RecCoT: Enhancing Recommendation via Chain-of-Thought

TL;DR

RecCoT introduces a chain-of-thought approach to recommendation systems, aiming to improve understanding of user preferences by integrating content semantics and providing human-understandable explanations.

Contribution

This paper proposes a novel chain-of-thought method for recommendation systems that incorporates content semantics to enhance interpretability and user understanding.

Findings

Improved recommendation accuracy over baseline models

Enhanced interpretability with human-understandable explanations

Better understanding of user preferences through semantic reasoning

Abstract

In real-world applications, users always interact with items in multiple aspects, such as through implicit binary feedback (e.g., clicks, dislikes, long views) and explicit feedback (e.g., comments, reviews). Modern recommendation systems (RecSys) learn user-item collaborative signals from these implicit feedback signals as a large-scale binary data-streaming, subsequently recommending other highly similar items based on users' personalized historical interactions. However, from this collaborative-connection perspective, the RecSys does not focus on the actual content of the items themselves but instead prioritizes higher-probability signals of behavioral co-occurrence among items. Consequently, under this binary learning paradigm, the RecSys struggles to understand why a user likes or dislikes certain items. To alleviate it, some works attempt to utilize the content-based reviews to capture the semantic knowledge to enhance recommender models. However, most of these methods focus on predicting the ratings of reviews, but do not provide a human-understandable explanation.