Social Collaborative Viewpoint Regression with Explainable Recommendations

By Zhaochun Ren, Shangsong Liang, Piji Li, Shuaiqiang Wang, Maarten de Rijke. 2017

146 citations recorded by the source corpus.

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. Yongfeng Zhang
3. Xu Chen
4. Tat-seng Chua
5. Xiang Wang
6. Xing Xie
7. Liqiang Nie
8. Fuli Feng

In Information Systems

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

Citations in the corpus

• Explainable Recommendation: A Survey and New Perspectives (2018, background): “A viewpoint is a mixture over a concept, a topic, and a sentiment (Ren et al. [2017]).”
• Explainable Outfit Recommendation with Joint Outfit Matching and Comment Generation (2018, background): “[19] propose a richer notion of explanation called viewpoint, which is represented as a tuple of a conceptual feature, a topic and a sentiment label; though they provide explanations for recommendations, the explanations are simple tags or extracted words or phrases.”
• Distilling Structured Knowledge into Embeddings for Explainable and Accurate Recommendation (2019, unknown): “[26] incorporate social relations for better explanations.”
• UniWalk: Explainable and Accurate Recommendation for Rating and Network Data (2017, methodology): “Many models such as SCAR [24], TriRank [8], and EFM [32] exploit user reviews.”
• Self-supervised Graph Learning for Recommendation (2020, unknown): “A surge of attention has also been dedicated to graph-level methods, which enriches the user-item graph by accounting for sideinformation apart from user-item interactions,which ranges from user social relations [1, 32, 53], item co-occurrence [2], to user and item attributes [27].”
• Visually Explainable Recommendation (2018, methodology): “He et al [9] devised a graph algorithm called TriRank for providing recommendations with better explainability and transparency, and to leverage user opinions as well as social information, Ren et al [23] introduced the concept of viewpoints (a tuple of concept, topic, and sentiment label), and prop”
• Denoising Implicit Feedback for Recommendation (2020, background): “Recommender systems have been a promising solution for mining user preference over items in various online services such as Ecommerce [31], news portals [30] and social media [32, 38].”
• The FacT: Taming Latent Factor Models for Explainability with Factorization Trees (2019, background): “, explaining how/why the customized result is presented to a user [20, 34, 38, 39].”
• Explainable Recommendation via Multi-Task Learning in Opinionated Text Data (2018, background): “r. A follow-up work [7] introduces aspect-level topic modeling to capture users’ finer-grained sentiment on different aspects of an item, so that aspect-level explanations become possible. Ren et al. [25] introduce social relations into topic modeling based recommendation via a concept named viewpoi”
• Automatic Generation of Natural Language Explanations (2017, background): “ work, they propose to extract aspects from reviews to generate explainable recommendations, but they do not consider user opinions and influences from social relations as a source of explanation. In [23] they propose the social collaborative viewpoint regression model, which detects viewpoints and ”
• 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].”
• Personalized Fashion Recommendation with Visual Explanations based on Multimodal Attention Network: Towards Visually Explainable Recommendation (2019, unknown): “Recommendation explainability is often assessed qualitatively [13, 29, 37, 39].”
• NAIS: Neural Attentive Item Similarity Model for Recommendation (2018, background): “Lastly, we will investigate the explainability of recommender systems, which is a promising direction recently [44], [28], [45], [41] and can be facilitated by introducing attention networks on item-based CF methods.”
• Neural Attentional Rating Regression with Review-level Explanations (2018, methodology): “First, manual preprocessing is usually required for sentiment analysis and feature extraction of reviews[17, 32, 44].”
• Explainable Recommendation through Attentive Multi-View Learning (2019, methodology): “Thus, many methods have been developed to improve the explainabil-ity of recommendation models (Ren et al. 2017; Peake and Wang 2018; Wang et al. 2018b).”
• MMALFM (2018, methodology): “However, as a typical collaborative filtering technique, the MF-based method easily suffers from the cold-start problem - when there are only few ratings for items or users [29, 53], the performance deteriorates dramatically.”