A Comparison of Machine Learning Techniques for Sentiment Analysis

Main Article Content

Shahzad Qaiser et.al

Abstract

The availability of the data has increased tremendously due to the excess usage of social media platforms like Twitter and Facebook. Due to the abundant availability of data, scientists, businesses, educationalists and other people working under different roles have started using Sentiment Analysis (SA) to get in-depth knowledge about the sentiments of the people regarding any topic of interest. There are many techniques to implement SA, and one of them is Machine Learning (ML). This study is focused on the comparison of ancient ML methods such as Naïve Bayes (NB), Decision Tree (DT), Support Vector Machine (SVM), and a modern method, i.e., Deep Learning (DL). The ML techniques are applied to a single dataset to compare their performance in terms of accuracy to understand how they perform against each other. The study found that DL performed the best with 96.41% accuracy followed by NB and SVM with 87.18% and 82.05% respectively. DT performed the poorest with 68.21% accuracy.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

Article Details

How to Cite
et.al, S. Q. (2021). A Comparison of Machine Learning Techniques for Sentiment Analysis. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(3), 1738–1744. Retrieved from https://turcomat.org/index.php/turkbilmat/article/view/999
Section
Research Articles