Cover Image

Hybrid Feature Extraction for Multi-Label Emotion Classification in English Text Messages

Emotions are vital for identifying an individual�s attitude and mental condition. Detecting and classifying emotions in Natural Language Processing applications can improve Human�Computer Interaction systems, leading to effective decision making in organizations. Several studies on emotion class...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahanin, Z., Ismail, M.A., Singh, N.S.S., AL-Ashmori, A.
Format: Article
Published: Multidisciplinary Digital Publishing Institute (MDPI) 2023
Online Access:http://scholars.utp.edu.my/id/eprint/37421/
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85169150020&doi=10.3390%2fsu151612539&partnerID=40&md5=8985e6e6b20628d2366925d67d0bf345
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:scholars.utp.edu.my:37421
record_format eprints
spelling oai:scholars.utp.edu.my:374212023-10-04T12:43:39Z http://scholars.utp.edu.my/id/eprint/37421/ Hybrid Feature Extraction for Multi-Label Emotion Classification in English Text Messages Ahanin, Z. Ismail, M.A. Singh, N.S.S. AL-Ashmori, A. Emotions are vital for identifying an individual�s attitude and mental condition. Detecting and classifying emotions in Natural Language Processing applications can improve Human�Computer Interaction systems, leading to effective decision making in organizations. Several studies on emotion classification have employed word embedding as a feature extraction method, but they do not consider the sentiment polarity of words. Moreover, relying exclusively on deep learning models to extract linguistic features may result in misclassifications due to the small training dataset. In this paper, we present a hybrid feature extraction model using human-engineered features combined with deep learning based features for emotion classification in English text. The proposed model uses data augmentation, captures contextual information, integrates knowledge from lexical resources, and employs deep learning models, including Bidirectional Long Short-Term Memory (Bi-LSTM) and Bidirectional Encoder Representation and Transformer (BERT), to address the issues mentioned above. The proposed model with hybrid features attained the highest Jaccard accuracy on two of the benchmark datasets, with 68.40 on SemEval-2018 and 53.45 on the GoEmotions dataset. The results show the significance of the proposed technique, and we can conclude that the incorporation of the hybrid features improves the performance of the baseline models. © 2023 by the authors. Multidisciplinary Digital Publishing Institute (MDPI) 2023 Article NonPeerReviewed Ahanin, Z. and Ismail, M.A. and Singh, N.S.S. and AL-Ashmori, A. (2023) Hybrid Feature Extraction for Multi-Label Emotion Classification in English Text Messages. Sustainability (Switzerland), 15 (16). ISSN 20711050 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85169150020&doi=10.3390%2fsu151612539&partnerID=40&md5=8985e6e6b20628d2366925d67d0bf345 10.3390/su151612539 10.3390/su151612539 10.3390/su151612539
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Institutional Repository
url_provider http://eprints.utp.edu.my/
description Emotions are vital for identifying an individual�s attitude and mental condition. Detecting and classifying emotions in Natural Language Processing applications can improve Human�Computer Interaction systems, leading to effective decision making in organizations. Several studies on emotion classification have employed word embedding as a feature extraction method, but they do not consider the sentiment polarity of words. Moreover, relying exclusively on deep learning models to extract linguistic features may result in misclassifications due to the small training dataset. In this paper, we present a hybrid feature extraction model using human-engineered features combined with deep learning based features for emotion classification in English text. The proposed model uses data augmentation, captures contextual information, integrates knowledge from lexical resources, and employs deep learning models, including Bidirectional Long Short-Term Memory (Bi-LSTM) and Bidirectional Encoder Representation and Transformer (BERT), to address the issues mentioned above. The proposed model with hybrid features attained the highest Jaccard accuracy on two of the benchmark datasets, with 68.40 on SemEval-2018 and 53.45 on the GoEmotions dataset. The results show the significance of the proposed technique, and we can conclude that the incorporation of the hybrid features improves the performance of the baseline models. © 2023 by the authors.
format Article
author Ahanin, Z.
Ismail, M.A.
Singh, N.S.S.
AL-Ashmori, A.
spellingShingle Ahanin, Z.
Ismail, M.A.
Singh, N.S.S.
AL-Ashmori, A.
Hybrid Feature Extraction for Multi-Label Emotion Classification in English Text Messages
author_facet Ahanin, Z.
Ismail, M.A.
Singh, N.S.S.
AL-Ashmori, A.
author_sort Ahanin, Z.
title Hybrid Feature Extraction for Multi-Label Emotion Classification in English Text Messages
title_short Hybrid Feature Extraction for Multi-Label Emotion Classification in English Text Messages
title_full Hybrid Feature Extraction for Multi-Label Emotion Classification in English Text Messages
title_fullStr Hybrid Feature Extraction for Multi-Label Emotion Classification in English Text Messages
title_full_unstemmed Hybrid Feature Extraction for Multi-Label Emotion Classification in English Text Messages
title_sort hybrid feature extraction for multi-label emotion classification in english text messages
publisher Multidisciplinary Digital Publishing Institute (MDPI)
publishDate 2023
url http://scholars.utp.edu.my/id/eprint/37421/
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85169150020&doi=10.3390%2fsu151612539&partnerID=40&md5=8985e6e6b20628d2366925d67d0bf345
_version_ 1779441380477632512
score 13.211869

Similar Items