Abstract
This paper presents our system developed for the Social Media Mining for Health (SMM4H) 2024 Task 05. The task objective was binary classification of tweets provided in the dataset, distinguishing between those reporting medical disorders and those merely mentioning diseases. We address this challenge through the utilization of a 5-fold cross-validation approach, employing the RoBERTa-Large model. Evaluation results demonstrate an F1-score of 0.886 on the validation dataset and 0.823 on the test dataset.- Anthology ID:
- 2024.smm4h-1.12
- Volume:
- Proceedings of The 9th Social Media Mining for Health Research and Applications (SMM4H 2024) Workshop and Shared Tasks
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Dongfang Xu, Graciela Gonzalez-Hernandez
- Venues:
- SMM4H | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 55–57
- Language:
- URL:
- https://aclanthology.org/2024.smm4h-1.12
- DOI:
- Cite (ACL):
- Lipika Dey, B Naik, Oppangi Poojita, and Kovidh Pothireddi. 2024. SMM4H 2024: 5 Fold Cross Validation for Classification of tweets reporting children’s disorders. In Proceedings of The 9th Social Media Mining for Health Research and Applications (SMM4H 2024) Workshop and Shared Tasks, pages 55–57, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- SMM4H 2024: 5 Fold Cross Validation for Classification of tweets reporting children’s disorders (Dey et al., SMM4H-WS 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.smm4h-1.12.pdf