Rating-Boosted Latent Topics: Understanding Users and Items with Ratings and Reviews

By Yunzhi Tan, Min Zhang, Yiqun Liu, Shaoping Ma. 2016

174 citations recorded by the source corpus.

How researchers see this paper

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

1. Yongfeng Zhang
2. Xu Chen
3. Hanxiong Chen
4. Qingyao Ai
5. Zhiyong Cheng
6. Xiangnan He
7. Zheng Qin
8. Chenliang Li

Citations in the corpus

• Explainable Recommendation: A Survey and New Perspectives (2018, methodology): “Following this idea, Tan et al. [2016] proposed to model item recommendability and user preference in a unified semantic space based on review information.”
• Personalized Fashion Recommendation with Visual Explanations based on Multimodal Attention Network: Towards Visually Explainable Recommendation (2019, methodology): “Based on this information, early methods, such as HFT [26] and RBLT [34], mainly focused on combining topic models ( e.g. , LDA [3]) with matrix factorization (MF) for collective user review and rating modeling.”
• MMALFM (2018, methodology): “is accompanied with an image. In this work, we leverage the review, rating, and image information. This dataset has been widely used for rating prediction with reviews and ratings in previous studies [9, 41, 45, 56]. The dataset is organized into 24 product categories. In this paper, we used five ca”
• Neural Attentional Rating Regression with Review-level Explanations (2018, methodology): “In the last few years, there is a large literature exploiting text review information for improving the rating prediction performance, such as HFT[27], RMR[26], EFM[44],TriRank[11], RBLT[39], and sCVR[32].”
• A Capsule Network for Recommendation and Explaining What You Like and Dislike (2019, methodology): “An item document can be considered as a summary of the item’s various aspects, where the important aspects can be easily exposed [19, 26].”
• Aspect-Aware Latent Factor Model: Rating Prediction with Ratings and Reviews (2018, methodology): “ITLFM [39] and RBLT [31] assume that the latent topics and latent factors are in the same space, and linearly combine them to form the latent representations for users and items to model the ratings in MF.”
• Adversarial Distillation for Efficient Recommendation with External Knowledge (2018, methodology): “To incorporate textual information into a recommender system, early methods, such as, HFT [30], RBLT [40] and CTR [42], mainly focused on how to effectively integrate topic model (e.”
• Joint Representation Learning for Top-N Recommendation with Heterogeneous Information Sources (2017, background): “One trend is to augment numerical ratings with textual reviews for recommendation [8], which includes topic modeling [3, 26, 27, 34], sentiment analysis [9, 13, 39, 42–44], and (deep) neural network [2, 36, 41, 45] approaches for review modeling.”