Identification of extreme guilt and grave fault in bengali language

Abstract

Numerous study has been done on the Bengali Language for the extraction of information, but none of them deals with extreme guilt (বাংলা দোষ) and grave fault (গুরুচণ্ডালী দোষ) in the Bengali Language. In this study, we have described extreme guilt (বাংলা দোষ) and grave fault (গুরুচণ্ডালী দোষ). We have also used two machine learning methods, such as Logistic Regression (LR) and Support Vector Machine (SVM). We have used count vectorizer for feature extraction. Result analysis shows that SVM has better accuracy then LR. LR and SVM method has 80% and 87% of accuracy for extreme guilt (বাংলা দোষ) respectively and 60% and 85% accuracy for grave fault (গুরুচণ্ডালী দোষ) respectively.