期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：4
DOI：10.15680/ijircce.2015.0304235
出版社：S&S Publications
摘要：This paper is concerned with the problem of mining social emotions from text. Recently, with the fastdevelopment of web 2.0, more and more documents are assigned by social users with emotion labels such ashappiness, sadness, and surprise. Such emotions can provide a new aspect for document categorization, and thereforehelp online users to select related documents based on their emotional preferences. Useful as it is, the ratio withmanual emotion labels is still very tiny comparing to the huge amount of web enterprise documents. In this paper, weaim to discover the connections between social emotions and affective terms and based on which predict the socialemotion from text content automatically. More specifically, we propose a joint emotion-topic model byaugmenting Latent Dirichlet Allocation with an additional layer for emotion modeling. It first generates a set of latenttopics from emotions, followed by generating affective terms from each topic. Experimental results on an online newscollection show that the proposed model can effectively identify meaningful latent topics for each emotion. Evaluationon emotion prediction further verifies the effectiveness of the proposed model.
关键词：Text Mining; Social Emotions; Dirichlet Allocation
