CNN and LSTM based hybrid deep learning model for sentiment analysis on Arabic text reviews
Companies with diverse product offerings rely on customer reviews to gauge product reception. Following a purchase, customers often share their opinions on the website. Prospective buyers, prior to deciding, typically peruse these reviews to inform their choices. Analysing such feedback, whether pos...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Mehran University of Engineering and Technology
2024-04-01
|
| Series: | Mehran University Research Journal of Engineering and Technology |
| Online Access: | https://publications.muet.edu.pk/index.php/muetrj/article/view/3130 |
| _version_ | 1797209768124743680 |
|---|---|
| author | Shakeel Ahmad Sheikh Muhammad Saqib Asif Hassan Syed |
| author_facet | Shakeel Ahmad Sheikh Muhammad Saqib Asif Hassan Syed |
| author_sort | Shakeel Ahmad |
| collection | DOAJ |
| description | Companies with diverse product offerings rely on customer reviews to gauge product reception. Following a purchase, customers often share their opinions on the website. Prospective buyers, prior to deciding, typically peruse these reviews to inform their choices. Analysing such feedback, whether positive or negative, holds paramount importance for companies seeking to improve product quality. Researchers are actively exploring methods to categorize comments based on sentiment scores. Notably, customers may express their reviews in Arabic text. Despite challenges such as the structure and morphology of Arabic text, a scarcity of machine-readable Arabic dictionaries, and limited tools for handling Arabic text, minimal progress has been made in the analysis of Arabic reviews. While some attempts have been undertaken, they have achieved suboptimal accuracy. In response, the authors propose a hybrid deep learning model comprising a Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) with GlobalMaxPooling. Through multiple iterations, the authors fine-tuned the proposed model and applied it to the publicly available Arabic Reviews dataset, achieving a notable 95% accuracy, precision, recall, and F1 score. The results indicate that, when compared to alternative models, the proposed model exhibits superior accuracy. |
| first_indexed | 2024-04-24T09:59:57Z |
| format | Article |
| id | doaj.art-8efc586228e14f328b49b429ad011b64 |
| institution | Directory Open Access Journal |
| issn | 0254-7821 2413-7219 |
| language | English |
| last_indexed | 2024-04-24T09:59:57Z |
| publishDate | 2024-04-01 |
| publisher | Mehran University of Engineering and Technology |
| record_format | Article |
| series | Mehran University Research Journal of Engineering and Technology |
| spelling | doaj.art-8efc586228e14f328b49b429ad011b642024-04-13T14:13:50ZengMehran University of Engineering and TechnologyMehran University Research Journal of Engineering and Technology0254-78212413-72192024-04-0143218319410.22581/muet1982.31303130CNN and LSTM based hybrid deep learning model for sentiment analysis on Arabic text reviewsShakeel Ahmad0Sheikh Muhammad Saqib1Asif Hassan Syed2Department of Computer Science, Faculty of Computing, and Information Technology in Rabigh (FCITR), King Abdulaziz University, Jeddah, Saudi ArabiaDepartment of Computing and Information Technology, Gomal University, Dera Ismail Khan, PakistanDepartment of Computer Science, Faculty of Computing, and Information Technology in Rabigh (FCITR), King Abdulaziz University, Jeddah, Saudi ArabiaCompanies with diverse product offerings rely on customer reviews to gauge product reception. Following a purchase, customers often share their opinions on the website. Prospective buyers, prior to deciding, typically peruse these reviews to inform their choices. Analysing such feedback, whether positive or negative, holds paramount importance for companies seeking to improve product quality. Researchers are actively exploring methods to categorize comments based on sentiment scores. Notably, customers may express their reviews in Arabic text. Despite challenges such as the structure and morphology of Arabic text, a scarcity of machine-readable Arabic dictionaries, and limited tools for handling Arabic text, minimal progress has been made in the analysis of Arabic reviews. While some attempts have been undertaken, they have achieved suboptimal accuracy. In response, the authors propose a hybrid deep learning model comprising a Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) with GlobalMaxPooling. Through multiple iterations, the authors fine-tuned the proposed model and applied it to the publicly available Arabic Reviews dataset, achieving a notable 95% accuracy, precision, recall, and F1 score. The results indicate that, when compared to alternative models, the proposed model exhibits superior accuracy.https://publications.muet.edu.pk/index.php/muetrj/article/view/3130 |
| spellingShingle | Shakeel Ahmad Sheikh Muhammad Saqib Asif Hassan Syed CNN and LSTM based hybrid deep learning model for sentiment analysis on Arabic text reviews Mehran University Research Journal of Engineering and Technology |
| title | CNN and LSTM based hybrid deep learning model for sentiment analysis on Arabic text reviews |
| title_full | CNN and LSTM based hybrid deep learning model for sentiment analysis on Arabic text reviews |
| title_fullStr | CNN and LSTM based hybrid deep learning model for sentiment analysis on Arabic text reviews |
| title_full_unstemmed | CNN and LSTM based hybrid deep learning model for sentiment analysis on Arabic text reviews |
| title_short | CNN and LSTM based hybrid deep learning model for sentiment analysis on Arabic text reviews |
| title_sort | cnn and lstm based hybrid deep learning model for sentiment analysis on arabic text reviews |
| url | https://publications.muet.edu.pk/index.php/muetrj/article/view/3130 |
| work_keys_str_mv | AT shakeelahmad cnnandlstmbasedhybriddeeplearningmodelforsentimentanalysisonarabictextreviews AT sheikhmuhammadsaqib cnnandlstmbasedhybriddeeplearningmodelforsentimentanalysisonarabictextreviews AT asifhassansyed cnnandlstmbasedhybriddeeplearningmodelforsentimentanalysisonarabictextreviews |