电子学报2017，Vol.45Issue(4)：1018-1024,7.DOI:10.3969/j.issn.0372-2112
基于情感标签的极性分类
Polarity Classification Based on Sentiment Tags
摘要
Abstract
Sentiment analysis is a very important technology in text mining.However,a number of systems require amounts of annotated training data in different fields.In order to solve these problems,an approach to polarity classification based on sentiment tags is proposed.Firstly,on the basis of all the documents,the sentiment-topic model is developed and the sentiment tags for each review are extracted.Then each review is divided into two sub-texts by these sentiment tags,and each sub-text is classified by exploiting the co-training algorithm.Finally,the category results of two sub-texts are combined to determine document-level polarity of each review.Experimental results show that compared with other algorithms,the method improves the classification precision without a large number of annotated samples.关键词
极性分类/情感标签/半监督学习/co-training学习Key words
polarity classification/sentiment tag/semi-supervised learning/co-training learning分类
信息技术与安全科学引用本文复制引用
周孟,朱福喜..基于情感标签的极性分类[J].电子学报,2017,45(4):1018-1024,7.基金项目
国家自然科学基金(No.61272277) （No.61272277）
