An Aspect Performance-aware Hypergraph Neural Network for Review-based Recommendation

2025-01-26

AI Summary

Existing review-driven recommendation methods struggle to model fine-grained item performance across distinct attributes, especially under sentiment polarity conflicts in user reviews, leading to biased recommendations. To address this, we propose the first attribute-performance-aware hypergraph neural network framework: (1) inferring attribute-level performance from sentiment polarity conflicts in reviews; (2) constructing a user-item-attribute-sentiment quadripartite hypergraph to capture multi-hop relational dependencies; and (3) designing a performance-weighted hypergraph aggregation mechanism that jointly learns subjective user preferences and objective attribute-level performance. Evaluated on six real-world datasets, our method achieves an average 2.30% reduction in MSE, and improvements of 4.89% in Precision@5 and 1.60% in Recall@5 over state-of-the-art approaches—demonstrating significant gains in both rating prediction accuracy and top-K recommendation quality.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Online reviews allow consumers to provide detailed feedback on various aspects of items. Existing methods utilize these aspects to model users' fine-grained preferences for specific item features through graph neural networks. We argue that the performance of items on different aspects is important for making precise recommendations, which has not been taken into account by existing approaches, due to lack of data. In this paper, we propose an aspect performance-aware hypergraph neural network (APH) for the review-based recommendation, which learns the performance of items from the conflicting sentiment polarity of user reviews. Specifically, APH comprehensively models the relationships among users, items, aspects, and sentiment polarity by systematically constructing an aspect hypergraph based on user reviews. In addition, APH aggregates aspects representing users and items by employing an aspect performance-aware hypergraph aggregation method. It aggregates the sentiment polarities from multiple users by jointly considering user preferences and the semantics of their sentiments, determining the weights of sentiment polarities to infer the performance of items on various aspects. Such performances are then used as weights to aggregate neighboring aspects. Experiments on six real-world datasets demonstrate that APH improves MSE, Precision@5, and Recall@5 by an average of 2.30%, 4.89%, and 1.60% over the best baseline. The source code and data are available at https://github.com/dianziliu/APH.

Problem

• Recommendation Systems
• Graph Neural Networks
• Sentiment Analysis

Innovation

• Hypergraph Neural Network
• Contradictory Sentiments Analysis
• Recommendation Accuracy Enhancement