DocumentCode :
172477
Title :
Research on building Chinese semantic lexicon based on the concept definition of HowNet
Author :
Hui Cao ; Sen Zhang
Author_Institution :
China Nat. Language Inf. Technol. Lab., Northwest Univ. for Minorities Gansu, Lanzhou, China
fYear :
2014
fDate :
20-22 Oct. 2014
Firstpage :
29
Lastpage :
33
Abstract :
Emotional tendency refers to people´s attitude towards people or things. It is a kind of subjective judgments and it can be divided into several parts, such as praise or criticize, positive or negative, good or bad. The judgment of emotional words´ emotional tendency and the problem of how to give emotional words a weight are the base of text tendency analysis. The study of semantic weight has been widely used in text tendency analysis, public sentiment, as well as text classification. This essay extracts words from glossary concept library (refer to glossary.dat) of HowNet and polish the library. In order to make the calculation study of the emotional words´ weight more accurately, the paper studies synonyms and antonyms, as well seed words selection manually. The experiment proved the method attains the results expected in sentiment judgment, weight calculation and application in text analysis.
Keywords :
natural language processing; pattern classification; text analysis; Chinese semantic lexicon; HowNet; antonyms; concept definition; emotional tendency; emotional word weight; emotional words; glossary concept library; glossary.dat; people attitude; public sentiment; seed words selection; semantic weight; sentiment judgment; synonyms; text analysis; text classification; text tendency analysis; weight calculation; word extraction; Accuracy; Buildings; Dictionaries; Educational institutions; Knowledge based systems; Semantics; HowNet; concept definition; orientation analysis; semantic weight;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Asian Language Processing (IALP), 2014 International Conference on
Conference_Location :
Kuching
Type :
conf
DOI :
10.1109/IALP.2014.6973477
Filename :
6973477
Link To Document :
بازگشت