A Comparative Analysis with the Hybrid Algorithm Approach for Sentimental Analysis through Machine Learning
Ravleen Singh, Ganpat Joshi, Paras Kothari · 2021
This research work focuses on the latest studies that have used Machine learning to find a solution to sentiment analysis problems related to sentiment polarisation. In preprocessing steps, the Models applied to stop words and Bag of words to collect datasets. Even with the widespread usage and acceptance of some approaches, a superior technique for categorising the polarisation of text documents is tough to make out. Machine learning has lately evoked attention as a method for sentiment investigation. The present work proposes a machine learning-based hybrid algorithm that incorporates N-gram technique as feature extraction. It combines a Decision tree classifier and Random forest Classifier techniques as a classification for sentiment analysis. Naïve bayse, linear classifier and support vector machine approaches are perform in the perspective of sentiment classification. Finally, a comparative study with the different supervised algorithms implemented on the product reviews dataset. The performance of the model evaluated on the confusion matrix. In the comparative analysis of classification techniques, the combined technique has shown better results than previously used supervised techniques of naïve bayse, linear classifier and support vector machine.