Optimal answerer ranking for new questions in community question answering
作者：
Highlights：
• We formally described the answerer ranking problem in CQA service.
• A novel model with tensor decomposition is proposed to solve the problem.
• The parameters of the above model are learned by maximizing the multi-class AUC.
• Introducing the asker dimension improves the answerer ranking performance.
• Our approach outperforms the previous methods on two real-world CQA datasets.
摘要
•We formally described the answerer ranking problem in CQA service.•A novel model with tensor decomposition is proposed to solve the problem.•The parameters of the above model are learned by maximizing the multi-class AUC.•Introducing the asker dimension improves the answerer ranking performance.•Our approach outperforms the previous methods on two real-world CQA datasets.
论文关键词：Answerer ranking,Learn to rank,Tensor model,AUC,Community question answering
论文评审过程：Received 12 June 2014, Revised 15 July 2014, Accepted 29 July 2014, Available online 24 August 2014.
论文官网地址：https://doi.org/10.1016/j.ipm.2014.07.009
