Sentiment Analysis On Movies Using Logistic Regression and SVM Classification

Abstract

In Opinion mining, the most popular task in text classification is sentiment analysis of reviews. Online or offline user opinions about a product are excellent platforms for gathering large amounts of data for sentiment analysis. As a result, sentimental analysis is a task of the product’s/object’s review by the users. To get the hidden sentiments such as a positive or negative review from the opinion mining, it is proposed to classify the given data by comparing the performance parameters. For comparison of each algorithm, the precision, Accuracy, f-measure and Recall are parameters used for performance calculations. Several methods of Machine Learning, like Logistic Regression and Support Vector Machine (SVM), are used for classification. Sentiment analysis uses two distinct text feature selection methods and three classification methods. The problem statement, in this case, is analyzing sentiment analysis across larger datasets.