TME-PSR: Time-aware, Multi-interest, and Explanation Personalization for Sequential Recommendation

TL;DR

This paper introduces TME-PSR, a sequential recommendation model that personalizes recommendations by integrating time-awareness, multiple interests, and explanations, improving accuracy and explanation quality efficiently.

Contribution

The paper presents a novel model combining time-aware, multi-interest, and explanation personalization for sequential recommendation, with new mechanisms for capturing temporal rhythms and interest modeling.

Findings

Improves recommendation accuracy on real-world datasets.

Enhances explanation quality with personalized semantic alignment.

Operates with lower computational cost than existing methods.

Abstract

In this paper, we propose a sequential recommendation model that integrates Time-aware personalization, Multi-interest personalization, and Explanation personalization for Personalized Sequential Recommendation (TME-PSR). That is, we consider the differences across different users in temporal rhythm preference, multiple fine-grained latent interests, and the personalized semantic alignment between recommendations and explanations. Specifically, the proposed TME-PSR model employs a dual-view gated time encoder to capture personalized temporal rhythms, a lightweight multihead Linear Recurrent Unit architecture that enables fine-grained sub-interest modeling with improved efficiency, and a dynamic dual-branch mutual information weighting mechanism to achieve personalized alignment between recommendations and explanations. Extensive experiments on real-world datasets demonstrate that our method consistently improves recommendation accuracy and explanation quality, at a lower computational cost.