Social Media Content Categorization Using Supervised Based Machine Learning Methods and Natural Language Processing in Bangla Language

Abstract

Social media has acquired the primary platform for people to connect. Millions of posts generate from social media consistently. The people of Bangladesh are habitually comfortable sharing their opinion on social media in the Bangla language. It is often arduous to place them in distinct categories relying on textual information. Classifying social media posts are challenging. It tends to be complicated to scrutinize when scripted in Bangla language. Our aspiration is to categorize these opinions from social platforms to enable searching, filtering, and organizing based on post sentiment. We employed the Sentiment Analysis to interpret the persuasion of the posts. We introduced a model that will classify the Bangla posts in several categories by using Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Decision Tree, Random Forest, Logistic regression algorithms. We adopted the algorithm that provides the most reliable performance to classify the social media post with quite proficient in Bangla Language