Sentiment analysis on Bangla conversation using machine learning approach

<span>Nowadays, online communication is more convenient and popular than face-to-face conversation. Therefore, people prefer over meetings. Enormous use chatting systems to speak with their loved ones at any given time throughout the world. People create massive quantities of conversation every second because engagement. People's feelings during period can be gleaned as useful information from these conversations. Text analysis conclusion material summarization done using sentiment by natural language processing. The for customer service portals in various e-commerce platforms crime investigations based on digital evidence increasing need a Other languages, such English, have well-developed libraries resources processing, yet there are few studies conducted Bangla. It challenging extract sentiments Bangla conversational data due language's grammatical complexity. As result, it opens vast study opportunities. So, support vector machine, multinomial naïve Bayes, k-nearest neighbors, logistic regression, decision tree, random forest was used. From dataset, extracted labeled positive negative.</span>