Abstract
Personalized recommendation has received a lot of attention as a highly practical research topic. However, existing recommender systems provide the recommendations with a generic statement such as "Customers who bought this item also bought . . . ". Explainable recommendation, which makes a user aware of why such items are recommended, is in demand. 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 personalized reason generation for explainable recommendation for songs in conversation applications and propose a solution that generates a natural language explanation of the reason for recommending a song to that particular user. For example, if the user is a student, our method can generate an output such as "Campus radio plays this song at noon every day, and I think it sounds wonderful," which the student may find easy to relate to. In the offline experiments, through manual assessments, the gain of our method is statistically significant on the relevance to songs and personalization to users comparing with baselines. Large-scale online experiments show that our method outperforms manually selected reasons by 8.2% in terms of click-Through rate. Evaluation results indicate that our generated reasons are relevant to songs and personalized to users, and they attract users to click the recommendations.
Original language | English |
---|---|
Article number | 41 |
Journal | ACM Transactions on Intelligent Systems and Technology |
Volume | 10 |
Issue number | 4 |
DOIs | |
Publication status | Published - 2019 Jul 1 |
Fingerprint
Keywords
- Conversational recommendation
- explainable recommendation
- natural language generation
- personalization
- recommender system
ASJC Scopus subject areas
- Theoretical Computer Science
- Artificial Intelligence
Cite this
Personalized Reason Generation for Explainable Song Recommendation. / Zhao, Guoshuai; Fu, Hao; Song, Ruihua; Sakai, Tetsuya; Chen, Zhongxia; Xie, Xing; Qian, Xueming.
In: ACM Transactions on Intelligent Systems and Technology, Vol. 10, No. 4, 41, 01.07.2019.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Personalized Reason Generation for Explainable Song Recommendation
AU - Zhao, Guoshuai
AU - Fu, Hao
AU - Song, Ruihua
AU - Sakai, Tetsuya
AU - Chen, Zhongxia
AU - Xie, Xing
AU - Qian, Xueming
PY - 2019/7/1
Y1 - 2019/7/1
N2 - Personalized recommendation has received a lot of attention as a highly practical research topic. However, existing recommender systems provide the recommendations with a generic statement such as "Customers who bought this item also bought . . . ". Explainable recommendation, which makes a user aware of why such items are recommended, is in demand. 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 personalized reason generation for explainable recommendation for songs in conversation applications and propose a solution that generates a natural language explanation of the reason for recommending a song to that particular user. For example, if the user is a student, our method can generate an output such as "Campus radio plays this song at noon every day, and I think it sounds wonderful," which the student may find easy to relate to. In the offline experiments, through manual assessments, the gain of our method is statistically significant on the relevance to songs and personalization to users comparing with baselines. Large-scale online experiments show that our method outperforms manually selected reasons by 8.2% in terms of click-Through rate. Evaluation results indicate that our generated reasons are relevant to songs and personalized to users, and they attract users to click the recommendations.
AB - Personalized recommendation has received a lot of attention as a highly practical research topic. However, existing recommender systems provide the recommendations with a generic statement such as "Customers who bought this item also bought . . . ". Explainable recommendation, which makes a user aware of why such items are recommended, is in demand. 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 personalized reason generation for explainable recommendation for songs in conversation applications and propose a solution that generates a natural language explanation of the reason for recommending a song to that particular user. For example, if the user is a student, our method can generate an output such as "Campus radio plays this song at noon every day, and I think it sounds wonderful," which the student may find easy to relate to. In the offline experiments, through manual assessments, the gain of our method is statistically significant on the relevance to songs and personalization to users comparing with baselines. Large-scale online experiments show that our method outperforms manually selected reasons by 8.2% in terms of click-Through rate. Evaluation results indicate that our generated reasons are relevant to songs and personalized to users, and they attract users to click the recommendations.
KW - Conversational recommendation
KW - explainable recommendation
KW - natural language generation
KW - personalization
KW - recommender system
UR - http://www.scopus.com/inward/record.url?scp=85069505877&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85069505877&partnerID=8YFLogxK
U2 - 10.1145/3337967
DO - 10.1145/3337967
M3 - Article
AN - SCOPUS:85069505877
VL - 10
JO - ACM Transactions on Intelligent Systems and Technology
JF - ACM Transactions on Intelligent Systems and Technology
SN - 2157-6904
IS - 4
M1 - 41
ER -