Aspect-Aware Latent Factor Model: Rating Prediction with Ratings and Reviews

Abstract

Although latent factor models (e.g., matrix factorization) achieve good accuracy in rating prediction, they suffer from several problems including cold-start, non-transparency, and suboptimal recommendation for local users or items. In this paper, we employ textual review information with ratings to tackle these limitations. Firstly, we apply a proposed aspect-aware topic model (ATM) on the review text to model user preferences and item features from different aspects, and estimate the aspect importance of a user towards an item. The aspect importance is then integrated into a novel aspect-aware latent factor model (ALFM), which learns user's and item's latent factors based on ratings. In particular, ALFM introduces a weighted matrix to associate those latent factors with the same set of aspects discovered by ATM, such that the latent factors could be used to estimate aspect ratings. Finally, the overall rating is computed via a linear combination of the aspect ratings, which are weighted by the corresponding aspect importance. To this end, our model could alleviate the data sparsity problem and gain good interpretability for recommendation. Besides, an aspect rating is weighted by an aspect importance, which is dependent on the targeted user's preferences and targeted item's features. Therefore, it is expected that the proposed method can model a user's preferences on an item more accurately for each user-item pair locally. Comprehensive experimental studies have been conducted on 19 datasets from Amazon and Yelp 2017 Challenge dataset. Results show that our method achieves significant improvement compared with strong baseline methods, especially for users with only few ratings. Moreover, our model could interpret the recommendation results in depth.

This paper has been accepted by the WWW 2018 Conference

References in corpus (3)

• TransNets: Learning to Transform for Recommendation
• Item Silk Road: Recommending Items from Information Domains to Social Users
• Joint Deep Modeling of Users and Items Using Reviews for Recommendation

Cited by in corpus (28)

• Neural Graph Collaborative Filtering
• Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems
• MMALFM: Explainable Recommendation by Leveraging Reviews and Images
• Reinforced Negative Sampling over Knowledge Graph for Recommendation
• Attentive Aspect Modeling for Review-aware Recommendation
• User Diverse Preference Modeling by Multimodal Attentive Metric Learning
• Multi-Behavior Recommendation with Cascading Graph Convolution Networks
• Learning to Recommend with Multiple Cascading Behaviors
• User-controllable Recommendation Against Filter Bubbles
• Explaining Latent Factor Models for Recommendation with Influence Functions
• Feature-aware Diversified Re-ranking with Disentangled Representations for Relevant Recommendation
• Bipartite Graph Convolutional Hashing for Effective and Efficient Top-N Search in Hamming Space
• RepeatNet: A Repeat Aware Neural Recommendation Machine for Session-based Recommendation
• A Comprehensive Overview of Recommender System and Sentiment Analysis
• DBRec: Dual-Bridging Recommendation via Discovering Latent Groups
• Top-Personalized-K Recommendation
• Doubly Calibrated Estimator for Recommendation on Data Missing Not At Random
• Towards Explainable Collaborative Filtering with Taste Clusters Learning
• A Capsule Network for Recommendation and Explaining What You Like and Dislike
• Intent Propagation Contrastive Collaborative Filtering
• Can Offline Metrics Measure Explanation Goals? A Comparative Survey Analysis of Offline Explanation Metrics in Recommender Systems
• Meta Matrix Factorization for Federated Rating Predictions
• Opinion-aware Answer Generation for Review-driven Question Answering in E-Commerce
• Attentive Long Short-Term Preference Modeling for Personalized Product Search
• Deep Representation Learning for Road Detection through Siamese Network
• Latent Multi-Criteria Ratings for Recommendations