A System for Affect Analysis of Utterances in Japanese Supported with Web Mining

Ptaszynski, Michal; Dybala, Pawel; Shi, Wenhan; Rzepka, Rafal; Araki, Kenji

A System for Affect Analysis of Utterances in Japanese Supported with Web Mining

Ptaszynski, Michal; Dybala, Pawel; Shi, Wenhan et al.

Journal of Japan Society for Fuzzy Theory and Intelligent Informatics, 2009, 21(2), 194-213

Permalink : https://hdl.handle.net/2115/63602

このアイテムのアクセス数:960件（2026-10-10 11:57 集計）

閲覧可能ファイル

ファイル	フォーマット	サイズ	閲覧回数	説明
JJSF 21-2 194-213	pdf	1.00 MB	494

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

アクセス権	open access
URI	https://hdl.handle.net/2115/63602
タイトル	A System for Affect Analysis of Utterances in Japanese Supported with Web Mining
著者	Ptaszynski, Michal ; Dybala, Pawel ; Shi, Wenhan ; Rzepka, Rafal ; Araki, Kenji
著者名 Ptaszynski, Michal
著者名 Dybala, Pawel
著者名 Shi, Wenhan
e-Rad_Researcher 80396316 著者名 Rzepka, Rafal
e-Rad_Researcher 50202742 著者名 Araki, Kenji
言語	英語
キーワード	Affect analysis
	Emotiveness
	Analysis of emotiveness
	Web mining
	Evaluation methods
発行日	2009-06-30
出版者	Japan Society for Fuzzy Theory and Intelligent Informatics
出版者	日本知能情報ファジィ学会
収録物名	Journal of Japan Society for Fuzzy Theory and Intelligent Informatics
収録物名	知能と情報
巻(号)	21(2)
ページ	194-213
抄録	We propose a method for affect analysis of textual input in Japanese supported with Web mining. The method is based on a pragmatic reasoning that emotional states of a speaker are conveyed by emotional expressions used in emotive utterances. It means that if an emotive expression is used in a sentence in a context described as emotive, the emotion conveyed in the text is revealed by the used emotive expression. The system ML-Ask (Emotive Elements / Expressions Analysis System) is constructed on the basis of this idea. An evaluation of the system is performed in which two evaluation methods are compared. To choose the most objective evaluation method we compare the most popular method in the field and a method proposed by us. The proposed evaluation method was shown to be more objective and revealed the strong and weak points of the system in detail. In the evaluation experiment ML-Ask reached human level in recognizing the general emotiveness of an utterance (0.83 balanced F-score) and 63% of human level in recognizing the specific types of emotions. We support the system with a Web mining technique to improve the performance of emotional state types extraction. In the Web mining technique emotive associations are extracted from the Web using co-occurrences of emotive expressions with morphemes of causality. The Web mining technique improved the performance of the emotional states types extraction to 85% of human performance.
資源タイプ	学術雑誌論文
出版タイプ	Version of Record
PISSN	1347-7986
EISSN	1881-7203
関連情報 (isIdenticalTo)	出版社版DOI https://doi.org/10.3156/jsoft.21.194