Proceedings of Annual Conference of China Institute of Communications (CIC 2009 E-BOOK)

Guangzhou,China,11.26-11.27,2009

ISBN: 978-1-935068-10-5 Scientific Research Publishing, USA

E-Book 604pp Pub. Date: March 2010

Category: Computer Science & Communications

Price: $80

Title: The Study on the Chinese Word Sentiment Polarity Automatic Estimation
Source: Proceedings of Annual Conference of China Institute of Communications (CIC 2009 E-BOOK) (pp 64-68)
Author(s): Jing Zhang, Campus Network Center, Panzhihua University, Panzhihua, China, 617000
Hao Jin, Department of Computer Science and Technology, Nanjing University, Nanjing, China, 210093
Abstract: The Chinese word sentiment polarity automatic judgement, the most important part of the Chinese sentiment analysis, can avoid artificial error and improve the efficiency of the subjective lexicon creation. The technology of the Chinese word sentiment polarity judgment is discussed and analyzed. The polarity was described by using the sentiment characteristics set; the model of the sentiment polarity mutual information characteristics was created based on the bi-gram dependency of POS tagging; the classifier was available by machine learning to automatically judge, compare and optimize the word sentiment polarity. All of these help to improve the properties, the highest accuracy of SVM reaches 95.47%, and the F value is up to 93.90%. So it is effective to describe the sentiment polarity by using characteristic set and to automatically judge the word sentiment polarity by machine learning and based on the mutual characteristics model.
Free SCIRP Newsletters
Copyright © 2006-2024 Scientific Research Publishing Inc. All Rights Reserved.
Top