L-Boost: Identifying Offensive Texts From Social Media Post in Bengali
Due to the significant increase in Internet activity since the COVID-19 epidemic, many informal, unstructured, offensive, and even misspelled textual content has been used for online communication through various social media. The Bengali and Banglish(Bengali words written in English format) offensi...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9642973/ |
| _version_ | 1811209834774659072 |
|---|---|
| author | M. F. Mridha Md. Anwar Hussen Wadud Md. Abdul Hamid Muhammad Mostafa Monowar M. Abdullah-Al-Wadud Atif Alamri |
| author_facet | M. F. Mridha Md. Anwar Hussen Wadud Md. Abdul Hamid Muhammad Mostafa Monowar M. Abdullah-Al-Wadud Atif Alamri |
| author_sort | M. F. Mridha |
| collection | DOAJ |
| description | Due to the significant increase in Internet activity since the COVID-19 epidemic, many informal, unstructured, offensive, and even misspelled textual content has been used for online communication through various social media. The Bengali and Banglish(Bengali words written in English format) offensive texts have recently been widely used to harass and criticize people on various social media. Our deep excavation reveals that limited work has been done to identify offensive Bengali texts. In this study, we have engineered a detection mechanism using natural language processing to identify Bengali and Banglish offensive messages in social media that could abuse other people. First, different classifiers have been employed to classify the offensive text as baseline classifiers from real-life datasets. Then, we applied boosting algorithms based on baseline classifiers. AdaBoost is the most effective ensemble method called adaptive boosting, which enhances the outcomes of the classifiers. The long short-term memory (LSTM) model is used to eliminate long-term dependency problems when classifying text, but overfitting problems occur. AdaBoost has strong forecasting ability and overfitting problem does not occur easily. By considering these two powerful and diverse models, we propose L-Boost, the modified AdaBoost algorithm using bidirectional encoder representations from transformers (BERT) with LSTM models. We tested the L-Boost model on three separate datasets, including the BERT pre-trained word-embedding vector model. We find our proposed L-Boost’s efficacy better than all the baseline classification algorithms reaching an accuracy of 95.11%. |
| first_indexed | 2024-04-12T04:45:44Z |
| format | Article |
| id | doaj.art-54468f8cfc684c3fb58f1fba6159cd76 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T04:45:44Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-54468f8cfc684c3fb58f1fba6159cd762022-12-22T03:47:30ZengIEEEIEEE Access2169-35362021-01-01916468116469910.1109/ACCESS.2021.31341549642973L-Boost: Identifying Offensive Texts From Social Media Post in BengaliM. F. Mridha0https://orcid.org/0000-0001-5738-1631Md. Anwar Hussen Wadud1https://orcid.org/0000-0002-7344-0838Md. Abdul Hamid2https://orcid.org/0000-0001-9698-4726Muhammad Mostafa Monowar3https://orcid.org/0000-0003-2822-2572M. Abdullah-Al-Wadud4https://orcid.org/0000-0001-6767-3574Atif Alamri5https://orcid.org/0000-0002-1887-5193Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, BangladeshDepartment of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, BangladeshDepartment of Information Technology, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi ArabiaDepartment of Information Technology, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi ArabiaResearch Chair of Pervasive and Mobile Computing, King Saud University, Riyadh, Saudi ArabiaResearch Chair of Pervasive and Mobile Computing, King Saud University, Riyadh, Saudi ArabiaDue to the significant increase in Internet activity since the COVID-19 epidemic, many informal, unstructured, offensive, and even misspelled textual content has been used for online communication through various social media. The Bengali and Banglish(Bengali words written in English format) offensive texts have recently been widely used to harass and criticize people on various social media. Our deep excavation reveals that limited work has been done to identify offensive Bengali texts. In this study, we have engineered a detection mechanism using natural language processing to identify Bengali and Banglish offensive messages in social media that could abuse other people. First, different classifiers have been employed to classify the offensive text as baseline classifiers from real-life datasets. Then, we applied boosting algorithms based on baseline classifiers. AdaBoost is the most effective ensemble method called adaptive boosting, which enhances the outcomes of the classifiers. The long short-term memory (LSTM) model is used to eliminate long-term dependency problems when classifying text, but overfitting problems occur. AdaBoost has strong forecasting ability and overfitting problem does not occur easily. By considering these two powerful and diverse models, we propose L-Boost, the modified AdaBoost algorithm using bidirectional encoder representations from transformers (BERT) with LSTM models. We tested the L-Boost model on three separate datasets, including the BERT pre-trained word-embedding vector model. We find our proposed L-Boost’s efficacy better than all the baseline classification algorithms reaching an accuracy of 95.11%.https://ieeexplore.ieee.org/document/9642973/Offensive textsocial media harassmentnatural language processingensemble learningBERT model |
| spellingShingle | M. F. Mridha Md. Anwar Hussen Wadud Md. Abdul Hamid Muhammad Mostafa Monowar M. Abdullah-Al-Wadud Atif Alamri L-Boost: Identifying Offensive Texts From Social Media Post in Bengali IEEE Access Offensive text social media harassment natural language processing ensemble learning BERT model |
| title | L-Boost: Identifying Offensive Texts From Social Media Post in Bengali |
| title_full | L-Boost: Identifying Offensive Texts From Social Media Post in Bengali |
| title_fullStr | L-Boost: Identifying Offensive Texts From Social Media Post in Bengali |
| title_full_unstemmed | L-Boost: Identifying Offensive Texts From Social Media Post in Bengali |
| title_short | L-Boost: Identifying Offensive Texts From Social Media Post in Bengali |
| title_sort | l boost identifying offensive texts from social media post in bengali |
| topic | Offensive text social media harassment natural language processing ensemble learning BERT model |
| url | https://ieeexplore.ieee.org/document/9642973/ |
| work_keys_str_mv | AT mfmridha lboostidentifyingoffensivetextsfromsocialmediapostinbengali AT mdanwarhussenwadud lboostidentifyingoffensivetextsfromsocialmediapostinbengali AT mdabdulhamid lboostidentifyingoffensivetextsfromsocialmediapostinbengali AT muhammadmostafamonowar lboostidentifyingoffensivetextsfromsocialmediapostinbengali AT mabdullahalwadud lboostidentifyingoffensivetextsfromsocialmediapostinbengali AT atifalamri lboostidentifyingoffensivetextsfromsocialmediapostinbengali |