Dynamic Review-based Recommenders

TL;DR

This paper introduces a dynamic, time-aware review-based recommender system that models the mutual influence between reviews and ratings, improving prediction accuracy by capturing evolving user preferences.

Contribution

It proposes a novel bidirectional, time-interval aware model that integrates review content and ratings in a continuous-time framework for improved recommendations.

Findings

Outperforms several state-of-the-art models on real-world datasets.

Effectively captures the temporal dynamics of user preferences.

Demonstrates the benefit of joint review and rating modeling.

Abstract

Just as user preferences change with time, item reviews also reflect those same preference changes. In a nutshell, if one is to sequentially incorporate review content knowledge into recommender systems, one is naturally led to dynamical models of text. In the present work we leverage the known power of reviews to enhance rating predictions in a way that (i) respects the causality of review generation and (ii) includes, in a bidirectional fashion, the ability of ratings to inform language review models and vice-versa, language representations that help predict ratings end-to-end. Moreover, our representations are time-interval aware and thus yield a continuous-time representation of the dynamics. We provide experiments on real-world datasets and show that our methodology is able to outperform several state-of-the-art models. Source code for all models can be found at [1].