中文微博情感分析研究综述

OVERVIEW ON SENTIMENT ANALYSIS OF CHINESE MICROBLOGGING

随着微博的风靡,与之相关的研究得到学术界和工商界的广泛关注。针对中文微博情感分析的研究进行综述。将中文微博文本情感分析分为三类任务:文本预处理、情感信息抽取和情感分类,对各自的研究方法和进展进行总结。其中情感信息抽取分为情感词、主题和关系的抽取,将微博主观文本情感分类方法归结为基于语义词典的情感计算和基于机器学习的情感分类。此外,从微博网站数据构成的角度出发,对情感分析做了延伸分析。最后总结微博情感分析的研究现状,并提出今后的研究方向。

With the sweeping of microblogging,the associated research achieves widespread concerns from academia to business sector.In the paper,we summarise the studies in light of Chinese microblogging sentiment analysis.We divide the Chinese microblogging text sentiment analysis into three categories of tasks： the text pre-processing,the emotional information extraction and the sentiment classification,and present the conclusion in regard to every research method and its progress.Among them,the emotional information extraction is divided into emotional words,themes and relationships extraction,the sentiment classification method of microblogging subjective text is attributed to the semantic dictionary-based affective computing and machine learning-based sentiment classification.In addition,from the perspective of microblogging site data formation,we extend the analysis on sentiment analysis.In the end,the status quo of microblogging sentiment analysis is summarised,and the future research directions are proposed as well.