UACH at SMM4H: a BERT based approach for classification of COVID-19 Twitter posts

摘要

This work describes the participation of the Universidad Autonoma de Chihuahua team at the Social Media Mining for Health Applications (SMM4H) 2021 shared task. Our team participated in Tasks 5 and 6, both focused on the automatic classification of tweets related to COVID-19. Task 5 considered a binary classification problem, aiming to identify self-reporting tweets of potential cases of COVID-19. On the other hand. Task 6 goal was to classify tweets containing COVID-19 symptoms. For both tasks we used models based on bidirectional encoder representations from transformers (BERT). Our objective was to determine whether a model trained on a corpus from the domain of interest could outperformed one trained on a much larger general domain corpus. Our F1 results were encouraging, 0.77 and 0.95 for Tasks 5 and 6 respectively, having achieved the highest score among all the participants in the latter.