Hope Speech Detection Using Social Media Discourse (Posi-Vox-2024): A Transfer Learning Approach
Background: The notion of hope is characterized as an optimistic expectation or anticipation of favorable outcomes. In the age of extensive social media usage, research has primarily focused on monolingual techniques, and the Urdu and Arabic languages have not been addressed. Purpose: This study...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
National Research University Higher School of Economics
2024-12-01
|
| Series: | Journal of Language and Education |
| Subjects: | |
| Online Access: | https://jle.hse.ru/article/view/22443 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841556004739743744 |
|---|---|
| author | Muhammad Ahmad Usman Sardar Farid Humaira Ameer Iqra Muhammad Muzzamil Ameer Hmaza Grigori Sidorov Ildar Batyrshin |
| author_facet | Muhammad Ahmad Usman Sardar Farid Humaira Ameer Iqra Muhammad Muzzamil Ameer Hmaza Grigori Sidorov Ildar Batyrshin |
| author_sort | Muhammad Ahmad |
| collection | DOAJ |
| description |
Background: The notion of hope is characterized as an optimistic expectation or anticipation of favorable outcomes. In the age of extensive social media usage, research has primarily focused on monolingual techniques, and the Urdu and Arabic languages have not been addressed.
Purpose: This study addresses joint multilingual hope speech detection in the Urdu, English, and Arabic languages using a transfer learning paradigm. We developed a new multilingual dataset named Posi-Vox-2024 and employed a joint multilingual technique to design a universal classifier for multilingual dataset. We explored the fine-tuned BERT model, which demonstrated a remarkable performance in capturing semantic and contextual information.
Method: The framework includes (1) preprocessing, (2) data representation using BERT, (3) fine-tuning, and (4) classification of hope speech into binary (‘hope’ and ‘not hope’) and multi-class (realistic, unrealistic, and generalized hope) categories.
Results: Our proposed model (BERT) demonstrated benchmark performance to our dataset, achieving 0.78 accuracy in binary classification and 0.66 in multi-class classification, with a 0.04 and 0.08 performance improvement over the baselines (Logistic Regression, in binary class 0.75 and multi class 0.61), respectively.
Conclusion: Our findings will be applied to improve automated systems for detecting and promoting supportive content in English, Arabic and Urdu on social media platforms, fostering positive online discourse. This work sets new benchmarks for multilingual hope speech detection, advancing existing knowledge and enabling future research in underrepresented languages.
|
| format | Article |
| id | doaj-art-c933a9ecba234071a2cd5a606bc4595e |
| institution | Kabale University |
| issn | 2411-7390 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | National Research University Higher School of Economics |
| record_format | Article |
| series | Journal of Language and Education |
| spelling | doaj-art-c933a9ecba234071a2cd5a606bc4595e2025-01-07T16:17:13ZengNational Research University Higher School of EconomicsJournal of Language and Education2411-73902024-12-0110410.17323/jle.2024.22443Hope Speech Detection Using Social Media Discourse (Posi-Vox-2024): A Transfer Learning ApproachMuhammad Ahmad0Usman Sardar1Farid Humaira2Ameer Iqra 3Muhammad Muzzamil4Ameer Hmaza5Grigori Sidorov6Ildar Batyrshin7Instituto Politecnico Nacional (CIC-IPN), Mexico City, MexicoInstitute of Arts and Culture, Lahore, PakistanIndependent Researcher, California, USAPennsylvania State University at Abington, PA, USAIslamia University of Bahawalpur, PakistanIslamia University of Bahawalpur, PakistanInstituto Politecnico Nacional (CIC-IPN), Mexico City, MexicoInstituto Politecnico Nacional (CIC-IPN), Mexico City, Mexico Background: The notion of hope is characterized as an optimistic expectation or anticipation of favorable outcomes. In the age of extensive social media usage, research has primarily focused on monolingual techniques, and the Urdu and Arabic languages have not been addressed. Purpose: This study addresses joint multilingual hope speech detection in the Urdu, English, and Arabic languages using a transfer learning paradigm. We developed a new multilingual dataset named Posi-Vox-2024 and employed a joint multilingual technique to design a universal classifier for multilingual dataset. We explored the fine-tuned BERT model, which demonstrated a remarkable performance in capturing semantic and contextual information. Method: The framework includes (1) preprocessing, (2) data representation using BERT, (3) fine-tuning, and (4) classification of hope speech into binary (‘hope’ and ‘not hope’) and multi-class (realistic, unrealistic, and generalized hope) categories. Results: Our proposed model (BERT) demonstrated benchmark performance to our dataset, achieving 0.78 accuracy in binary classification and 0.66 in multi-class classification, with a 0.04 and 0.08 performance improvement over the baselines (Logistic Regression, in binary class 0.75 and multi class 0.61), respectively. Conclusion: Our findings will be applied to improve automated systems for detecting and promoting supportive content in English, Arabic and Urdu on social media platforms, fostering positive online discourse. This work sets new benchmarks for multilingual hope speech detection, advancing existing knowledge and enabling future research in underrepresented languages. https://jle.hse.ru/article/view/22443Hope SpeechBERTMashine learningTwitter AnalysisSocial MediaTransfer learning |
| spellingShingle | Muhammad Ahmad Usman Sardar Farid Humaira Ameer Iqra Muhammad Muzzamil Ameer Hmaza Grigori Sidorov Ildar Batyrshin Hope Speech Detection Using Social Media Discourse (Posi-Vox-2024): A Transfer Learning Approach Journal of Language and Education Hope Speech BERT Mashine learning Twitter Analysis Social Media Transfer learning |
| title | Hope Speech Detection Using Social Media Discourse (Posi-Vox-2024): A Transfer Learning Approach |
| title_full | Hope Speech Detection Using Social Media Discourse (Posi-Vox-2024): A Transfer Learning Approach |
| title_fullStr | Hope Speech Detection Using Social Media Discourse (Posi-Vox-2024): A Transfer Learning Approach |
| title_full_unstemmed | Hope Speech Detection Using Social Media Discourse (Posi-Vox-2024): A Transfer Learning Approach |
| title_short | Hope Speech Detection Using Social Media Discourse (Posi-Vox-2024): A Transfer Learning Approach |
| title_sort | hope speech detection using social media discourse posi vox 2024 a transfer learning approach |
| topic | Hope Speech BERT Mashine learning Twitter Analysis Social Media Transfer learning |
| url | https://jle.hse.ru/article/view/22443 |
| work_keys_str_mv | AT muhammadahmad hopespeechdetectionusingsocialmediadiscourseposivox2024atransferlearningapproach AT usmansardar hopespeechdetectionusingsocialmediadiscourseposivox2024atransferlearningapproach AT faridhumaira hopespeechdetectionusingsocialmediadiscourseposivox2024atransferlearningapproach AT ameeriqra hopespeechdetectionusingsocialmediadiscourseposivox2024atransferlearningapproach AT muhammadmuzzamil hopespeechdetectionusingsocialmediadiscourseposivox2024atransferlearningapproach AT ameerhmaza hopespeechdetectionusingsocialmediadiscourseposivox2024atransferlearningapproach AT grigorisidorov hopespeechdetectionusingsocialmediadiscourseposivox2024atransferlearningapproach AT ildarbatyrshin hopespeechdetectionusingsocialmediadiscourseposivox2024atransferlearningapproach |