Urdu Sentiment Analysis via Multimodal Data Mining Based on Deep Learning Algorithms

Every day, a massive amount of text, audio, and video data is published on websites all over the world. This valuable data can be used to gauge global trends and public perceptions. Companies are showcasing their preferred advertisements to consumers based on their online behavioral trends. Carefull...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Urooba Sehar, Summrina Kanwal, Kia Dashtipur, Usama Mir, Ubaid Abbasi, Faiza Khan
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Multimodal sentiment analysis (MSA) Urdu sentiment analysis (URSA) convolutional neural network (CNN) long short-term memory (LSTM) Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/549a75538fd447709e4ae06590132c62
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:549a75538fd447709e4ae06590132c62
record_format	dspace
spelling	oai:doaj.org-article:549a75538fd447709e4ae06590132c622021-11-20T00:02:35ZUrdu Sentiment Analysis via Multimodal Data Mining Based on Deep Learning Algorithms2169-353610.1109/ACCESS.2021.3122025https://doaj.org/article/549a75538fd447709e4ae06590132c622021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9583225/https://doaj.org/toc/2169-3536Every day, a massive amount of text, audio, and video data is published on websites all over the world. This valuable data can be used to gauge global trends and public perceptions. Companies are showcasing their preferred advertisements to consumers based on their online behavioral trends. Carefully analyzing this raw data to uncover useful patterns is indeed a challenging task, even more so for a resource-constrained language such as Urdu. A unique Urdu language-based multimodal dataset containing 1372 expressions has been presented in this paper as a first step to address the challenge to reveal useful patterns. Secondly, we have also presented a novel framework for multimodal sentiment analysis (MSA) that incorporates acoustic, visual, and textual responses to detect context-aware sentiments. Furthermore, we have used both decision-level and feature-level fusion methods to improve sentiment polarity prediction. The experimental results demonstrated that integration of multimodal features improves the polarity detection capability of the proposed algorithm from 84.32% (with unimodal features) to 95.35% (with multimodal features).Urooba SeharSummrina KanwalKia DashtipurUsama MirUbaid AbbasiFaiza KhanIEEEarticleMultimodal sentiment analysis (MSA)Urdu sentiment analysis (URSA)convolutional neural network (CNN)long short-term memory (LSTM)Electrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 153072-153082 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Multimodal sentiment analysis (MSA) Urdu sentiment analysis (URSA) convolutional neural network (CNN) long short-term memory (LSTM) Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Multimodal sentiment analysis (MSA) Urdu sentiment analysis (URSA) convolutional neural network (CNN) long short-term memory (LSTM) Electrical engineering. Electronics. Nuclear engineering TK1-9971 Urooba Sehar Summrina Kanwal Kia Dashtipur Usama Mir Ubaid Abbasi Faiza Khan Urdu Sentiment Analysis via Multimodal Data Mining Based on Deep Learning Algorithms
description	Every day, a massive amount of text, audio, and video data is published on websites all over the world. This valuable data can be used to gauge global trends and public perceptions. Companies are showcasing their preferred advertisements to consumers based on their online behavioral trends. Carefully analyzing this raw data to uncover useful patterns is indeed a challenging task, even more so for a resource-constrained language such as Urdu. A unique Urdu language-based multimodal dataset containing 1372 expressions has been presented in this paper as a first step to address the challenge to reveal useful patterns. Secondly, we have also presented a novel framework for multimodal sentiment analysis (MSA) that incorporates acoustic, visual, and textual responses to detect context-aware sentiments. Furthermore, we have used both decision-level and feature-level fusion methods to improve sentiment polarity prediction. The experimental results demonstrated that integration of multimodal features improves the polarity detection capability of the proposed algorithm from 84.32% (with unimodal features) to 95.35% (with multimodal features).
format	article
author	Urooba Sehar Summrina Kanwal Kia Dashtipur Usama Mir Ubaid Abbasi Faiza Khan
author_facet	Urooba Sehar Summrina Kanwal Kia Dashtipur Usama Mir Ubaid Abbasi Faiza Khan
author_sort	Urooba Sehar
title	Urdu Sentiment Analysis via Multimodal Data Mining Based on Deep Learning Algorithms
title_short	Urdu Sentiment Analysis via Multimodal Data Mining Based on Deep Learning Algorithms
title_full	Urdu Sentiment Analysis via Multimodal Data Mining Based on Deep Learning Algorithms
title_fullStr	Urdu Sentiment Analysis via Multimodal Data Mining Based on Deep Learning Algorithms
title_full_unstemmed	Urdu Sentiment Analysis via Multimodal Data Mining Based on Deep Learning Algorithms
title_sort	urdu sentiment analysis via multimodal data mining based on deep learning algorithms
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/549a75538fd447709e4ae06590132c62
work_keys_str_mv	AT uroobasehar urdusentimentanalysisviamultimodaldataminingbasedondeeplearningalgorithms AT summrinakanwal urdusentimentanalysisviamultimodaldataminingbasedondeeplearningalgorithms AT kiadashtipur urdusentimentanalysisviamultimodaldataminingbasedondeeplearningalgorithms AT usamamir urdusentimentanalysisviamultimodaldataminingbasedondeeplearningalgorithms AT ubaidabbasi urdusentimentanalysisviamultimodaldataminingbasedondeeplearningalgorithms AT faizakhan urdusentimentanalysisviamultimodaldataminingbasedondeeplearningalgorithms
_version_	1718419832374820864

Urdu Sentiment Analysis via Multimodal Data Mining Based on Deep Learning Algorithms

Ejemplares similares