ThangDLU at #SMM4H 2024: Encoder-decoder models for classifying text data on social disorders in children and adolescents

TL;DR

This paper explores the use of encoder-decoder models like BART and T5 for classifying social media tweets related to social disorders in children and adolescents, achieving high F1 scores.

Contribution

It introduces the application of transfer learning with encoder-decoder models and data augmentation techniques for social media text classification in health-related tasks.

Findings

F1 score of 0.627 in Task 3

F1 score of 0.841 in Task 5

Data augmentation improved model performance

Abstract

This paper describes our participation in Task 3 and Task 5 of the #SMM4H (Social Media Mining for Health) 2024 Workshop, explicitly targeting the classification challenges within tweet data. Task 3 is a multi-class classification task centered on tweets discussing the impact of outdoor environments on symptoms of social anxiety. Task 5 involves a binary classification task focusing on tweets reporting medical disorders in children. We applied transfer learning from pre-trained encoder-decoder models such as BART-base and T5-small to identify the labels of a set of given tweets. We also presented some data augmentation methods to see their impact on the model performance. Finally, the systems obtained the best F1 score of 0.627 in Task 3 and the best F1 score of 0.841 in Task 5.