An efficient approach for ensemble of SVM and ANN for sentiment classification

Nowadays Opinion mining is given more important, since it provides decision makers to estimate the success of a newly proposed techniques, novel ad campaign or novel product launch. In general, supervised methods such as Support Vector Machine (SVM) and Artificial Neural Network (ANN) are used to classify the opinions. In some cases SVM performs better classification and some cases ANN performs better than SVM. To overcome this constraint, we proposed a novel ensemble classification method for opinion mining. This novel technique aims to ensemble Artificial Neural network (ANN) and Support Vector Machine (SVM) for opinion analysis. In which, weight factor of both ANN and SVM is recalibrated by comparing error value between them. The experimental results show that ensemble of ANN and SVM techniques provides high accuracy than individual.