A Comprehensive Study for the Hindi Language to Implement Supervised Text Classification Techniques
Vijay Kumar Soni, Smita Selot · 2021
A large amount of feedback, comments, and postings made every second in social networking is rapidly growing the social database. Now, enormous data must be analyzed to determine the direction of people’s opinions about a certain business and its products. The bulk of evaluations on the internet are in English, however as technology develops and people’s knowledge expands, Also the amount of online information available in Hindi languages grows. To comprehend people’s sentiments around real-world things, due to this Hindi language sentiment analysis is necessary; their reviews are equally important to us. For categorization accuracy, we used the Hindi language resource for general news headlines from several news sources. For text categorization, we utilized machine learning (ML) classification methods such as Random Forest (RF), Support Vector Machines (SVM), Naive Bayes (NB), and Logistic Regression (LR), and the accuracy varied.