Telugu News Classification Using N-gram Model

Putting text documents into predetermined genres or categories is a critical operation in natural language processing (NLP) known as genre categorization. While a significant amount of research has been done on genre classification for languages that are widely spoken, like English, studies on less frequently spoken languages, like Telugu, are noticeably lacking. This research uses a dataset of 10,000 articles across five categories: business, sports, nation, entertainment, and editorial. The classification was performed using an N-gram model combined with the Multinomial Naive Bayes algorithm, implemented with Python libraries like NLTK and scikit-learn. The model achieved an overall accuracy of 93%, with high precision, recall, and F1-scores for all categories, demonstrating effective classification performance.