Exploring Users' Perception of Collaborative Explanation Styles

TL;DR

This paper investigates how users perceive different collaborative explanation styles in recommender systems and how rating characteristics influence their choices, providing insights for designing more effective explanations.

Contribution

It offers empirical evidence on the impact of rating summaries and explanation styles on user decision-making in collaborative filtering.

Findings

Mean rating has a greater influence than total number of ratings.

Users prefer explanations based on rating summaries over other styles.

Results inform the development of algorithms that improve recommendation explainability.

Abstract

Collaborative filtering systems heavily depend on user feedback expressed in product ratings to select and rank items to recommend. In this study we explore how users value different collaborative explanation styles following the user-based or item-based paradigm. Furthermore, we explore how the characteristics of these rating summarizations, like the total number of ratings and the mean rating value, influence the decisions of online users. Results, based on a choice-based conjoint experimental design, show that the mean indicator has a higher impact compared to the total number of ratings. Finally, we discuss how these empirical results can serve as an input to developing algorithms that foster items with a, consequently, higher probability of choice based on their rating summarizations or their explainability due to these ratings when ranking recommendations.