TADO: Time-varying Attention with Dual-Optimizer Model

TL;DR

This paper introduces TADO, a novel review-based recommender system that combines dual-optimizer training, BERT for semantic understanding, and time-varying preference modeling to improve recommendation accuracy, especially for rare ratings.

Contribution

The paper proposes a comprehensive model integrating dual-optimizer training, BERT-based semantic analysis, and time-varying feature extraction for improved review-based recommendations.

Findings

Significant performance improvements over state-of-the-art methods.

Effective handling of class imbalance in rating levels.

Validation on 23 benchmark datasets showing consistent gains.

Abstract

The review-based recommender systems are commonly utilized to measure users preferences towards different items. In this paper, we focus on addressing three main problems existing in the review-based methods. Firstly, these methods suffer from the class-imbalanced problem where rating levels with lower proportions will be ignored to some extent. Thus, their performance on relatively rare rating levels is unsatisfactory. As the first attempt in this field to address this problem, we propose a flexible dual-optimizer model to gain robustness from both regression loss and classification loss. Secondly, to address the problem caused by the insufficient contextual information extraction ability of word embedding, we first introduce BERT into the review-based method to improve the performance of the semantic analysis. Thirdly, the existing methods ignore the feature information of the time-varying user preferences. Therefore, we propose a time-varying feature extraction module with bidirectional long short-term memory and multi-scale convolutional neural network. Afterward, an interaction component is proposed to further summarize the contextual information of the user-item pairs. To verify the effectiveness of the proposed TADO, we conduct extensive experiments on 23 benchmark datasets selected from Amazon Product Reviews. Compared with several recently proposed state-of-the-art methods, our model obtains significant gain over ALFM, MPCN, and ANR averagely with 20.98\%, 9.84\%, and 15.46\%, respectively. Further analysis proves the necessity of jointly using the proposed components in TADO.