摘要
微博作为时下热门的社交网络平台,针对其所产生的评论文本进行情感分析已经成为人工智能领域的一个研究热点。考虑到虚假评论会降低情感分析的准确度,从评论用户的状态和行为出发,提出一种基于用户状态与行为的可信度评价体系,用于提取虚假评论特征。结合该特征与PU(Positive and unlabeled)学习算法进行虚假评论识别;运用SVM分类器和随机梯度下降回归模型对去除虚假评论的文本进行主观句分类与情感分析。实验表明,进行虚假评论识别后的情感分析准确率、召回率分别达到0.88和0.89,比传统方法具有更高的分析效能。
As a popular social network platform nowadays, sentimental analysis of comments text generated by Weibo has become a hot research topic in the field of artificial intelligence. Considering that fake comments could reduce the accuracy of sentimental analysis, this paper proposed a credibility evaluation system based on users’ status and behavior to extract the features of fake comments. Combining this feature with PU learning, fake comments were identified. We used SVM classifier and stochastic gradient descent regression model to classify subjective sentences and analyze sentiments of texts that remove fake comments. Experiments show that the accuracy and recall rates of sentimental analysis after fake comments recognition are 0.88 and 0.89 respectively, which have higher analysis efficiency than traditional methods.
作者
罗昌银
但唐朋
李艳红
陈昌昊
王泰
Luo Changyin;Dan Tangpeng;Li Yanhong;Chen Changhao;Wang Tai(School of Computer,Central China Normal University,Wuhan 430079,Hubei,China;School of Computer Science,South-Central University For Nationalities,Wuhan 430074,Hubei,China;National Engineering Research Center for E-Learning,Central China Normal University,Wuhan 430079,Hubei,China)
出处
《计算机应用与软件》
北大核心
2019年第4期55-62,共8页
Computer Applications and Software
基金
国家自然科学基金项目(61309002)
湖北省自然科学基金项目(2017CFB135)
中央高校基金项目(CCNU18QN017
CZZ17003)
关键词
机器学习
情感分析
自然语言处理
虚假评论识别
PU学习算法
Machine learning
Sentimental analysis
Natural language processing
Fake comments recognition
Positive and unlabeled learning
