Research Article
Answer Ranking by Analyzing Characteristic of Tags and Behaviors of Users
@INPROCEEDINGS{10.1007/978-3-319-69605-8_6, author={Qian Wang and Lei Su and Yiyang Li and Junhui Liu}, title={Answer Ranking by Analyzing Characteristic of Tags and Behaviors of Users}, proceedings={Cloud Computing, Security, Privacy in New Computing Environments. 7th International Conference, CloudComp 2016, and First International Conference, SPNCE 2016, Guangzhou, China, November 25--26, and December 15--16, 2016, Proceedings}, proceedings_a={CLOUDCOMP}, year={2017}, month={11}, keywords={Community question answering system User tags Behavioral characteristics ListNet Gradient descent Feature space}, doi={10.1007/978-3-319-69605-8_6} }- Qian Wang
Lei Su
Yiyang Li
Junhui Liu
Year: 2017
Answer Ranking by Analyzing Characteristic of Tags and Behaviors of Users
CLOUDCOMP
Springer
DOI: 10.1007/978-3-319-69605-8_6
Abstract
The quality of the ranking answer is good or bad, directly affects the high quality answers for users in the community question answering system. Learning method by sorting, establish the answer ranking model, is a research hotspot in community question answering system. The characteristics of tags and behavior of users, often have a direct relationship with the answer to the users’ expectations. In this paper, ListNet is used as the ranking method which selects Neural Networks as the model and Gradient Descent as the optimization method to structure ListNet ranking model which blends in characteristics of tags and behaviors of user. Then, the ranking mode is utilized to finish experiment combining the answers feature space, and the result of experiment shows that the ListNet ranking model can improve effect of answers ranking obviously which blends in the characteristics of tags and behaviors of users.