Attentive Graph-based Text-aware Preference Modeling for Top-N Recommendation

TL;DR

This paper introduces AGTM, a novel graph-based model that leverages item textual content and user-item graph connectivity to enhance top-N recommendation accuracy, especially in scenarios lacking user reviews.

Contribution

The paper proposes AGTM, a new model combining textual content and graph connectivity for improved top-N recommendation, addressing limitations of review-based models.

Findings

AGTM outperforms existing models in top-N recommendation tasks.

Incorporating item textual content improves recommendation performance.

Model effectively captures high-order user-item relationships.

Abstract

Textual data are commonly used as auxiliary information for modeling user preference nowadays. While many prior works utilize user reviews for rating prediction, few focus on top-N recommendation, and even few try to incorporate item textual contents such as title and description. Though delivering promising performance for rating prediction, we empirically find that many review-based models cannot perform comparably well on top-N recommendation. Also, user reviews are not available in some recommendation scenarios, while item textual contents are more prevalent. On the other hand, recent graph convolutional network (GCN) based models demonstrate state-of-the-art performance for top-N recommendation. Thus, in this work, we aim to further improve top-N recommendation by effectively modeling both item textual content and high-order connectivity in user-item graph. We propose a new model named Attentive Graph-based Text-aware Recommendation Model (AGTM). Extensive experiments are provided to justify the rationality and effectiveness of our model design.