Investigating the Impact of Semi-Supervised Methods with Data Augmentation on Offensive Language Detection in Romanian Language

TL;DR

This paper evaluates semi-supervised learning combined with data augmentation techniques to improve offensive language detection in Romanian, demonstrating that certain methods significantly benefit from augmentation.

Contribution

It introduces and compares eight semi-supervised methods with data augmentation for Romanian offensive language detection, highlighting their effectiveness.

Findings

Some semi-supervised methods benefit more from data augmentation.

Augmentation techniques improve model robustness.

Certain methods outperform others with augmentation.

Abstract

Offensive language detection is a crucial task in today's digital landscape, where online platforms grapple with maintaining a respectful and inclusive environment. However, building robust offensive language detection models requires large amounts of labeled data, which can be expensive and time-consuming to obtain. Semi-supervised learning offers a feasible solution by utilizing labeled and unlabeled data to create more accurate and robust models. In this paper, we explore a few different semi-supervised methods, as well as data augmentation techniques. Concretely, we implemented eight semi-supervised methods and ran experiments for them using only the available data in the RO-Offense dataset and applying five augmentation techniques before feeding the data to the models. Experimental results demonstrate that some of them benefit more from augmentations than others.