计算机工程与应用 ›› 2012, Vol. 48 ›› Issue (15): 129-132.

• 数据库、信号与信息处理 • 上一篇    下一篇

话题跟踪方法的研究

夏春艳1,崔广才2,李树平1   

  1. 1.牡丹江师范学院 计算机科学与技术系,黑龙江 牡丹江 157011
    2.长春理工大学 计算机科学技术学院,长春 130022
  • 出版日期:2012-05-21 发布日期:2012-05-30

Research on method of topic tracking

XIA Chunyan1, CUI Guangcai2, LI Shuping1   

  1. 1.Department of Computer Science and Technology, Mudanjiang Normal University, Mudanjiang, Heilongjiang 157011, China
    2.School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China
  • Online:2012-05-21 Published:2012-05-30

摘要: 话题跟踪旨在实现对新闻媒体信息流中已知话题的动态跟踪。在现有的向量空间模型分类算法的基础上,提出一种基于话题更新的话题跟踪算法,通过实验对其进行评价。

关键词: 话题检测, 话题跟踪, 向量空间模型, K最近邻居

Abstract: Topic tracking aims at tracking stories on known topic from the information stream of news media. In the vector space model based on classification algorithm, tracking algorithm is proposed based on updated topic and it is evaluated through experiments.

Key words: topic detection, topic tracking, vector space model, K-Nearest Neighbor(KNN)