Detecting Offensive Language in Bengali, Bodo, and Assamese using Word Unigrams, Char N-grams, Classical Machine Learning, and Deep Learning Methods

Keyphrases

• Classical Machine Learning 100%
• Deep Learning Methods 100%
• N-gram 100%
• Unigram 100%
• F1 Score 100%
• Deep Machine Learning 100%
• Machine Learning Learning 100%
• Offensive Language 100%
• Bengali 100%
• Char-N 100%
• Assamese 100%
• Bodo 100%
• Logistic Regression 66%
• Best Model 66%
• Training Set 33%
• Random Forest 33%
• Supervised Machine Learning 33%
• Support Vector Machine Classifier 33%
• Hate Speech 33%
• Multilayer Perceptron 33%
• Deep Learning Model 33%
• Offensive Language Identification 33%
• HASOC 33%
• Speech Language Identification 33%
• GitHub 33%
• GitHub Repositories 33%
• Forest Logistics 33%
• Assamese Language 33%
• Multinomial Naïve Bayes 33%

Computer Science

• Machine Learning 100%
• Deep Learning 100%
• Logistic Regression 100%
• Classical Gram 100%
• Language Identification 50%
• Deep Learning Model 50%
• Support Vector 50%
• Random Forest Classifier 50%
• Multilayer Perceptron 50%

Biochemistry, Genetics and Molecular Biology

• Support Vector Machine 100%
• Hate 100%
• Supervised Machine Learning 100%
• Random Forest 100%
• Perceptron 100%
• Bayesian Learning 100%