Accuracy Enhancement During Sentiment Analysis in Twitter Using CNN

In order to determine user sentiment, researchers are utilizing sentiment analysis on a Twitter data set that includes both graphical and textual user comments. The world is fast changing as a result of contemporary technological breakthroughs. In today's world, the Internet has become a need for everyone. People are using social network applications to voice their opinions on common issues because of the rapid rise of these platforms. Obtaining and analyzing people's answers to purchasing a product, utilizing public services, and so on is essential. Opinion mining (also known as sentiment analysis) is a common practice for getting ready for a discussion in which the sentiments that underlie various points of view are sought to be discovered. Recent years have seen the rise of sentiment analysis as a tool for determining how consumers are feeling. Textual and graphical tweets posted by users are the primary focus of current study. CNN-based technique is used for graphical content; neural networks are used for textual content. An increasing amount of attention has been paid in recent years to “tweets” (comments) and the content of these expressions in opinion research utilizing Twitter data. Because of this, the goal of this research is to find out how various sentiment analyses on Twitter data turn out. The suggested research uses a neural network machine learning method to detect feelings based on graphical input.