Comparative Analysis of Machine Learning and Deep Learning Algorithms for the Detection of Hate Speech

Le résumé fourni par la source

Hate speech on social media platforms poses significant challenges, necessitating advanced approaches for effective detection and mitigation. The study focuses on a dataset comprising approximately 25,000 tweets classified into 3 classes: hate speech, offensive, and neither, collected from Twitter, reflecting a diverse range of linguistic expressions and sentiments. This research conducts a comparative analysis of machine learning, ensemble learning, and deep learning algorithms such as KNN, Logistic Regression, Random Forest, Support Vector Classifier, Naive Bayes, Decision Tree, Neural Network LSTM, CatBoost, Stacking, AdaBoost, XGboost, Pasting, and Bagging, in discerning hate speech from non-hateful content within the ETHOS dataset. The findings of this research provide valuable insights for the development of effective and reliable hate speech detection systems, aiding in the creation of safer online spaces and promoting healthier online discourse.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.