Comparative study of machine learning algorithms for Kannada twitter sentimental analysis

Abstract

Analyzing the client’s reviews from various online platform helps to improvise the busi ness to higher levels. These User’s opinions can be analyzed using Sentiment Analysis. Sentimental analysis on Indian languages is a tedious work as there is a wide diversity in diferent languages of the India. Kannada is one of the prominent languages in India as 43 million of Indian population use Kannada as their native language for communication and it holds 27th rank among top 30 languages across the world, as there is very less work carried out on Indian languages, especially in Kannada language, more work is required to process the Kannada language across diferent domains. The sentimental analysis on the Kannada language has the accuracy about 72% from the previous work. So, in this work, we have made comparative study of various machine learning algorithms for Kan nada Twitter sentimental analysis. It is experimented on live Twitter data and found that Multinomial Naive Bayes Classifer has performed better with accuracy of 75%.