Detecting Tweets Reporting Birth Defect Pregnancy Outcome Using Two-View CNN RNN Based Architecture

Saichethan Reddy


Abstract
This research work addresses a new multi-class classification task (fifth task) provided at the fifth Social Media Mining for Health Applications (SMM4H) workshop. This automatic tweet classification task involves distinguishing three classes of tweets that mention birth defects. We propose a novel two view based CNN-BiGRU based architectures for this task. Experimental evaluation of our proposed architecture over the validation set gives encouraging results as it improves by approximately 7% over our single view model for the fifth task. Code of our proposed framework is made available on Github
Anthology ID:
2020.smm4h-1.21
Volume:
Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Graciela Gonzalez-Hernandez, Ari Z. Klein, Ivan Flores, Davy Weissenbacher, Arjun Magge, Karen O'Connor, Abeed Sarker, Anne-Lyse Minard, Elena Tutubalina, Zulfat Miftahutdinov, Ilseyar Alimova
Venue:
SMM4H
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
125–127
Language:
URL:
https://aclanthology.org/2020.smm4h-1.21
DOI:
Bibkey:
Cite (ACL):
Saichethan Reddy. 2020. Detecting Tweets Reporting Birth Defect Pregnancy Outcome Using Two-View CNN RNN Based Architecture. In Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task, pages 125–127, Barcelona, Spain (Online). Association for Computational Linguistics.
Cite (Informal):
Detecting Tweets Reporting Birth Defect Pregnancy Outcome Using Two-View CNN RNN Based Architecture (Reddy, SMM4H 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.smm4h-1.21.pdf
Data
SMM4H