Deep learning approaches for Bengali cyberbullying cetection on social media: a comparative study of BiLSTM, BiGRU and BERT models
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023.
| Главные авторы: | , , , , |
|---|---|
| Другие авторы: | |
| Формат: | Диссертация |
| Язык: | English |
| Опубликовано: |
Brac University
2024
|
| Предметы: | |
| Online-ссылка: | http://hdl.handle.net/10361/23576 |
| id |
10361-23576 |
|---|---|
| record_format |
dspace |
| spelling |
10361-235762024-06-25T21:06:07Z Deep learning approaches for Bengali cyberbullying cetection on social media: a comparative study of BiLSTM, BiGRU and BERT models Fahim, Kaji Mehedi Hasan Nyla, Nasita Saha, Priti Akter, Mst. Shamima Shourav, Musfiqur Rahman Sadeque, Farig Yousuf Department of Computer Science and Engineering, Brac University Natural language processing Machine learning Fast text embedding Deep learning (Machine learning) This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023. Cataloged from the PDF version of the thesis. Includes bibliographical references (pages 36-37). As technology becomes more accessible, it is now much easier than ever to abuse someone by misusing it. Usually, people use slang or absurd language with the goal of bullying, harassing, and harming someone by using social media. Moreover, these types of cyberbullying activities are more widespread among teenagers and young people despite knowing the fact that these may break someone down emotionally and may lead them towards suicidal activities. Hence, our goal is to detect cyberbullying happening on social media in the Bengali language with the help of state-of-theart deep learning and Natural Language Processing (NLP) techniques. We have examined with 3 different algorithms such as Bi-LSTM, Bi-GRU and BERT for both multiclass and binary classification. For both binary and multiclass classifications, BERT outperformed the other two models in terms of performance with the f1 score of 0.89 for binary and 0.85 for multiclass classification. Our proposed state-of-theart transformer model BERT will detect whether a message or comment is sent to harass someone or not and could help to take immediate action against them. Therefore, our research might have a positive impact on changing the social media environment by detecting hate speeches and bullying messages. Kaji Mehedi Hasan Fahim Nasita Nyla Priti Saha Mst. Shamima Akter Musfiqur Rahman Shourav B.Sc in Computer Science 2024-06-25T06:38:45Z 2024-06-25T06:38:45Z 2023 2023-09 Thesis ID 21341038 ID 23141053 ID 20101475 ID 19101473 ID 19201116 http://hdl.handle.net/10361/23576 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 37 pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
English |
| topic |
Natural language processing Machine learning Fast text embedding Deep learning (Machine learning) |
| spellingShingle |
Natural language processing Machine learning Fast text embedding Deep learning (Machine learning) Fahim, Kaji Mehedi Hasan Nyla, Nasita Saha, Priti Akter, Mst. Shamima Shourav, Musfiqur Rahman Deep learning approaches for Bengali cyberbullying cetection on social media: a comparative study of BiLSTM, BiGRU and BERT models |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023. |
| author2 |
Sadeque, Farig Yousuf |
| author_facet |
Sadeque, Farig Yousuf Fahim, Kaji Mehedi Hasan Nyla, Nasita Saha, Priti Akter, Mst. Shamima Shourav, Musfiqur Rahman |
| format |
Thesis |
| author |
Fahim, Kaji Mehedi Hasan Nyla, Nasita Saha, Priti Akter, Mst. Shamima Shourav, Musfiqur Rahman |
| author_sort |
Fahim, Kaji Mehedi Hasan |
| title |
Deep learning approaches for Bengali cyberbullying cetection on social media: a comparative study of BiLSTM, BiGRU and BERT models |
| title_short |
Deep learning approaches for Bengali cyberbullying cetection on social media: a comparative study of BiLSTM, BiGRU and BERT models |
| title_full |
Deep learning approaches for Bengali cyberbullying cetection on social media: a comparative study of BiLSTM, BiGRU and BERT models |
| title_fullStr |
Deep learning approaches for Bengali cyberbullying cetection on social media: a comparative study of BiLSTM, BiGRU and BERT models |
| title_full_unstemmed |
Deep learning approaches for Bengali cyberbullying cetection on social media: a comparative study of BiLSTM, BiGRU and BERT models |
| title_sort |
deep learning approaches for bengali cyberbullying cetection on social media: a comparative study of bilstm, bigru and bert models |
| publisher |
Brac University |
| publishDate |
2024 |
| url |
http://hdl.handle.net/10361/23576 |
| work_keys_str_mv |
AT fahimkajimehedihasan deeplearningapproachesforbengalicyberbullyingcetectiononsocialmediaacomparativestudyofbilstmbigruandbertmodels AT nylanasita deeplearningapproachesforbengalicyberbullyingcetectiononsocialmediaacomparativestudyofbilstmbigruandbertmodels AT sahapriti deeplearningapproachesforbengalicyberbullyingcetectiononsocialmediaacomparativestudyofbilstmbigruandbertmodels AT aktermstshamima deeplearningapproachesforbengalicyberbullyingcetectiononsocialmediaacomparativestudyofbilstmbigruandbertmodels AT shouravmusfiqurrahman deeplearningapproachesforbengalicyberbullyingcetectiononsocialmediaacomparativestudyofbilstmbigruandbertmodels |
| _version_ |
1814309595486617600 |