Identifying and Categorizing Offensive Language in Social Media

TL;DR

This paper presents a classification system for detecting and categorizing offensive language in social media posts, utilizing machine learning and deep learning models to improve accuracy in identifying offensive content.

Contribution

It introduces a comprehensive system for offensive language detection and categorization, applying various models and techniques for the SemEval-2019 OffensEval task.

Findings

Deep learning models outperform traditional ML models

Data preprocessing significantly improves classification accuracy

LSTM achieves the best results among tested models

Abstract

Offensive language is pervasive in social media. Individuals frequently take advantage of the perceived anonymity of computer-mediated communication, using this to engage in behavior that many of them would not consider in real life. The automatic identification of offensive content online is an important task that has gained more attention in recent years. This task can be modeled as a supervised classification problem in which systems are trained using a dataset containing posts that are annotated with respect to the presence of some form(s) of abusive or offensive content. The objective of this study is to provide a description of a classification system built for SemEval-2019 Task 6: OffensEval. This system classifies a tweet as either offensive or not offensive (Sub-task A) and further classifies offensive tweets into categories (Sub-tasks B \& C). We trained machine learning and deep learning models along with data preprocessing and sampling techniques to come up with the best results. Models discussed include Naive Bayes, SVM, Logistic Regression, Random Forest and LSTM.