AIR-JPMC@SMM4H'22: Classifying Self-Reported Intimate Partner Violence in Tweets with Multiple BERT-based Models

TL;DR

This paper describes an ensemble of five RoBERTa models that effectively classifies self-reported intimate partner violence in tweets, achieving top performance in a shared task.

Contribution

It introduces a novel ensemble approach using multiple BERT-based models for classifying sensitive social media content.

Findings

System outperformed baseline by 13%

Achieved best overall performance in shared task

Ensemble approach improved classification accuracy

Abstract

This paper presents our submission for the SMM4H 2022-Shared Task on the classification of self-reported intimate partner violence on Twitter (in English). The goal of this task was to accurately determine if the contents of a given tweet demonstrated someone reporting their own experience with intimate partner violence. The submitted system is an ensemble of five RoBERTa models each weighted by their respective F1-scores on the validation data-set. This system performed 13% better than the baseline and was the best performing system overall for this shared task.