Hate Speech Detection and Classification in Amharic Text with Deep Learning

TL;DR

This paper presents a new dataset and a deep learning model for detecting and classifying hate speech in Amharic social media posts, achieving high accuracy and addressing a resource gap.

Contribution

The study introduces the first annotated Amharic hate speech dataset and a specialized deep learning model for classification, filling a resource gap in low-resource language processing.

Findings

Achieved 94.8% F1-score in hate speech classification

Annotated 5,000 Amharic social media posts with four hate speech categories

Demonstrated effectiveness of SBi-LSTM model for low-resource language hate speech detection

Abstract

Hate speech is a growing problem on social media. It can seriously impact society, especially in countries like Ethiopia, where it can trigger conflicts among diverse ethnic and religious groups. While hate speech detection in resource rich languages are progressing, for low resource languages such as Amharic are lacking. To address this gap, we develop Amharic hate speech data and SBi-LSTM deep learning model that can detect and classify text into four categories of hate speech: racial, religious, gender, and non-hate speech. We have annotated 5k Amharic social media post and comment data into four categories. The data is annotated using a custom annotation tool by a total of 100 native Amharic speakers. The model achieves a 94.8 F1-score performance. Future improvements will include expanding the dataset and develop state-of-the art models. Keywords: Amharic hate speech detection, classification, Amharic dataset, Deep Learning, SBi-LSTM