绿色网络博文倾向性分析算法研究  

Orientation analysis algorithm for blog text in green network

作　　者：龙珑[1] 邓伟[2] 

机构地区：[1]广西师范学院计算机与信息学院,南宁530023 [2]广西肿瘤防治研究所,南宁530021

出　　处：《计算机应用研究》2013年第4期1095-1098,共4页Application Research of Computers

基　　金：国家创新基金资助项目(10C26224504901);广西自然科学基金资助项目(2011GXNSFB0180825)

摘　　要：由于目前博客基本是文本格式,提出基于语义理解分析博文倾向性的方法。算法以HowNet情感词语词库为基础,绿色网络云系统可以创建并不断完善绿色网络系统的情感字典云数据库,使用词语相似度方法计算词语的情感权值,同时利用词语的情感权值的计算对博文倾向性作初始判定,从而得到博文的情感倾向性判定结果。最后通过实验对该方法进行验证,结果表明该算法可以有效地判定博客文本情感倾向性,为绿色网络系统是否过滤该博客提供准确依据。Because most of the blog text is text format,this paper proposed an orientation analysis algorithm of blog text on semantic comprehension in green network.Firstly,the algorithm was based on the HowNet emotional word database,and cloud system of the green network could construct and constantly improved the emotion of the green network system dictionary cloud database,then calculated the emotional weights of emotional words on the basis of similarity of the words.At the same time the green network system judged the emotional orientation of the blog by word the emotional power,next the results were amended by style of the blogger language.Finally,the experiments result show that the new algorithm can effectively judge the blog text sentiment preference,and help the green work to filer the bad emotional tendency blog.

关 键 词：绿色网络 语义理解 云数据库 倾向性分析 情感词典 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]