基于文本挖掘的网络新闻报道差异分析  

Analysis on Web Media Report Differences Based on Text Mining

作　　者：阮光册[1,2] 

机构地区：[1]上海海关学院基础部,上海201204 [2]华东师范大学,上海201204

出　　处：《情报科学》2012年第1期105-109,共5页Information Science

基　　金：2010上海市哲学社会科学规划课题一般项目(2010BTQ003)

摘　　要：运用文本挖掘技术发现网络新闻报道中潜在的、有价值的信息是情报研究的一个新尝试。笔者探讨了网络新闻的文本挖掘方法,以上海世博新闻媒体网络版报道为例,进行实证研究,并对报道差异进行对比分析。本文选取香港、台湾、境外媒体华语版、上海本地媒体对世博会相关报道,基于文本挖掘、特征提取对报道内容的差异进行阐述,并得出结论。It is a new research on how to find potential but valued information in the web media reports based on text mining technology. This paper discusses the text mining methods of web media reports. In the case of web media reports on Shanghai Expo, the author has done some empirical study to analyze the differences among different web media. The paper selected the web media reports on Expo＂ from Hong Kong, Tai Wan, overseas newspapers （Chinese version） and Shanghai, analyzed the differences among these different regions base on text mining and attribution extraction and drew some conclusions.

关 键 词：文本挖掘 网络新闻 特征提取 上海世博 

分 类 号：G350[文化科学—情报学]