Hierarchical Text Interaction for Rating Prediction
Preprint
Abstract
Traditional recommender systems encounter several challenges such as data sparsity and unexplained recommendation. To address these challenges, many works propose to exploit semantic information from review data. However, these methods have two major limitations in terms of the way to model textual features and capture textual interaction. For textual modeling, they simply concatenate all the reviews of a user/item into a single review. However, feature extraction at word/phrase level can violate the meaning of the original reviews. As for textual interaction, they defer the interactions to the prediction layer, making them fail to capture complex correlations between users and items. To address those limitations, we propose a novel Hierarchical Text Interaction model(HTI) for rating prediction. In HTI, we propose to model low-level word semantics and high-level review representations hierarchically. The hierarchy allows us to exploit textual features at different granularities. To further capture complex user-item interactions, we propose to exploit semantic correlations between each user-item pair at different hierarchies. At word level, we propose an attention mechanism specialized to each user-item pair, and capture the important words for representing each review. At review level, we mutually propagate textual features between the user and item, and capture the informative reviews. The aggregated review representations are integrated into a collaborative filtering framework for rating prediction. Experiments on five real-world datasets demonstrate that HTI outperforms state-of-the-art models by a large margin. Further case studies provide a deep insight into HTI's ability to capture semantic correlations at different levels of granularities for rating prediction.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Generalized Incomplete Multiview Clustering With Flexible Locality Structure DiffusionIEEE Transactions on Cybernetics, 2020
- Scalable Supervised Asymmetric Hashing With Semantic and Latent Factor EmbeddingIEEE Transactions on Image Processing, 2019
- A Hierarchical Attention Model for Social Contextual Image RecommendationIEEE Transactions on Knowledge and Data Engineering, 2019
- A scalable and robust trust-based nonnegative matrix factorization recommender using the alternating direction methodKnowledge-Based Systems, 2019
- Discrete Optimal Graph ClusteringIEEE Transactions on Cybernetics, 2018
- Transfer Independently Together: A Generalized Framework for Domain AdaptationIEEE Transactions on Cybernetics, 2018
- A cross-domain recommender system with consistent information transferDecision Support Systems, 2017
- Discrete Multimodal Hashing With Canonical Views for Robust Mobile Landmark SearchIEEE Transactions on Multimedia, 2017
- Member contribution-based group recommender systemDecision Support Systems, 2016
- Matrix Factorization Techniques for Recommender SystemsComputer, 2009