Coevolutionary Recommendation Model: Mutual Learning between Ratings and Reviews

By Yichao Lu, Ruihai Dong, Barry Smyth. 2018

170 citations recorded by the source corpus.

Collaborative filtering (CF) is a common recommendation approach that relies on user-item ratings. However, the natural sparsity of user-item rating data can be problematic in many domains and settings, limiting the ability to generate accurate predictions and effective recommendations. Moreover, in some CF approaches latent features are often used to represent users and items, which can lead to a lack of recommendation transparency and explainability. User-generated, customer reviews are now commonplace on many websites, providing users with an opportunity to convey their experiences and opinions of products and services. As such, these reviews have the potential to serve as a useful source of recommendation data, through capturing valuable sentiment information about particular product features. In this paper, we present a novel deep learning recommendation model, which co-learns user and item information from ratings and customer reviews, by optimizing matrix factorization and an attention-based GRU network. Using real-world datasets we show a significant improvement in recommendation performance, compared to a variety of alternatives. Furthermore, the approach is useful when it comes to assigning intuitive meanings to latent features to improve the transparency and explainability of recommender systems.

How researchers see this paper

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

1. Xu Chen
2. Xiangnan He
3. Yongfeng Zhang
4. Xiang Wang
5. Le Wu
6. Hanxiong Chen
7. Meng Wang
8. Chen Gao

Citations in the corpus

• Explainable Recommendation: A Survey and New Perspectives (2018, background): “, 2019) and (Lu et al., 2018a), the attention weights over review words are leveraged to explain the recommendations.”
• Recommendation system based on deep learning methods: a systematic review and new directions (2019, background): “For example, Dai et al. (2016), Lu et al. (2018) introduced a coevolutionary latent model for capturing the coevolution of the user/item latent features for improving the performance of RS. Jing and Smo (2017) used LSTM models for multitasking learning to simultaneously predict the returning times…”
• A Survey on Accuracy-Oriented Neural Recommendation: From Collaborative Filtering to Information-Rich Recommendation (2021, background): “Researchers have also proposed a co-evolutionary topical attention regularizedmatrix factorizationmodel, with the user attentive features learned from an attention network that combines the user reviews, and the item attentive features learned from an attention network that combines the item reviews”
• Generate Natural Language Explanations for Recommendation (2021, background): “Although the reviews are plentiful, informative and contain valuable information about users opinions and product features [21, 47], they can be very noisy and not all the sentences in a review are of explanation purpose.”
• A Context-Aware User-Item Representation Learning for Item Recommendation (2017, methodology): “TARMF [23] employs an attention-based GRU network to interpret the semantic meaning associated with each latent factor in the latent vectors gained by an MF model.”
• A Capsule Network for Recommendation and Explaining What You Like and Dislike (2019, methodology): “xtract item characteristics from the item description [15]. TARMF uses the features extracted from both user document and item document to calibrate the latent factors in the factor learning paradigm [19]. DeepCoNN uses parallel CNN networks to uncover semantic features from user and item documents ”