Arabic sentiment analysis about online learning to mitigate covid-19

The Covid-19 pandemic is forcing organizations to innovate and change their strategies for a new reality. This study collects online learning related tweets in Arabic language to perform a comprehensive emotion mining and sentiment analysis (SA) during the pandemic. The present study exploits Natura...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor principal: Ali Manal Mostafa
Formato: article
Lenguaje:EN
Publicado: De Gruyter 2021
Materias:
Q
Acceso en línea:https://doaj.org/article/65397c9cbafa4ea5b00febb645edf9d5
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:65397c9cbafa4ea5b00febb645edf9d5
record_format dspace
spelling oai:doaj.org-article:65397c9cbafa4ea5b00febb645edf9d52021-12-05T14:10:51ZArabic sentiment analysis about online learning to mitigate covid-192191-026X10.1515/jisys-2020-0115https://doaj.org/article/65397c9cbafa4ea5b00febb645edf9d52021-04-01T00:00:00Zhttps://doi.org/10.1515/jisys-2020-0115https://doaj.org/toc/2191-026XThe Covid-19 pandemic is forcing organizations to innovate and change their strategies for a new reality. This study collects online learning related tweets in Arabic language to perform a comprehensive emotion mining and sentiment analysis (SA) during the pandemic. The present study exploits Natural Language Processing (NLP) and Machine Learning (ML) algorithms to extract subjective information, determine polarity and detect the feeling. We begin with pulling out the tweets using Twitter APIs and then preparing for intensive preprocessing. Second, the National Research Council Canada (NRC) Word-Emotion Lexicon was examined to calculate the presence of the eight emotions at their emotional weight. Third, Information Gain (IG) is used as a filtering technique. Fourth, the latent reasons behind the negative sentiments were recognized and analyzed. Finally, different classification algorithms including Naïve Bayes (NB), Multinomial Naïve Bayes (MNB), K Nearest Neighbor (KNN), Logistic Regression (LR), and Support Vector Machine (SVM) were examined. The experiments reveal that the proposed model performs well in analyzing the perception of people about coronavirus with a maximum accuracy of about 89.6% using SVM classifier.Ali Manal MostafaDe Gruyterarticlesentiment analysismachine learningarabiccovid-19online educationemotionsScienceQElectronic computers. Computer scienceQA75.5-76.95ENJournal of Intelligent Systems, Vol 30, Iss 1, Pp 524-540 (2021)
institution DOAJ
collection DOAJ
language EN
topic sentiment analysis
machine learning
arabic
covid-19
online education
emotions
Science
Q
Electronic computers. Computer science
QA75.5-76.95
spellingShingle sentiment analysis
machine learning
arabic
covid-19
online education
emotions
Science
Q
Electronic computers. Computer science
QA75.5-76.95
Ali Manal Mostafa
Arabic sentiment analysis about online learning to mitigate covid-19
description The Covid-19 pandemic is forcing organizations to innovate and change their strategies for a new reality. This study collects online learning related tweets in Arabic language to perform a comprehensive emotion mining and sentiment analysis (SA) during the pandemic. The present study exploits Natural Language Processing (NLP) and Machine Learning (ML) algorithms to extract subjective information, determine polarity and detect the feeling. We begin with pulling out the tweets using Twitter APIs and then preparing for intensive preprocessing. Second, the National Research Council Canada (NRC) Word-Emotion Lexicon was examined to calculate the presence of the eight emotions at their emotional weight. Third, Information Gain (IG) is used as a filtering technique. Fourth, the latent reasons behind the negative sentiments were recognized and analyzed. Finally, different classification algorithms including Naïve Bayes (NB), Multinomial Naïve Bayes (MNB), K Nearest Neighbor (KNN), Logistic Regression (LR), and Support Vector Machine (SVM) were examined. The experiments reveal that the proposed model performs well in analyzing the perception of people about coronavirus with a maximum accuracy of about 89.6% using SVM classifier.
format article
author Ali Manal Mostafa
author_facet Ali Manal Mostafa
author_sort Ali Manal Mostafa
title Arabic sentiment analysis about online learning to mitigate covid-19
title_short Arabic sentiment analysis about online learning to mitigate covid-19
title_full Arabic sentiment analysis about online learning to mitigate covid-19
title_fullStr Arabic sentiment analysis about online learning to mitigate covid-19
title_full_unstemmed Arabic sentiment analysis about online learning to mitigate covid-19
title_sort arabic sentiment analysis about online learning to mitigate covid-19
publisher De Gruyter
publishDate 2021
url https://doaj.org/article/65397c9cbafa4ea5b00febb645edf9d5
work_keys_str_mv AT alimanalmostafa arabicsentimentanalysisaboutonlinelearningtomitigatecovid19
_version_ 1718371670968762368