A Features Based Machine Learning Prediction Model for Sentiment Analysis on Social Media

Abstract

Sentiment analysis is discovering the current ideology opinion of a group of people and their thoughts. The Sentiment analysis based onthe natural reaction of people on social media platform to reflect their mantel status and state. The main poupose of sentiment analysis is to dealing with society's environment and its impact effects towards the media world and surrounding environment. However, this is the key task of understanding every part of the world. The evolution of feeling simulates the sentiment behaviours to shows different direction of reactions and feeling across time. It can help users obtain a more advanced and detailed understanding of the views and attitudes represented in the content provided by users. The development of social media platforms, such as journals, forums, blogs, micro-blogs, Twitter, and social networks, has fostered sentiment analysis. Competitive advantages for organizations are collecting corporate social media and implementing machine learning algorithms to get valuable insights. In this study, our tasks are to show Bag of Words (BoW) and Term-Frequency-Inverse-Document-Frequency (tf_idf) feature-based machine learning prediction models that can help with sentiment analysis and figure out what their customers need and want from company items. Market research is perhaps the most important field for sentiment analysis applications, aside from brand perception and customer opinion surveys and feedbacks. This study results analysis shows the crucial way of classifying social media tweets feedback into positive or negative categories via using the classifier as a baseline to demonstrate in what manner comments are important based on features for any business model and their result.