TY - GEN
T1 - Why you should listen to this song
T2 - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018
AU - Zhao, Guoshuai
AU - Fu, Hao
AU - Song, Ruihua
AU - Sakai, Tetsuya
AU - Xie, Xing
AU - Qian, Xueming
N1 - Funding Information:
This work was supported in part by NSFC under Grants 61732008, 61772407, 61332018, and u1531141, in part by the National Key R&D Program of China under Grant 2017YFF0107700.
Publisher Copyright:
© 2018 IEEE.
PY - 2019/2/7
Y1 - 2019/2/7
N2 - Explainable recommendation, which makes a user aware of why such items are recommended has received a lot of attention as a highly practical research topic. The goal of our research is to make the users feel as if they are receiving recommendations from their friends. To this end, we formulate a new challenging problem called reason generation for explainable recommendation in conversation applications, and propose a solution that generates a natural language explanation of the reason for recommending an item to that particular user. Evaluation with manual assessments indicates that our generated reasons are relevant to songs and personalized to users. They are also fluent and easy to understand. A large-scale online experiments show that our method outperforms manually selected reasons by 8.2% in terms of click-through rate.
AB - Explainable recommendation, which makes a user aware of why such items are recommended has received a lot of attention as a highly practical research topic. The goal of our research is to make the users feel as if they are receiving recommendations from their friends. To this end, we formulate a new challenging problem called reason generation for explainable recommendation in conversation applications, and propose a solution that generates a natural language explanation of the reason for recommending an item to that particular user. Evaluation with manual assessments indicates that our generated reasons are relevant to songs and personalized to users. They are also fluent and easy to understand. A large-scale online experiments show that our method outperforms manually selected reasons by 8.2% in terms of click-through rate.
KW - Conversational recommendation
KW - explainable recommendation
KW - natural language generation
KW - personalization
KW - recommender system
UR - http://www.scopus.com/inward/record.url?scp=85062878936&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062878936&partnerID=8YFLogxK
U2 - 10.1109/ICDMW.2018.00187
DO - 10.1109/ICDMW.2018.00187
M3 - Conference contribution
AN - SCOPUS:85062878936
T3 - IEEE International Conference on Data Mining Workshops, ICDMW
SP - 1316
EP - 1322
BT - Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018
A2 - Li, Zhenhui
A2 - Zhu, Feida
A2 - Tong, Hanghang
A2 - Yu, Jeffrey
PB - IEEE Computer Society
Y2 - 17 November 2018 through 20 November 2018
ER -