SalamNET at SemEval-2020 Task12: Deep Learning Approach for Arabic Offensive Language Detection

TL;DR

SalamNET is a deep learning system utilizing Bi-GRU for Arabic offensive language detection, achieving high accuracy and providing insights for future social media moderation tools.

Contribution

The paper introduces SalamNET, a novel Bi-GRU based model for Arabic offensive language detection, with comprehensive error analysis and evaluation of multiple deep learning architectures.

Findings

SalamNET achieved a macro-F1 score of 0.83.

Bi-GRU outperformed other models tested.

In-depth error analysis informs future improvements.

Abstract

This paper describes SalamNET, an Arabic offensive language detection system that has been submitted to SemEval 2020 shared task 12: Multilingual Offensive Language Identification in Social Media. Our approach focuses on applying multiple deep learning models and conducting in depth error analysis of results to provide system implications for future development considerations. To pursue our goal, a Recurrent Neural Network (RNN), a Gated Recurrent Unit (GRU), and Long-Short Term Memory (LSTM) models with different design architectures have been developed and evaluated. The SalamNET, a Bi-directional Gated Recurrent Unit (Bi-GRU) based model, reports a macro-F1 score of 0.83.