Minimizing Mindless Mentions: Recommendation with Minimal Necessary User Reviews

TL;DR

This paper advocates for minimizing user reviews in recommender systems by automatically editing reviews to contain only essential information, aiming to reduce unnecessary data use while maintaining recommendation quality.

Contribution

It introduces the novel idea of applying data minimization to user reviews in recommender systems, proposing automatic editing to retain only necessary review content.

Findings

Conceptual framework for review minimization

Potential reduction in data usage for recommendations

Improved privacy and efficiency in recommender systems

Abstract

Recently, researchers have turned their attention to recommender systems that use only minimal necessary data. This trend is informed by the idea that recommender systems should use no more user interactions than are needed in order to provide users with useful recommendations. In this position paper, we make the case for applying the idea of minimal necessary data to recommender systems that use user reviews. We argue that the content of individual user reviews should be subject to minimization. Specifically, reviews used as training data to generate recommendations or reviews used to help users decide on purchases or consumption should be automatically edited to contain only the information that is needed.