基于旬法信息的微博情绪识别方法研究-计算机科学.pdf

Vo1. 44 No.2 第 44 卷第2 期 计算机科学 2017 年 2 月 COMPUTER SCIENCE Feb.2017 基于旬法信息的微博情绪识别方法研究 黄磊李寿山周国栋 (苏州大学计算机科学与技术学院 苏州 215006) 摘 要 情绪识别旨在自动识别文本是否含有情绪。情绪识别是情感分析研究中的一项基本任务。针对该任务，提 出了一种基于句法信息的微博文本情绪识别方法。该方法的特色在于充分考虑了微博文本的句法信息。具体实现 中，首先利用词性标注CPOS)序列和结构句法树来表示句法信息，以分别提取POS 序列模式、重写规则和二元句法标 签作为特征进行文本表示;然后利用最大煽分类算法对微博文本进行情绪识别。实验结果表明，所提方法能够获得较 好的识别效果。 关键词 自然语言处理，微博，情绪识别，POS 序列模式，句法树 中固法分类号 TP391 文献标识码 A DOI 10. 11896/j. issn. 1002-137)♀ 2017.02.040 Emotion Recognition of Chinese Microblogs with Syntactic Information HUANG Lei LI Shou-shan ZHOU Guσdong (School of Computer Science and Technology ,Soochow University ,Suzhou 215006 ,China) Abstract Emotion recognition aims to predict the involving emotion towards a piece of text. Automatic emotion recog- nition is a basic task for sentiment analysis. ln this paper ,an emotion recognition for Chinese microblogs approach based on s严ltactic information was proposed. One distinguishing feature of the proposed method is that the microblog s s严1 tactic information is employed. Specifically ,we took advantage of POS Cpart of speech) sequence and syntactic tree to represent syntactic information in order to extract POS sequence pattern ,rewrite rules and bigrams of syntactic labels as features for text representatio几 Then， we utilized the maximum entropy algorithm to perform the classification. Experi mental studies demonstrate that our approach is very effective for emotion recognitio n. Keywords Natural language processing ,Microblog , Emotion recognition , POS sequence pattern , Syntax tree