Automatic Hate Speech Detection in English-Odia Code Mixed Social Media Data Using Machine Learning Techniques

Hate speech on social media may spread quickly through online users and subsequently, even escalate into local vile violence heinous crimes. This paper proposes a hate detection model by means of machine learning text mining feature extraction techniques. In this study, the authors collected English-Odia code mixed data from Facebook public page manually organized them three classes. order to build binary ternary datasets, are further converted The modeling employs combination algorithm features extraction. Support vector (SVM), naïve Bayes (NB) random forest (RF) models were trained using whole dataset, with extracted based word unigram, bigram, trigram, combined n-grams, term frequency-inverse document frequency (TF-IDF), n-grams weighted TF-IDF word2vec for both datasets. Using two we developed kinds each feature—binary models. SVM achieved better performance than NB RF categories. result reveals that less confusion between non-hate