基于层叠模型细粒度情感要素抽取及倾向分析-模式识别与人工智能.pdfVIP

第28 卷摇 第6 期摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 模式识别与人工智能摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 Vol.28摇 No.6 摇 2015年6月摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 PR AI摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 Jun.摇 2015 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 基基于层叠模型细粒度情感要素抽取 及倾向分析* 孙摇 晓摇 摇 唐陈意 (合肥工业大学 计算机与信息学院情感计算与先进智能机器安徽省重点实验室摇 合肥230009) 摘摇 要摇 针对商品评论中的细粒度情感要素抽取问题,提出基于条件随机场模型(CRFs)和支持向量机(SVM)的 层叠模型.针对情感对象与情感词的识别,将评论的句法信息、语义信息等引入CRFs模型,进一步提高CRFs特征 模板的鲁棒性.在SVM模型中,引入情感对象和情感词的深层词义及情感词的基本情感倾向等特征,改进传统的 词包模型,对掖情感对象,情感词业词对进行细粒度的情感分类判断,从而获得商品评论中的情感关键信息:(情感对 象,情感词,情感倾向性)三元组.实验表明,文中的CRFs和SVM层叠模型可提高情感要素抽取与情感分类判断的 准确性. 关键词摇 情感计算,情感要素,语义角色,语法依存树,词义聚类 中图法分类号摇 TP391 DOI摇 10.16451/ ki.issn1003鄄6059.201506005 Fine鄄Grained Emotional Elements Extraction and Affection Analysis Based on Cascaded Model SUN Xiao,TANG Chen鄄Yi (AnhuiProvince Key Laboratory of Affective Computing andAdvanced Intelligent Machine, School of Computer and Information,Hefei University of Technology,Hefei230009) ABSTRACT For the fine鄄grained emotional elements extraction problem in product reviews,a cascaded model combining conditional randomfields (CRFs)and supportvector machine (SVM)isputforward. Aiming at the recognition of sentiment objects and emotional words, the review of syntactic and semantic informations are introduced into CRFs model to further improve the robustness of feature templates in CRFs. InSVMmodel,thefeaturesof deepsemanticinformationof sentimentobjectsandemotionalwords and basic emotional orientation of emotional words are introduced to improve the traditional bag鄄of鄄words model. The sentiment of sentiment object, emotional wo