Offensive language identification in dravidian languages using MPNet and CNN
Social media has effectively replaced traditional forms of communication and marketing. As these platforms allow for the free expression of ideas and facts through text, images, and videos, there exists a significant need to screen them to safeguard people and organisations from objectionable inform...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-04-01
|
| Series: | International Journal of Information Management Data Insights |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667096822000945 |
| _version_ | 1797847711228100608 |
|---|---|
| author | Bharathi Raja Chakravarthi Manoj Balaji Jagadeeshan Vasanth Palanikumar Ruba Priyadharshini |
| author_facet | Bharathi Raja Chakravarthi Manoj Balaji Jagadeeshan Vasanth Palanikumar Ruba Priyadharshini |
| author_sort | Bharathi Raja Chakravarthi |
| collection | DOAJ |
| description | Social media has effectively replaced traditional forms of communication and marketing. As these platforms allow for the free expression of ideas and facts through text, images, and videos, there exists a significant need to screen them to safeguard people and organisations from objectionable information directed at them. Our work aims to categorise code-mixed social media comments and posts in Tamil, Malayalam, and Kannada into offensive or not offensive at different levels. We present a multilingual MPNet and CNN fusion model for detecting offensive language content directed at an individual (or group) in low-resource Dravidian languages at different levels. Our model is capable of handling data that has been code-mixed, such as Tamil and Latin scripts. The model was successfully validated on the datasets, achieving offensive language detection results better than those of other baseline models with weighted average F1-score of 0.85, 0.98, and 0.76, and performed better than the baseline models EWDT, and EWODT by 0.02, 0.02, 0.04 for Tamil, Malayalam, and Kannada respectively. |
| first_indexed | 2024-04-09T18:15:48Z |
| format | Article |
| id | doaj.art-8a406a67cc4b4f8ea591d777248aee9d |
| institution | Directory Open Access Journal |
| issn | 2667-0968 |
| language | English |
| last_indexed | 2024-04-09T18:15:48Z |
| publishDate | 2023-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Information Management Data Insights |
| spelling | doaj.art-8a406a67cc4b4f8ea591d777248aee9d2023-04-13T04:27:21ZengElsevierInternational Journal of Information Management Data Insights2667-09682023-04-0131100151Offensive language identification in dravidian languages using MPNet and CNNBharathi Raja Chakravarthi0Manoj Balaji Jagadeeshan1Vasanth Palanikumar2Ruba Priyadharshini3Corresponding author.; School of Computer Science, University of Galway, IrelandBirla Institute of Technology and Science Pilani, IndiaChennai Institute of Technology, Chennai, IndiaThe Gandhigram Rural Institute - Deemed University, IndiaSocial media has effectively replaced traditional forms of communication and marketing. As these platforms allow for the free expression of ideas and facts through text, images, and videos, there exists a significant need to screen them to safeguard people and organisations from objectionable information directed at them. Our work aims to categorise code-mixed social media comments and posts in Tamil, Malayalam, and Kannada into offensive or not offensive at different levels. We present a multilingual MPNet and CNN fusion model for detecting offensive language content directed at an individual (or group) in low-resource Dravidian languages at different levels. Our model is capable of handling data that has been code-mixed, such as Tamil and Latin scripts. The model was successfully validated on the datasets, achieving offensive language detection results better than those of other baseline models with weighted average F1-score of 0.85, 0.98, and 0.76, and performed better than the baseline models EWDT, and EWODT by 0.02, 0.02, 0.04 for Tamil, Malayalam, and Kannada respectively.http://www.sciencedirect.com/science/article/pii/S2667096822000945Offensive language identificationDravidian languagesCode-mixingDeep learningMPNetCNN |
| spellingShingle | Bharathi Raja Chakravarthi Manoj Balaji Jagadeeshan Vasanth Palanikumar Ruba Priyadharshini Offensive language identification in dravidian languages using MPNet and CNN International Journal of Information Management Data Insights Offensive language identification Dravidian languages Code-mixing Deep learning MPNet CNN |
| title | Offensive language identification in dravidian languages using MPNet and CNN |
| title_full | Offensive language identification in dravidian languages using MPNet and CNN |
| title_fullStr | Offensive language identification in dravidian languages using MPNet and CNN |
| title_full_unstemmed | Offensive language identification in dravidian languages using MPNet and CNN |
| title_short | Offensive language identification in dravidian languages using MPNet and CNN |
| title_sort | offensive language identification in dravidian languages using mpnet and cnn |
| topic | Offensive language identification Dravidian languages Code-mixing Deep learning MPNet CNN |
| url | http://www.sciencedirect.com/science/article/pii/S2667096822000945 |
| work_keys_str_mv | AT bharathirajachakravarthi offensivelanguageidentificationindravidianlanguagesusingmpnetandcnn AT manojbalajijagadeeshan offensivelanguageidentificationindravidianlanguagesusingmpnetandcnn AT vasanthpalanikumar offensivelanguageidentificationindravidianlanguagesusingmpnetandcnn AT rubapriyadharshini offensivelanguageidentificationindravidianlanguagesusingmpnetandcnn |