Development of a Predictive Model for Textual Data Using Support Vector Machine Based on Diverse Kernel Functions Upon Sentiment Score Analysis

Abstract

This research work specifically focusses on the development of a predictive model for movie review data using support vector machine (SVM) classifier with its improvisations using different kernel functions upon sentiment score estimation. The predictive model development proceeds with user level data input with the data processing with the data stream for analysis. Then formal calculation of TF-IDF evaluation has been made upon data clustering using simple k-means algorithm. Once the labeled data has been sorted out, then the SVM with kernel functions corresponding to linear, sigmoid, rbf, and polynomial have been applied over the clustered data with specific parameter setting for each type of library functions. Performance of each of the kernels has been measured using precision, recall, and F-score values for each of the specified kernel, and from the analysis, it has been found that sentiment analysis using SVM linear kernel with sentiment score analysis has been found to provide an improved accuracy of about 91.18%.