Leveraging Review Properties for Effective Recommendation

TL;DR

This paper introduces RPRM, a novel recommendation model that leverages review properties to better capture review usefulness, improving recommendation accuracy by modeling property importance and integrating tailored loss functions.

Contribution

The paper proposes a new review properties-based recommendation model (RPRM) that learns the significance of review properties and incorporates specific loss functions and negative sampling to enhance recommendations.

Findings

RPRM outperforms classical and state-of-the-art baselines on Yelp and Amazon datasets.

Modeling review properties improves recommendation accuracy.

Loss functions and negative sampling strategies further boost RPRM's performance.

Abstract

Many state-of-the-art recommendation systems leverage explicit item reviews posted by users by considering their usefulness in representing the users' preferences and describing the items' attributes. These posted reviews may have various associated properties, such as their length, their age since they were posted, or their item rating. However, it remains unclear how these different review properties contribute to the usefulness of their corresponding reviews in addressing the recommendation task. In particular, users show distinct preferences when considering different aspects of the reviews (i.e. properties) for making decisions about the items. Hence, it is important to model the relationship between the reviews' properties and the usefulness of reviews while learning the users' preferences and the items' attributes. Therefore, we propose to model the reviews with their associated available properties. We introduce a novel review properties-based recommendation model (RPRM) that learns which review properties are more important than others in capturing the usefulness of reviews, thereby enhancing the recommendation results. Furthermore, inspired by the users' information adoption framework, we integrate two loss functions and a negative sampling strategy into our proposed RPRM model, to ensure that the properties of reviews are correlated with the users' preferences. We examine the effectiveness of RPRM using the well-known Yelp and Amazon datasets. Our results show that RPRM significantly outperforms a classical and five state-of-the-art baselines. Moreover, we experimentally show the advantages of using our proposed loss functions and negative sampling strategy, which further enhance the recommendation performances of RPRM.