Sentiment Analysis on Twitter Data using KNN and SVM

Millions of users share opinions on various topics using micro-blogging every day. Twitter is a very popular microblogging site where users are allowed a limit of 140 characters; this kind of restriction makes the users be concise as well as expressive at the same time. For that reason, it becomes a rich source for sentiment analysis and belief mining. The aim of this paper is to develop such a functional classifier which can correctly and automatically classify the sentiment of an unknown tweet. In our work, we propose techniques to classify the sentiment label accurately. We introduce two methods: one of the methods is known as sentiment classification algorithm (SCA) based on k-nearest neighbor (KNN) and the other one is based on support vector machine (SVM). We also evaluate their performance based on real tweets. Keywords—Support Vector Machine (SVM); k-nearest neighbor (KNN); Grid Search; Confusion matrix; ROC graph; Hyperplane; Social data analysis