摘要
近年来,以微博为代表的社交媒体在情感分析中备受关注。然而,绝大多数现有的主题情感模型并没有充分考虑到用户性格特征,导致情感分析结果难尽人意。故该文在现有的JST模型基础上进行改进,提出一种基于时间的性格建模方法,将用户性格特征纳入主题情感模型中;鉴于微博数据包含大量的表情符号之类的特有信息,为了充分利用表情符号来提升微博情感识别性能,该文将情感符号融入JST模型中,进而提出了一种改进的主题情感联合模型UC-JST(Joint Sentiment/Topic Model Based on User Character)。通过在真实的新浪微博数据集上进行实验,结果表明UC-JST情感分类效果优于JST、TUS-LDA、JUST、TSMMF四种典型的无监督情感分类方法。
In the sentiment analysis in micro-blogs,most existing topic sentiment models do not fully consider the user’s personality characteristics.Based on the JST model,this paper proposes a time-based personality modeling method to incorporate user’s personality features into the topic sentiment model.Since the microblog data contains a lot of unique information such as emoticons,we also introduce emoticons into the JST model.As a result,an probabilistic model named UC-JST(Joint Sentimet/Topic model based on User Character)is proposed.Tested on the real Sina Weibo dataset,the results show that UC-JST performs better than JST,TUS-LDA,JUST and TSMMF in terms of sentiment classification accuracy.
作者
李玉强
黄瑜
孙念
李琳
刘爱华
LI Yuqiang;HUANG Yu;SUN Nian;LI Lin;LIU Aihua(School of Computer Science and Technology,Wuhan University of Technology,Wuhan,Hubei 430063,China;School of Energy and Power Engineering,Wuhan University of Technology,Wuhan,Hubei 430063,China)
出处
《中文信息学报》
CSCD
北大核心
2020年第7期96-104,共9页
Journal of Chinese Information Processing
基金
国家社会科学基金(15BGL048)
关键词
主题情感模型
时间
性格特征
表情符号
topic sentiment model
time
personality features
emoticons
