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

By Zhiyong Cheng, Ying Ding, Lei Zhu, Mohan Kankanhalli. 2018

322 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiangnan He
2. Tat-seng Chua
3. Xiang Wang
4. Xu Chen
5. Yongfeng Zhang
6. Liqiang Nie
7. Fuli Feng
8. Yixin Cao

In Information Systems

1. Xiangnan He
2. Tat-seng Chua
3. Xiang Wang
4. Xu Chen
5. Liqiang Nie
6. Yongfeng Zhang
7. Fuli Feng
8. Yixin Cao

Citations in the corpus

• Explainable Recommendation: A Survey and New Perspectives (2018, background): “Cheng et al. [2018] proposed aspect-aware latent factor model for rating prediction with ratings and reviews.”
• Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences (2019, background): “Content-based methods deal with the issues by introducing various side information, such as the contextual reviews [9, 25], relational data [10, 36] and knowledge graphs [6].”
• Disentangled Graph Collaborative Filtering (2020, background): “history with users [21], item knowledge [15, 32, 39, 41, 42], and user reviews [5, 22], or conduct psychology experiments [24] to establish the ground truth on user intents and further interpret disentangled representations better.”
• Neural Compatibility Modeling with Attentive Knowledge Distillation (2018, methodology): “Due to the sparsity of our dataset, where matrix factorization based methods [7, 8, 31, 40] are not applicable, we chose the following content-based baselines regarding compatibility modeling to evaluate the proposed model AKD-DBPR.”
• MMALFM (2018, background): “Note that we presented a preliminary study in [13].”
• A Capsule Network for Recommendation and Explaining What You Like and Dislike (2019, methodology): “extent [6].”
• Interest-aware Message-Passing GCN for Recommendation (2021, methodology): “Among various recommendation approaches, the model-based collaborative filtering (CF) [5, 6, 14–16, 19, 20, 27, 32, 33] achieves a great success and becomes the mainstream recommendation technique.”
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation (2020, unknown): “embedding) to represent a user and an item, and perform prediction based on the embedding vectors [6, 19].”
• Neural Compatibility Modeling With Probabilistic Knowledge Distillation (2020, methodology): “Due to the sparsity of our dataset, the matrix factorization based methods [42]–[44] are not much suitable.”
• Incorporating Interpretability into Latent Factor Models via Fast Influence Analysis (2018, unknown): “Wang et al. (2018) and Cheng et al. (2018b) empowered LFMs with explanations using both product features and review aspects.”
• TEM: Tree-enhanced Embedding Model for Explainable Recommendation (2018, background): “Content-based works have considered various side information, ranging from item tags [38, 40], social relationships [31, 37], contextual reviews written by users [13, 15, 28, 31, 48] to knowledge graphs [3, 8, 47].”
• Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems (2020, unknown): “[7, 8] exploits user’s reviews and image information.”