Title :
The Study and Implementation of Chinese Words Segmentation and Chinese Language Emotion Analysis System
Author :
Zhang, Haomin ; Shi, Boying
Author_Institution :
Sch. of Software Eng., Beijing Univ. of Posts & Telecommun., Beijing, China
Abstract :
The emotion analysis of Chinese language, basing on the foundation of Chinese words segmentation, aims to study and analyze the emotion that sentences and paragraphs express. Previous algorithm adapted Bayes Algorithm and Weight Algorithm to accomplishing the analysis part, however both of them are not as accurate as the results of some experiments and there is a large discrepancy between the analysis result and the reality on the strength degree of emotion. In this article, a new algorithm is brought forward which is based on the analysis of sentence structure combining with weight algorithm. After the segmentation of words, sentence structure and proposition words will be further analyzed. According to the result, the irrespective emotion of sentences or paragraphs will be largely filtered and finally the strength of words will be calculated and matched according to the weight algorithm. A large number of experiments show that this new algorithm can greatly improve the accuracy of emotion analysis.
Keywords :
emotion recognition; information filtering; natural language processing; psychology; text analysis; word processing; Chinese language emotion analysis system; Chinese words segmentation system; information filtering; paragraphs; proposition words; sentence structure analysis; weight algorithm; Accuracy; Algorithm design and analysis; Dictionaries; Educational institutions; Internet; Libraries; Telecommunications; Chinese emotion; public opinion; sentence structure; strong degree of word; weight algorithm; word match;
Conference_Titel :
Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2012 4th International Conference on
Conference_Location :
Nanchang, Jiangxi
Print_ISBN :
978-1-4673-1902-7
DOI :
10.1109/IHMSC.2012.179
