计算机应用 ›› 2011, Vol. 31 ›› Issue (01): 93-96.

• 人工智能 • 上一篇    下一篇

基于语义相似度的论坛话题追踪方法

席耀一1,林琛2,李弼程3,周杰3,许旭阳1   

  1. 1. 解放军信息工程大学信息工程学院
    2. 解放军信息工程大学信息工程学院信息科学系
    3. 信息工程大学信息工程学院
  • 收稿日期:2010-06-07 修回日期:2010-07-19 发布日期:2011-01-12 出版日期:2011-01-01
  • 通讯作者: 席耀一
  • 基金资助:
    网络舆情态势分析与预警关键技术研究

Method for BBS topic tracking based on semantic similarity

  • Received:2010-06-07 Revised:2010-07-19 Online:2011-01-12 Published:2011-01-01
  • Contact: Xi Yaoyi

摘要: 现有的话题追踪方法大多面向新闻数据,将其应用于论坛时效果不够理想。结合论坛的特点,提出一种基于语义相似度的论坛话题追踪方法。该方法首先通过构建话题和帖子的关键词表建立其文本表示模型,然后利用知网计算两个关键词表的语义相似度并以此作为帖子与话题的相关程度,最后根据相关程度实现论坛话题追踪。该方法较好地避免了向量空间模型的缺陷。实验表明,该方法能比较有效地解决面向论坛的话题追踪问题。

关键词: 话题追踪, 论坛, 关键词, 语义相似度, 向量空间模型

Abstract: To study the BBS topic tracking problem, the paper discovered that most of the traditional methods of topic tracking deal with news reports, and they aren’t appropriate when they are applied to BBS. The paper utilizes the characteristics of BBS and presents a topic tracking method for BBS data based on semantic similarity. This method firstly constructs keywords tables of topic and post as their representation models, then computes the two tables’ semantic similarity with the help of HowNet which is served as correlation degree between post and topic. Finally, this method uses the correlation degree to realize BBS-oriented topic tracking. This method effectively avoids the shortage of Vector Space Model. The Experiment results show that this method can solve the problem of BBS-oriented topic tracking effectively.

Key words: Topick Tracking, BBS, key words, semantic similarity, Vector Space Model(VSM)