Who Also Likes It? Generating the Most Persuasive Social Explanations in Recommender Systems
By Beidou Wang, Martin Ester, Jiajun Bu, Deng Cai. 2014
36 citations recorded by the source corpus.
Social explanation, the statement with the form of "A and B also like the item", is widely used in almost all the major recommender systems in the web and effectively improves the persuasiveness of the recommendation results by convincing more users to try. This paper presents the first algorithm to generate the most persuasive social explanation by recommending the optimal set of users to be put in the explanation. New challenges like modeling persuasiveness of multiple users, different types of users in social network, sparsity of likes, are discussed in depth and solved in our algorithm. The extensive evaluation demonstrates the advantage of our proposed algorithm compared with traditional methods.
Subfields: Information Systems, Management Science and Operations Research
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Information Systems
- Xu Chen
- Yongfeng Zhang
- Xing Xie
- Celestine Mendler-Dünner
- Hao Fu
- Reinhard Heckel
- Michail Vlachos
- Tetsuya Sakai
In Management Science and Operations Research
- Xing Xie
- Hao Fu
- Michail Vlachos
- Tetsuya Sakai
- Yongfeng Zhang
- Xu Chen
- Zhongxia Chen
- Peter Brusilovsky
Citations in the corpus
- Explainable Recommendation: A Survey and New Perspectives (2018, methodology): “Explainable multimedia recommendation broadly includes the explainable recommendation of books (Wang et al. [2018a]), news/articles”
- Personalized Reason Generation for Explainable Song Recommendation (2019, background): “[44] generate social explanations such as “A and B also like the item.”
- Scalable and Interpretable Product Recommendations via Overlapping Co-Clustering (2016, background): “Interpretability adds trust, confidence [11], and persuasiveness [49] to the recommendations, and in certain scenarios helps highlight tradeoffs and compromises [24] and even incorporates aspects of social endorsement [45].”