Sentiment Analysis in Social Media Networks

Abstract

After the growth of social media platforms like Twitter, there has been a marked increase in the quantity of textual information available online, including news stories and historical records. More individuals are using the internet and different forms of social media to share their thoughts and emotions with the world. Because of this, there has been a rise in the quantity of user-generated phrases that express emotions. It's natural that researchers will investigate new approaches to understanding people's emotions and reactions. In addition to providing novel hybrid systems that combine text mining and neural network for sentiment categorization, this research evaluates the efficacy of many machine learning and deep learning techniques. More than a million tweets from across five different topics were utilized to create this dataset. The datasets were split that 75% was used for training and 25% was used for testing. The findings reveal a maximum accuracy rate of 90%, demonstrating the superiority of the system's hybrid learning technique over conventional supervised methods.