一种基于TF·IEF模型的在线新闻事件探测方法  

On-line news event detection based on TF·IEF model

作　　者：张辉[1] 李国辉[1] 贾立[1] 孙博良[1] 

机构地区：[1]国防科技大学信息系统与管理学院,湖南长沙410073

出　　处：《国防科技大学学报》2013年第3期55-60,共6页Journal of National University of Defense Technology

基　　金：国家部委资助项目;国家自然科学基金资助项目(61170158);湖南省自然科学基金资助项目(12JJ5028)

摘　　要：为了提升在线新闻事件探测的性能,提出一种基于TF.IEF模型的在线新闻事件探测方法。该方法受TF.IDF思想的启发,直接计算特征词表征事件的权重,建立新的增量事件模型,并将探测过程分为两个阶段:第一阶段利用Single-Pass将一定时段内收集到的报道聚成微簇;第二阶段将微簇与已有事件进行相似性匹配,然后通过重新计算事件向量实现模型更新。实验结果表明,该方法运算速度快,特征信息丢失少,提高了探测的效率和准确率。According to the characters of web news stream,an on-line news event detection（ONED） method,based on the two-stage clustering,is proposed to solve the problem of repeated matching.A novel incremental event model was established by calculating terms weighting of events directly.Two stages are involved in our method.In the first stage,the similar reports collected in a certain period were clustered into micro-clusters.In the second,the micro-clusters were matched with existed events,and then this method updated the event model.Experiment shows that the proposed method improves the efficiency and accuracy of ONED with lower complexity and less feature information loss.

关 键 词：在线新闻事件探测 TF·IEF模型 增量事件模型 Single-Pass聚类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]