The rarity, sarcasm, and spelling variations of hate speech make it difficult to identify on social media. This work uses SVM, which uses kernel functions to translate text information into high-dimensional space, to increase classification accuracy. Social media APIs and custom crawlers are used to gather data, which is subsequently preprocessed using stop-word removal, denoising, and regular expressions. Contextual semantics are improved using word embeddings from TF-IDF and Word2Vec’s Skip-gram model. BERT and sentiment analysis are used in a multi-level framework to provide sophisticated recognition. High accuracy and efficiency in the experimental results facilitate real-time hate speech identification and help create a safer online environment.https://www.mdpi.com/2078-2489/16/5/344Share this: Click to share on Facebook (Opens in new window) Facebook Click to share on X (Opens in new window) X Like this:Like Loading... Post navigation Few-shot Hate Speech Detection Based on the MindSpore Framework (arXiv) SAHSD: Enhancing Hate Speech Detection in LLM-Powered Web Applications via Sentiment Analysis and Few-Shot Learning (ACM Digital Library)