Edgar Morais


2022

pdf
BioInfo@UAVR@SMM4H’22: Classification and Extraction of Adverse Event mentions in Tweets using Transformer Models
Edgar Morais | José Luis Oliveira | Alina Trifan | Olga Fajarda
Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task

This paper describes BioInfo@UAVR team’s approach for adressing subtasks 1a and 1b of the Social Media Mining for Health Applications 2022 shared task. These sub-tasks deal with the classification of tweets that contain an Adverse Drug Event mentions and the detection of spans that correspond to those mentions. Our approach relies on transformer-based models, data augmentation, and an external dataset.