Home > Papers

 
 
A Topic Detection Algorithm Based on Multiple Strategies for Group Chat
Wu Xu 1 *,Chen Chunxu 2
1.Key Laboratory of Trustworthy Distributed Computing and Service, Ministry of Education; School of Cyberspace Security, BUPT; Beijing University of Posts and Telecommunications Library, No.10 XiTu Cheng Road HaiDian District Beijing 100876, China;Key Laboratory of Trustworthy Distributed Computing and Service, Ministry of Education; School of Cyberspace Security, BUPT
2.
*Correspondence author
#Submitted by
Subject:
Funding: National Key Research and Development Plan (No.Grant No.2017YFC0820603), Director’s Project Fund of Key Laboratory of Trustworthy Distributed Computing and Service (No.BUPT), Ministry of Educatio)
Opened online: 1 March 2021
Accepted by: none
Citation: Wu Xu,Chen Chunxu.A Topic Detection Algorithm Based on Multiple Strategies for Group Chat[OL]. [ 1 March 2021] http://en.paper.edu.cn/en_releasepaper/content/4753717
 
 
There are a large number of group chat messages on the Internet, and public opinion analysis requires topic detection to aggregate messages with similar discussions. Group chat topics are easy to be crossing and parallel, and group chat messages also have the characteristics of sparse text features. In order to solve these two problems, this paper proposes a multi-strategy group chat topic detection technology. On the one hand, the topic sequence is constructed to solve the problem of topic crossing and parallel, on the other hand, the user, time, type and other attributes of the message are used to make up for the shortcomings of clustering that rely solely on short text features. The results of experiments conducted on three datasets derived from real group chat logs show that this method has better performance than traditional algorithms. In addition, the types of group chat messages it can process are much more than traditional methods.
Keywords:group chat message; topic detection; short text
 
 
 

For this paper

  • PDF (0B)
  • ● Revision 0   
  • ● Print this paper
  • ● Recommend this paper to a friend
  • ● Add to my favorite list

    Saved Papers

    Please enter a name for this paper to be shown in your personalized Saved Papers list

Tags

Add yours

Related Papers

Statistics

PDF Downloaded 13
Bookmarked 0
Recommend 0
Comments Array
Submit your papers