Comparison of Different Machine Learning Algorithms for Sentiment Analysis

There is an exponential growth in textual content generation every day in today's world. In-app messaging such as Telegram and WhatsApp, social media websites such as Instagram & Facebook, Google searches, news publishing websites, and a variety of additional sources are the possible suppliers. Every instant, all of these sources produce massive amounts of text data. Because of the large amounts of text data, Natural Language Processing (NLP) turns out to be an important tool for interpreting the content. NLP which is a popular subtask of sentiment analysis is the topic of this research. Sentiment Analysis (SA) is a type of textual data mining that discovers and extracts subjective information. It has proven to be an excellent asset for individuals to obtain important data and for organizations to analyze the social outlook of their product, brand or service by observing electronic discussions. The study carried out in this paper primarily focuses on the implementation and performance analysis of various machine learning classification models. The experiment results show that Support Vector Machine (SVM) classifier resulted in the maximum accuracy of 82% for the provided dataset.