Title :
A multi feature fusion clustering algorithm based on Q&A community
Author :
Diandian Qian ; Yonghua Li ; Yueming Lu
Author_Institution :
Key Laboratary of Trustworthy Distributed Computing and Service, Ministry of Education, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, China 100876
Abstract :
In this paper, a multi feature fusion clustering algorithm based on the Q&A community is presented, which to extract the candidate label by performing clustering on the Q-A pairs. It is proposed to combine TF/IDF, context information entropy, word length as feature to extract, select and score keywords. The experiment not only confirms effectiveness the compared with the traditional system, but also validates the precision of the multi feature fusion model.
Keywords :
Clustering; Feature Fusion; Q&A community; TF/IDF;
Conference_Titel :
Cyberspace Technology (CCT 2013), International Conference on
Conference_Location :
Beijing, China
Electronic_ISBN :
978-1-84919-801-1
DOI :
10.1049/cp.2013.2084
