基于直觉模糊推理的网页在线评论情感倾向分类

CLASSIFYING EMOTIONAL TENDENCIES OF ONLINE COMMENTS IN WEBPAGES BASED ON INTUITIONISTIC FUZZY REASONING

在分析情感倾向分类的特点的基础上,提出一种基于直觉模糊推理的网页在线评论情感倾向分类方法。该方法通过样本库的学习将特征在分类时的不确定性分别用隶属度、非隶属度、犹豫度定量地描述,同时定量地考虑程度副词、转折词、否定词对表达情感的作用;然后通过对特征的直觉模糊信息的集结,按词组、句子、文本三个级别依次合成其情感倾向,得到文本的情感倾向。该方法在对公开语料库的测试中获得了很高的准确率和召回率。

An approach of emotional tendencies classification for online comments in webpages based on intuitionistic fuzzy reasoning is presented on the basis of analysing the characteristics of emotional tendencies classification. The approach employs membership function, non-membership function and hesitant function to depict respectively the uncertainties of the features being classified, quantitatively, by sample library learning, as well as takes into consideration quantitatively the roles of the adverbs of degree, the conjunctions and the negative words in sentiment expressions. Then the emotional tendencies are compounded on three levels of phrases, sentences and texts in turn by means of the aggregation of intuitionistic fuzzy information of features for obtaining the emotional tendency of the text. The presented approach achieves high precision and recall rates in the test using public corpora.