计算机应用 ›› 2012, Vol. 32 ›› Issue (11): 3026-3029.DOI: 10.3724/SP.J.1087.2012.03026

• 人工智能 • 上一篇    下一篇

基于维基百科的军事舆情论坛话题追踪方法

刘晓亮   

  1. 广州军区 综合训练基地, 广西 桂林 541002
  • 收稿日期:2012-05-25 修回日期:2012-07-19 发布日期:2012-11-12 出版日期:2012-11-01
  • 通讯作者: 刘晓亮
  • 作者简介:刘晓亮(1979-),男,湖北武汉人,博士,主要研究方向:话题检测与追踪、Web数据挖掘。

BBS topic tracking method for military public opinion based on Wikipedia

LIU Xiao-liang   

  1. The Comprehensive Training Base,Guangzhou Military Area, Guilin Guangxi 541002, China
  • Received:2012-05-25 Revised:2012-07-19 Online:2012-11-12 Published:2012-11-01
  • Contact: LIU Xiao-liang

摘要: 针对互联网论坛话题追踪,提出一种基于维基百科知识的军事话题追踪方法。该方法首先以基于维基百科的词语语义相关度与共现统计方式,同时结合军事主题与帖子的结构特征建立文本图中节点间的关系边及其权重;接着以改进的基于图的链接挖掘方法选取帖子关键词;最后通过计算话题与文本关键词列表间的语义相关度实现话题追踪。实验表明,该方法无需大规模样本训练与语义知识的手工构建,能够有效解决语义稀疏对追踪所带来的负面影响,较好地追踪到军事话题帖。

关键词: 话题追踪, 维基百科, 语义相关度, 关键词选取

Abstract: A method using Wikipedia as semantic and background knowledge was proposed for public military topic tracking on BBS. The semantic profiles of a post was modeled by text graph, in which nodes and edges were considered as: Wikipediabased words semantic relevance, word cooccurrence with military themes and post structure, then a modified link mining method was utilized to extract the key words from text graph. At last, topic tracking was realized by calculating the semantic relevance of keywords between the post and topic. In the experiment, the results show that this method can effectively solve the problem of semantic feature scarcity in BBSoriented military topic tracking.

Key words: topic tracking, Wikipedia, semantic relatedness, keyword extraction

中图分类号: