# UBC-NLP at SemEval-2019 Task 6:Ensemble Learning of Offensive Content With Enhanced Training Data

## TL;DR

This paper presents an ensemble learning approach with enhanced training data to detect offensive content on Twitter, achieving top-10 rankings in SemEval-2019 tasks despite limited and imbalanced data.

## Contribution

It introduces data enhancement techniques combined with classical ensemble classifiers for improved offensive content detection on Twitter.

## Key findings

- Ranked 6th in sub-task B with 0.706 macro F1-score
- Ranked 9th in sub-task C with 0.587 macro F1-score
- Effective in limited, imbalanced data scenarios

## Abstract

We examine learning offensive content on Twitter with limited, imbalanced data. For the purpose, we investigate the utility of using various data enhancement methods with a host of classical ensemble classifiers. Among the 75 participating teams in SemEval-2019 sub-task B, our system ranks 6th (with 0.706 macro F1-score). For sub-task C, among the 65 participating teams, our system ranks 9th (with 0.587 macro F1-score).