotional and utilitarian needs.

Contribution

The paper provides empirical evidence on the effects of contextualized versus generic LLM explanations in recommender systems and offers insights into designing more effective user-centric explanations.

Findings

Contextualized explanations meet cognitive needs effectively.

They increase users' intentions to watch recommended movies.

Limited benefits observed for utilitarian and affective needs.

Abstract

Large language models (LLMs) are increasingly prevalent in recommender systems, where LLMs can be used to generate personalized recommendations. Here, we examine how different LLM-generated explanations for movie recommendations affect users' perceptions of cognitive, affective, and utilitarian needs and consumption intentions. In a pre-registered, between-subject online experiment (N=759) and follow-up interviews (N=30), we compare (a) LLM-generated generic explanations, and (b) LLM-generated contextualized explanations. Our findings show that contextualized explanations (i.e., explanations that incorporate users' past behaviors) effectively meet users' cognitive needs while increasing users' intentions to watch recommended movies. However, adding explanations offers limited benefits in meeting users' utilitarian and affective needs, raising concerns about the proper design and implications of LLM-generated explanations. Qualitative insights from interviews reveal that referencing users' past preferences enhances trust and understanding but can feel excessive if overused. Furthermore, users with more active and positive engagement with the recommender system and movie-watching get substantial gains from contextualized explanations. Overall, our research clarifies how LLM-generated recommendations influence users' motivations and behaviors, providing valuable insights for the future development of user-centric recommender systems, a key element in social media platforms and online ecosystems.