Sentiment Analysis and Topic Modeling on Arabic Twitter Data during Covid-19 Pandemic
Twitter Sentiment Analysis is the task of detecting opinions and sentiments in tweets using different algorithms. In our research work, we conducted a study to analyze and compare different Algorithms of Machine Learning (MLAs) for the classification task, and hence we collected 37 875 Moroccan twee...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
CV. Literasi Indonesia
2022-02-01
|
| Series: | Indonesian Journal of Innovation and Applied Sciences |
| Subjects: | |
| Online Access: | https://ojs.literacyinstitute.org/index.php/ijias/article/view/432 |
| _version_ | 1819279523633430528 |
|---|---|
| author | Nassera Habbat Houda Anoun Larbi Hassouni |
| author_facet | Nassera Habbat Houda Anoun Larbi Hassouni |
| author_sort | Nassera Habbat |
| collection | DOAJ |
| description | Twitter Sentiment Analysis is the task of detecting opinions and sentiments in tweets using different algorithms. In our research work, we conducted a study to analyze and compare different Algorithms of Machine Learning (MLAs) for the classification task, and hence we collected 37 875 Moroccan tweets, during the COVID-19 pandemic, from 01 March 2020 to 28 June 2020. The analysis was done using six classification algorithms (Naive Bayes, Logistic Regression, Support Vector Machine, K-Nearest Neighbors, Decision Tree, Random Forest classifier) and considering Accuracy, Recall, Precision, and F-Score as evaluation parameters. Then we applied topic modeling over the three classified tweets categories (negative, positive, and neutral) using Latent Dirichlet Allocation (LDA) which is among the most effective approaches to extract discussed topics. As result, the logistic regression classifier gave the best predictions of sentiments with an accuracy of 68.80%. |
| first_indexed | 2024-12-24T00:29:16Z |
| format | Article |
| id | doaj.art-3ddb4b39452c4a1fa016ad5db164aaa8 |
| institution | Directory Open Access Journal |
| issn | 2775-4162 |
| language | English |
| last_indexed | 2024-12-24T00:29:16Z |
| publishDate | 2022-02-01 |
| publisher | CV. Literasi Indonesia |
| record_format | Article |
| series | Indonesian Journal of Innovation and Applied Sciences |
| spelling | doaj.art-3ddb4b39452c4a1fa016ad5db164aaa82022-12-21T17:24:18ZengCV. Literasi IndonesiaIndonesian Journal of Innovation and Applied Sciences2775-41622022-02-0121606710.47540/ijias.v2i1.432433Sentiment Analysis and Topic Modeling on Arabic Twitter Data during Covid-19 PandemicNassera Habbat0Houda Anoun1Larbi Hassouni2Ecole Superieure de Technologie Hassan II University, MoroccoEcole Superieure de Technologie Hassan II University, MoroccoEcole Superieure de Technologie Hassan II University, MoroccoTwitter Sentiment Analysis is the task of detecting opinions and sentiments in tweets using different algorithms. In our research work, we conducted a study to analyze and compare different Algorithms of Machine Learning (MLAs) for the classification task, and hence we collected 37 875 Moroccan tweets, during the COVID-19 pandemic, from 01 March 2020 to 28 June 2020. The analysis was done using six classification algorithms (Naive Bayes, Logistic Regression, Support Vector Machine, K-Nearest Neighbors, Decision Tree, Random Forest classifier) and considering Accuracy, Recall, Precision, and F-Score as evaluation parameters. Then we applied topic modeling over the three classified tweets categories (negative, positive, and neutral) using Latent Dirichlet Allocation (LDA) which is among the most effective approaches to extract discussed topics. As result, the logistic regression classifier gave the best predictions of sentiments with an accuracy of 68.80%.https://ojs.literacyinstitute.org/index.php/ijias/article/view/432latent dirichlet allocationsentiment analysistopic modelingtwitter |
| spellingShingle | Nassera Habbat Houda Anoun Larbi Hassouni Sentiment Analysis and Topic Modeling on Arabic Twitter Data during Covid-19 Pandemic Indonesian Journal of Innovation and Applied Sciences latent dirichlet allocation sentiment analysis topic modeling |
| title | Sentiment Analysis and Topic Modeling on Arabic Twitter Data during Covid-19 Pandemic |
| title_full | Sentiment Analysis and Topic Modeling on Arabic Twitter Data during Covid-19 Pandemic |
| title_fullStr | Sentiment Analysis and Topic Modeling on Arabic Twitter Data during Covid-19 Pandemic |
| title_full_unstemmed | Sentiment Analysis and Topic Modeling on Arabic Twitter Data during Covid-19 Pandemic |
| title_short | Sentiment Analysis and Topic Modeling on Arabic Twitter Data during Covid-19 Pandemic |
| title_sort | sentiment analysis and topic modeling on arabic twitter data during covid 19 pandemic |
| topic | latent dirichlet allocation sentiment analysis topic modeling |
| url | https://ojs.literacyinstitute.org/index.php/ijias/article/view/432 |
| work_keys_str_mv | AT nasserahabbat sentimentanalysisandtopicmodelingonarabictwitterdataduringcovid19pandemic AT houdaanoun sentimentanalysisandtopicmodelingonarabictwitterdataduringcovid19pandemic AT larbihassouni sentimentanalysisandtopicmodelingonarabictwitterdataduringcovid19pandemic |