评价对象抽取和其倾向性分析.pdfVIP

24 1 Vol. 24, No . 1 2010 1 JOU RNAL OF CHINESE INFORMAT ION PROCESSIN G Jan., 2010 : 1003-00 ( 2010) 01-0084-05 , , , ( , 150001) : 情感分析近年来已经成为自然语言处理领域的热点问题, 该文对情感分析中的两项关 技术) ) ) 评价对 象抽取和倾向性判断进行了深入研究在评价对象抽取阶段, 首先使用句法分析结果获取候选评价对象, 继而结 合基于网络挖掘的PMI 算法和名词剪枝算法对候选评价对象进行筛选在倾向性判断阶段, 通过分析情感句句 型, 归纳相应的分析规则, 使用无指导的方法完成评价对象在情感句中的倾向性判断该系统参加了 COAE2008 任务三的评测, 取得了较好成绩 : 计算机应用; 中文信息处理; 情感分析; 评价对象; 倾向性判断; 句法分析 : T P391 : A Comment Target Extraction and Sentiment Classif ication LIU Hongyu, ZHAO Yanyan, QIN Bing, LIU T ing ( Information Retrieval Laboratory , School of Comput er Science and T echnology, H arbin Institut e of Technology, H arbin, H eilongjiang 150001, China) Abstract: The research on sentiment analysis is a hot issue in natural language processing . T his paper makes an intensive study of the two st ages of sentiment analysis: t he comment t arget extraction and the corresponding sentiment classification. For t he first task, w e use the syntact ic analysis to obtain the candidat s, and t hen combine PMI based on w eb mining and NN filt ering algorithm to decide the targets. For the second task, we design certain heurist ic rules by analyzing subjective sentences, and then apply these rules t o predict the orientation of opinion in the sentences. This method performs well in T ask Three of the COAE2008 i. Key words: computer application; Chinese information processing; sent iment classification; target; orientation judgment; syntactic analysis : , 1 ; ,