An Explainable Recommender System by Integrating Graph Neural Networks and User Reviews

• Published in: Proceedings (IEEE International Conference on Data Mining) pp. 669 - 674
• Main Authors: Batmani, Sahar, Moradi, Parham, Heidari, Narges, Jalili, Mahdi
• Format: Conference Proceeding
• Language: English
• Published: IEEE 09.12.2024
• Subjects: Bipartite graph; Contrastive learning; Convolution; Convolutional neural networks; Data mining; Explainability; Feature extraction; Graph neural networks; Recommender System; Recommender systems; Reviews; Temporal Convolution Networks; User Reviews; Vectors
• ISSN: 2374-8486
• DOI: 10.1109/ICDM59182.2024.00074

This paper introduces an explainable Graph Neural Network (GNN)-based recommender system that integrates user-item interactions and user reviews to enhance recommendation accuracy and interpretability. The proposed method leverages Temporal Convolutional Networks (TCNs) as a language model to encode user reviews into vector representations, capturing temporal dynamics and contextual information. Additionally, it extracts opinion-aspect pairs from reviews, enabling the system to understand specific product features and user sentiments. Bipartite graphs are constructed to represent interactions between users/items and opinion aspects, facilitating the integration of user reviews into the GNN framework. A contrastive learning approach is employed to combine these graphs with TCN-generated review embeddings, enhancing the system's ability to capture complex relationships. Finally, a recommendation strategy is proposed which considers relevant opinion-aspects as explanations for recommendations. The experiments conducted on several benchmarks reveal that our method outperforms its competitors.