MIDAS@SMM4H-2019: Identifying Adverse Drug Reactions and Personal Health Experience Mentions from Twitter

Debanjan Mahata, Sarthak Anand, Haimin Zhang, Simra Shahid, Laiba Mehnaz, Yaman Kumar, Rajiv Ratn Shah


Abstract
In this paper, we present our approach and the system description for the Social Media Mining for Health Applications (SMM4H) Shared Task 1,2 and 4 (2019). Our main contribution is to show the effectiveness of Transfer Learning approaches like BERT and ULMFiT, and how they generalize for the classification tasks like identification of adverse drug reaction mentions and reporting of personal health problems in tweets. We show the use of stacked embeddings combined with BLSTM+CRF tagger for identifying spans mentioning adverse drug reactions in tweets. We also show that these approaches perform well even with imbalanced dataset in comparison to undersampling and oversampling.
Anthology ID:
W19-3223
Volume:
Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Davy Weissenbacher, Graciela Gonzalez-Hernandez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
127–132
Language:
URL:
https://aclanthology.org/W19-3223
DOI:
10.18653/v1/W19-3223
Bibkey:
Cite (ACL):
Debanjan Mahata, Sarthak Anand, Haimin Zhang, Simra Shahid, Laiba Mehnaz, Yaman Kumar, and Rajiv Ratn Shah. 2019. MIDAS@SMM4H-2019: Identifying Adverse Drug Reactions and Personal Health Experience Mentions from Twitter. In Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task, pages 127–132, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
MIDAS@SMM4H-2019: Identifying Adverse Drug Reactions and Personal Health Experience Mentions from Twitter (Mahata et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-3223.pdf
Data
SMM4H