Recognition of fine-grained emotions from text

An approach based on the compositionality principle

Alena Neviarouskaya, Helmut Prendinger, Mitsuru Ishizuka

Research output: Chapter in Book/Report/Conference proceedingChapter

6 Citations (Scopus)

Abstract

This chapter addresses the tasks of recognition, interpretation and visualization of affect communicated through text messaging in virtual communication environments. In order to facilitate sensitive and expressive communication in such environments, we introduced a novel syntactic rule-based approach to affect recognition from text. Our Affect Analysis Model follows the compositionality principle, according to which emotional meaning of a sentence is determined by composing parts that correspond to lexical units or other linguistic constituent types governed by the rules of aggregation, propagation, domination, neutralization, and intensification, at various grammatical levels. The proposed rule-based approach processes each sentence in sequential stages, including symbolic cue processing, detection and transformation of abbreviations, sentence parsing, and word/phrase/sentence-level analyses. Our method is capable of processing sentences of different complexity, including simple, compound, complex (with complement and relative clauses), and complex-compound sentences. Affect in text is classified into nine emotion categories (or neutral), and, additionally, information that indicates social communicative behaviour is identified. The evaluation of the Affect Analysis Model algorithm showed promising results regarding its capability to accurately recognize affective information in text from an existing corpus of informal online conversations. The applications of the developed Affect Analysis Model in Instant Messaging system (AffectIM) and in Second Life (EmoHeart, iFeel_IM!) are described in the chapter.

Original languageEnglish
Title of host publicationSmart Innovation, Systems and Technologies
Pages179-207
Number of pages29
Volume2010
Edition1
Publication statusPublished - 2010
Externally publishedYes

Publication series

NameSmart Innovation, Systems and Technologies
Number1
Volume2010
ISSN (Print)21903018
ISSN (Electronic)21903026

Fingerprint

Text messaging
Communication
Syntactics
Processing
Linguistics
Agglomeration
Visualization
Emotion
Rule-based
Propagation
Evaluation
Second life
Domination
Instant messaging
Process approach

ASJC Scopus subject areas

  • Computer Science(all)
  • Decision Sciences(all)

Cite this

Neviarouskaya, A., Prendinger, H., & Ishizuka, M. (2010). Recognition of fine-grained emotions from text: An approach based on the compositionality principle. In Smart Innovation, Systems and Technologies (1 ed., Vol. 2010, pp. 179-207). (Smart Innovation, Systems and Technologies; Vol. 2010, No. 1).

Recognition of fine-grained emotions from text : An approach based on the compositionality principle. / Neviarouskaya, Alena; Prendinger, Helmut; Ishizuka, Mitsuru.

Smart Innovation, Systems and Technologies. Vol. 2010 1. ed. 2010. p. 179-207 (Smart Innovation, Systems and Technologies; Vol. 2010, No. 1).

Research output: Chapter in Book/Report/Conference proceedingChapter

Neviarouskaya, A, Prendinger, H & Ishizuka, M 2010, Recognition of fine-grained emotions from text: An approach based on the compositionality principle. in Smart Innovation, Systems and Technologies. 1 edn, vol. 2010, Smart Innovation, Systems and Technologies, no. 1, vol. 2010, pp. 179-207.
Neviarouskaya A, Prendinger H, Ishizuka M. Recognition of fine-grained emotions from text: An approach based on the compositionality principle. In Smart Innovation, Systems and Technologies. 1 ed. Vol. 2010. 2010. p. 179-207. (Smart Innovation, Systems and Technologies; 1).
Neviarouskaya, Alena ; Prendinger, Helmut ; Ishizuka, Mitsuru. / Recognition of fine-grained emotions from text : An approach based on the compositionality principle. Smart Innovation, Systems and Technologies. Vol. 2010 1. ed. 2010. pp. 179-207 (Smart Innovation, Systems and Technologies; 1).
@inbook{988481b074bc42b3bec8a565961f604f,
title = "Recognition of fine-grained emotions from text: An approach based on the compositionality principle",
abstract = "This chapter addresses the tasks of recognition, interpretation and visualization of affect communicated through text messaging in virtual communication environments. In order to facilitate sensitive and expressive communication in such environments, we introduced a novel syntactic rule-based approach to affect recognition from text. Our Affect Analysis Model follows the compositionality principle, according to which emotional meaning of a sentence is determined by composing parts that correspond to lexical units or other linguistic constituent types governed by the rules of aggregation, propagation, domination, neutralization, and intensification, at various grammatical levels. The proposed rule-based approach processes each sentence in sequential stages, including symbolic cue processing, detection and transformation of abbreviations, sentence parsing, and word/phrase/sentence-level analyses. Our method is capable of processing sentences of different complexity, including simple, compound, complex (with complement and relative clauses), and complex-compound sentences. Affect in text is classified into nine emotion categories (or neutral), and, additionally, information that indicates social communicative behaviour is identified. The evaluation of the Affect Analysis Model algorithm showed promising results regarding its capability to accurately recognize affective information in text from an existing corpus of informal online conversations. The applications of the developed Affect Analysis Model in Instant Messaging system (AffectIM) and in Second Life (EmoHeart, iFeel_IM!) are described in the chapter.",
author = "Alena Neviarouskaya and Helmut Prendinger and Mitsuru Ishizuka",
year = "2010",
language = "English",
isbn = "9783642126031",
volume = "2010",
series = "Smart Innovation, Systems and Technologies",
number = "1",
pages = "179--207",
booktitle = "Smart Innovation, Systems and Technologies",
edition = "1",

}

TY - CHAP

T1 - Recognition of fine-grained emotions from text

T2 - An approach based on the compositionality principle

AU - Neviarouskaya, Alena

AU - Prendinger, Helmut

AU - Ishizuka, Mitsuru

PY - 2010

Y1 - 2010

N2 - This chapter addresses the tasks of recognition, interpretation and visualization of affect communicated through text messaging in virtual communication environments. In order to facilitate sensitive and expressive communication in such environments, we introduced a novel syntactic rule-based approach to affect recognition from text. Our Affect Analysis Model follows the compositionality principle, according to which emotional meaning of a sentence is determined by composing parts that correspond to lexical units or other linguistic constituent types governed by the rules of aggregation, propagation, domination, neutralization, and intensification, at various grammatical levels. The proposed rule-based approach processes each sentence in sequential stages, including symbolic cue processing, detection and transformation of abbreviations, sentence parsing, and word/phrase/sentence-level analyses. Our method is capable of processing sentences of different complexity, including simple, compound, complex (with complement and relative clauses), and complex-compound sentences. Affect in text is classified into nine emotion categories (or neutral), and, additionally, information that indicates social communicative behaviour is identified. The evaluation of the Affect Analysis Model algorithm showed promising results regarding its capability to accurately recognize affective information in text from an existing corpus of informal online conversations. The applications of the developed Affect Analysis Model in Instant Messaging system (AffectIM) and in Second Life (EmoHeart, iFeel_IM!) are described in the chapter.

AB - This chapter addresses the tasks of recognition, interpretation and visualization of affect communicated through text messaging in virtual communication environments. In order to facilitate sensitive and expressive communication in such environments, we introduced a novel syntactic rule-based approach to affect recognition from text. Our Affect Analysis Model follows the compositionality principle, according to which emotional meaning of a sentence is determined by composing parts that correspond to lexical units or other linguistic constituent types governed by the rules of aggregation, propagation, domination, neutralization, and intensification, at various grammatical levels. The proposed rule-based approach processes each sentence in sequential stages, including symbolic cue processing, detection and transformation of abbreviations, sentence parsing, and word/phrase/sentence-level analyses. Our method is capable of processing sentences of different complexity, including simple, compound, complex (with complement and relative clauses), and complex-compound sentences. Affect in text is classified into nine emotion categories (or neutral), and, additionally, information that indicates social communicative behaviour is identified. The evaluation of the Affect Analysis Model algorithm showed promising results regarding its capability to accurately recognize affective information in text from an existing corpus of informal online conversations. The applications of the developed Affect Analysis Model in Instant Messaging system (AffectIM) and in Second Life (EmoHeart, iFeel_IM!) are described in the chapter.

UR - http://www.scopus.com/inward/record.url?scp=84865779796&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865779796&partnerID=8YFLogxK

M3 - Chapter

SN - 9783642126031

VL - 2010

T3 - Smart Innovation, Systems and Technologies

SP - 179

EP - 207

BT - Smart Innovation, Systems and Technologies

ER -