基于论坛主题的网页褒贬倾向性识别

Appraisial Orientation Identification in WebPages Based on Forums Theme

褒贬倾向性识别在信息过滤、自动文摘、文本分类等领域有良好的应用前景。针对褒贬倾向性较为集中的论坛网页,提出了基于特定论坛主题的网页文本褒贬倾向性计算方法。结合句法分析和词语相似度计算方法,提取反映主题倾向的特征词,根据每个信息块的倾向性计算页面的褒贬倾向,实现了论坛网页句子级别、信息块级别和网页级别等三个层次的褒贬倾向性计算,在部分语料范围内的实验结果良好,对于此类网页的分析评价有一定的意义。

Orientation identification has good application in some fields such as information filtering, automatic summarizations, text classification and so on. Aiming at Web forums which mass appraisial orientation, present a method to calculate orientation of Webpages based on certain forums. Combining with syntax analysis and words similarity, extract trait words to reflect theme orientation, and compute the orientation of whole forums pages basing on each information block. And the calculating orientation of Web forums sentences rank, information block rank and page rank has been implemented. The computing of results of experiments at range of considerable Web data are good. It has some significance to the analysis and evaluation of this kind Webpage.