Detection of Hate Speech Texts Using Machine Learning Algorithm
- 26 January 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 0266-0273
Abstract
Identifying hate speech on social media has become increasingly crucial for society. It has been shown that cyberbul-lying significantly affects the social tranquillity of the Chadian population, mainly in places of conflict. This article aims to detect hate speech for texts written in “lingua franca”, a mix of the local Chadian and French languages. The dataset consists of 14,000 comments extracted from the most visited Facebook pages and annotated in four categories (hate, offence, insult and neutral) were used for this study. The data were cleaned by Natural Language Processing techniques (NLP) and applied to three word embedding methods such as Word2Vec, Doc2Vec, and Fasttext. Finally, four Machine Learning methods, namely Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbours (KNN), were computed to classify the different categories. The result showed that FastText features representation as input to SVM classifier was the best with 95.4% accuracy for predicting the comment contained insult statement followed by hate statement 93.9%. The result demonstrated our model could be used to detect the hate speech made by Chadians on social media texts.Keywords
This publication has 26 references indexed in Scilit:
- An Analysis of Demographic and Behavior Trends Using Social Media: Facebook, Twitter, and Instagram2019
- Hate Speech Classification in Social Media Using Emotional Analysis2018
- Are they Our Brothers? Analysis and Detection of Religious Hate Speech in the Arabic Twittersphere2018
- Enriching Word Vectors with Subword InformationTransactions of the Association for Computational Linguistics, 2017
- Towards enhancement of a lexicon-based approach for Saudi dialect sentiment analysisJournal of Information Science, 2017
- Deep Learning for Hate Speech Detection in Tweets2017
- Arabic tweets sentiment analysis – a hybrid schemeJournal of Information Science, 2016
- The impact of indexing approaches on Arabic text classificationJournal of Information Science, 2016
- Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter2016
- Chad1989