DocumentCode
3318113
Title
Semi-automatic emotion recognition from textual input based on the constructed emotion thesaurus
Author
Zhang, Yu ; Li, Zhuoming ; Ren, Fuji ; Kuroiwa, Shingo
Author_Institution
Dept. of Inf. Sci.& Intelligent Syst., Tokushima Univ., Japan
fYear
2005
fDate
30 Oct.-1 Nov. 2005
Firstpage
571
Lastpage
576
Abstract
Natural language has attracted importance to some researchers working on Emotion recognizing. Our study focuses on the semi-automatic acquisition technique to obtain the emotion information with the constructed emotion thesaurus we have made. In this paper, we set up a system to recognize the affect sensing from the sentence or the text. During the building processing of our system, we firstly construct a Chinese language emotion thesaurus, the word in which thesaurus has its own classifying (such as commendatory, derogatory sense and neuter and the image value of the corresponding emotion information. Secondly, we set up the system to recognize the object sentence including functions of the syntax analysis, accidence analysis, emotion sensing and emotion computing. The following investigations are presented to show that the concept of "image value" can be used by the constructed system to obtain the emotion information from the sentence based on the constructed emotion thesaurus.
Keywords
emotion recognition; object recognition; text analysis; thesauri; accidence analysis; emotion computing; emotion sensing; emotion thesaurus; natural language; object recognition; semiautomatic acquisition; semiautomatic emotion recognition; syntax analysis; Data mining; Emotion recognition; Information science; Intelligent systems; Natural languages; Speech; Systems engineering and theory; Text recognition; Thesauri; User interfaces;
fLanguage
English
Publisher
ieee
Conference_Titel
Natural Language Processing and Knowledge Engineering, 2005. IEEE NLP-KE '05. Proceedings of 2005 IEEE International Conference on
Print_ISBN
0-7803-9361-9
Type
conf
DOI
10.1109/NLPKE.2005.1598802
Filename
1598802
Link To Document