Publication detail

Identifying Expression of Emotions in Czech Text Using Semantic Relations for Dimension Reduction

CERVENEC, R. BURGET, R.

Original Title

Identifying Expression of Emotions in Czech Text Using Semantic Relations for Dimension Reduction

Type

journal article - other

Language

English

Original Abstract

Since the amount of information stored in the form of electronic text documents has been rapidly growing over the past few years, there is an increasing demand for tools enabling to automatically analyze these documents and benefit from their emotional content. This paper describes experiments concerned with an automatic analysis of emotions in Czech text. The selected method has some characteristics of hybrid approach to emotion recognition as it is not only based on machine learning but also utilizes a lexical database and derived domain dictionaries. A fundamental part of machine learning methods is training data set and therefore the creation of an emotional corpus is described as well. The purpose of this paper is to introduce implemented system, present and evaluate achieved results of classification of text documents into defined emotion classes.

Keywords

text processing, emotions, semantics, artificial inteligency

Authors

CERVENEC, R.; BURGET, R.

RIV year

2011

Released

20. 1. 2011

ISBN

1213-1539

Periodical

Elektrorevue - Internetový časopis (http://www.elektrorevue.cz)

Year of study

2011

Number

1

State

Czech Republic

Pages from

1

Pages to

7

Pages count

7

BibTex

@article{BUT50891,
  author="Radek {Červenec} and Radim {Burget}",
  title="Identifying Expression of Emotions in Czech Text Using Semantic Relations for Dimension Reduction",
  journal="Elektrorevue - Internetový časopis (http://www.elektrorevue.cz)",
  year="2011",
  volume="2011",
  number="1",
  pages="1--7",
  issn="1213-1539"
}