Adverse Drug Reaction Detection in Twitter Using RoBERTa and Rules

Authors

Sedigh Khademi, Pari Delirhaghighi, Frada Burstein

Abstract

This paper describes the method we developed for the Task 2 English variation of the Social Media Mining for Health Applications (SMM4H) 2020 shared task. The task was to classify tweets containing adverse effects (AE) after medication intake. Our approach combined transfer learning using a RoBERTa Large Transformer model with a rule-based post-prediction correction to improve model precision. The model’s F1-Score of 0.56 on the test dataset was 10% better than the mean of the F1-Score of the best submissions in the task.

Table of Contents

Abstract

  1. Introduction
  2. Data description and preparation
  3. Model
  4. Method
    • Best model vs an ensemble
    • Rule-based correction
  5. Generated texts
  6. Results
  7. Analysis
  8. Future work

References

Link to full publication

https://aclanthology.org/2020.smm4h-1.18