Aspect based sentiment classication: Svd features

Research on sentiment analysis and classification is a hot research topic as it have application in several disciplines and domains. In this paper, the work is focused on classification of laptop and restaurant data set towards three different polarity categories such as positive, negative, neutral. Current work used Singular Value Decomposition(SVD) based feature for sentiment prediction as it can capture the latent relation among the data. The paper presents a comparison on classification performed using SVM via linear, polynomial and rbf kernel, naive bayes, simple logistics, random forest. Precision, recall, f1 score, accuracy are used as evaluation measure. During the evaluation it is found that the SVM with rbf and polynomial gave better classification result.