Text-Based Emotion Recognition in English and Polish for Therapeutic Chatbot

In this article, we present the results of our experiments on sentiment and emotion recognition for English and Polish texts, aiming to work in the context of a therapeutic chatbot. We created a dedicated dataset by adding samples of neutral texts to an existing English-language emotion-labeled corp...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Artur Zygadło, Marek Kozłowski, Artur Janicki
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	human-machine interaction chatbot sentiment recognition emotion recognition Polish language parallel text corpus Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/2367ffc32566422687116e31ad3d0359
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2367ffc32566422687116e31ad3d0359
record_format	dspace
spelling	oai:doaj.org-article:2367ffc32566422687116e31ad3d03592021-11-11T15:12:37ZText-Based Emotion Recognition in English and Polish for Therapeutic Chatbot10.3390/app1121101462076-3417https://doaj.org/article/2367ffc32566422687116e31ad3d03592021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10146https://doaj.org/toc/2076-3417In this article, we present the results of our experiments on sentiment and emotion recognition for English and Polish texts, aiming to work in the context of a therapeutic chatbot. We created a dedicated dataset by adding samples of neutral texts to an existing English-language emotion-labeled corpus. Next, using neural machine translation, we developed a Polish version of the English database. A bilingual, parallel corpus created in this way, named CORTEX (CORpus of Translated Emotional teXts), labeled with three sentiment polarity classes and nine emotion classes, was used for experiments on classification. We employed various classifiers: Naïve Bayes, Support Vector Machines, fastText, and BERT. The results obtained were satisfactory: we achieved the best scores for the BERT-based models, which yielded accuracy of over <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>90</mn><mo>%</mo></mrow></semantics></math></inline-formula> for sentiment (3-class) classification and almost <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>80</mn><mo>%</mo></mrow></semantics></math></inline-formula> for emotion (9-class) classification. We compared the results for both languages and discussed the differences. Both the accuracy and the F1-scores for Polish turned out to be slightly inferior to those for English, with the highest difference visible for BERT.Artur ZygadłoMarek KozłowskiArtur JanickiMDPI AGarticlehuman-machine interactionchatbotsentiment recognitionemotion recognitionPolish languageparallel text corpusTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10146, p 10146 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	human-machine interaction chatbot sentiment recognition emotion recognition Polish language parallel text corpus Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	human-machine interaction chatbot sentiment recognition emotion recognition Polish language parallel text corpus Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Artur Zygadło Marek Kozłowski Artur Janicki Text-Based Emotion Recognition in English and Polish for Therapeutic Chatbot
description	In this article, we present the results of our experiments on sentiment and emotion recognition for English and Polish texts, aiming to work in the context of a therapeutic chatbot. We created a dedicated dataset by adding samples of neutral texts to an existing English-language emotion-labeled corpus. Next, using neural machine translation, we developed a Polish version of the English database. A bilingual, parallel corpus created in this way, named CORTEX (CORpus of Translated Emotional teXts), labeled with three sentiment polarity classes and nine emotion classes, was used for experiments on classification. We employed various classifiers: Naïve Bayes, Support Vector Machines, fastText, and BERT. The results obtained were satisfactory: we achieved the best scores for the BERT-based models, which yielded accuracy of over <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>90</mn><mo>%</mo></mrow></semantics></math></inline-formula> for sentiment (3-class) classification and almost <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>80</mn><mo>%</mo></mrow></semantics></math></inline-formula> for emotion (9-class) classification. We compared the results for both languages and discussed the differences. Both the accuracy and the F1-scores for Polish turned out to be slightly inferior to those for English, with the highest difference visible for BERT.
format	article
author	Artur Zygadło Marek Kozłowski Artur Janicki
author_facet	Artur Zygadło Marek Kozłowski Artur Janicki
author_sort	Artur Zygadło
title	Text-Based Emotion Recognition in English and Polish for Therapeutic Chatbot
title_short	Text-Based Emotion Recognition in English and Polish for Therapeutic Chatbot
title_full	Text-Based Emotion Recognition in English and Polish for Therapeutic Chatbot
title_fullStr	Text-Based Emotion Recognition in English and Polish for Therapeutic Chatbot
title_full_unstemmed	Text-Based Emotion Recognition in English and Polish for Therapeutic Chatbot
title_sort	text-based emotion recognition in english and polish for therapeutic chatbot
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/2367ffc32566422687116e31ad3d0359
work_keys_str_mv	AT arturzygadło textbasedemotionrecognitioninenglishandpolishfortherapeuticchatbot AT marekkozłowski textbasedemotionrecognitioninenglishandpolishfortherapeuticchatbot AT arturjanicki textbasedemotionrecognitioninenglishandpolishfortherapeuticchatbot
_version_	1718436634333020160

Text-Based Emotion Recognition in English and Polish for Therapeutic Chatbot

Ejemplares similares