Sentiment Analysis of Twitter Dataset using Ensemble Classification Approach

On social media, words and phrases express people's opinions about companies, services, governments, and events. The objective of sentiment analysis in the discipline of natural language processing is to extract positive or negative polarities from social media text. The exponential growth of demands for businesses and governments motivates academics to complete sentiment analysis study. For sentiment analysis, we have proposed various machine learning algorithms like Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbor (K-NN) and ensemble learning like Random Forest (RF), Gradient Boosting (GB), Voting Classifier (VC), XGBoost Classifier (XGBC), ADABoost Classifier (ADABC), Bagging Classifier (BC). Then the accuracy of each algorithm is compared and the result was quite good with GB. The accuracy of 94.99% is obtained with gradient descent.