Aspect Based Recommendations: Recommending Items with the Most Valuable Aspects Based on User Reviews

By Konstantin Bauman, B. Liu, Alexander Tuzhilin. 2017

199 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Information Systems, Sociology and Political Science

How researchers see this paper

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

In Computer Vision and Pattern Recognition

1. Yongfeng Zhang
2. Xu Chen
3. Xing Xie
4. Minyi Guo
5. Jialin Wang
6. Miao Zhao
7. Fuzheng Zhang
8. Hongwei Wang

In Information Systems

1. Xing Xie
2. Xu Chen
3. Yongfeng Zhang
4. Miao Zhao
5. Wenjie Li
6. Hongwei Wang
7. Xiangnan He
8. Fuzheng Zhang

In Sociology and Political Science

1. Xing Xie
2. Yongfeng Zhang
3. Xu Chen

Citations in the corpus

• RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems (2018, background): “ticular item, which helps improve their acceptance or satisfaction of recommendations and increase trust in RS. The explanations are usually based on community tags [29], social networks [23], aspect [2], and phrase sentiment [44] Since RippleNet explores users’ interests based on the KG, it provide”
• Explainable Recommendation: A Survey and New Perspectives (2018, background): “In terms of the research on explainable POI recommendation, Wu and Ester [2015] conducted restaurant recommendation in Yelp and hotel recommendation in TripAdvisor, and the authors proposed a probabilistic model combining aspect based opinion mining and collaborative filtering to provide explainable”
• Joint Representation Learning for Top-N Recommendation with Heterogeneous Information Sources (2017, unknown): “Furthermore, [4] proposed a Sentiment Utility Logistic Model to recommend not only items but also item aspects to provide beŠer experience for the users, and [43] jointly considered sentiment, aspect, and regional features based on geographical topic modeling for location-aware recommendation.”
• MMALFM (2018, unknown): “nd (3) deep learning-based. Our approach falls into the second category. Sentiment-based. These works analyze user’s sentiments on items in reviews to boost the rating prediction performance, such as [4, 19, 48, 49, 66]. For example, [48] estimates a sentiment score for each review to build a user-i”