Machine Learning Approach to Classify Twitter Hate Speech

In this modern age, social media platforms have become indispensable tools for communication and information sharing. However, this unprecedented connectivity has also given rise to a concerning proliferation of hate speech and offensive content. This research article presents a comprehensive study on the development and evaluation of machine learning ML models for the automatic detection of hate speech on Twitter. We leverage a diverse dataset collected from Twitter, encompassing a wide range of hate speech categories, including hate speech targeting race, gender, religion, and more. To address the multifaceted nature of hate speech, we employ a hybrid approach that combines traditional natural language processing NLP techniques with state of the art machine learning algorithms. Our methodology involves extensive preprocessing of the text data, including tokenization, stemming, and feature extraction. We then experiment with various machine learning algorithms, including Naïve Bayes NB , K nearest Neighbor KNN , Random Forest RF , and Support Vector Machines SVM . The models are trained and fine tuned on a labeled dataset and evaluated using robust metrics to assess their performance. Subrata Saha | Md. Motinur Rahman | Md. Mahbub Alam "Machine Learning Approach to Classify Twitter Hate Speech" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-7 | Issue-5 , October 2023, URL: https://www.ijtsrd.com/papers/ijtsrd59873.pdf Paper Url: https://www.ijtsrd.com/computer-science/artificial-intelligence/59873/machine-learning-approach-to-classify-twitter-hate-speech/subrata-saha