Automated Sentiment Analysis using Machine Learning and Deep Learning Techniques

Abstract

Due to exponential growth in Internet usage, social media has become common means of communication. People use to express opinions through social networks, review sites, blogs and forums. Daily a lot of data is generated on Internet. This data holds immense value as it can help in decision making which is possible through sentiment analysis. Sentiment analysis is the process of extracting useful information from user’s opinions. With the advancement of social media usage, sentiment analysis has become an important area of research in today’s life. But manual analysis of such a huge data is very difficult and time consuming process. So, automated sentiment analysis system is needed for analysis of this data. A number of automated systems are available online that provide a number of features for text analysis, but no one is satisfying the requirements completely. Some features are available in one tool and some in others. In this research work a customized sentiment analysis system has been developed by merging two existing systems to facilitate the features of those tools on a common platform. Secondly, a real time Twitter sentiment analysis system has been developed using machine learning to analyze Twitter data in real time. In this research work, some deep learning approaches have also been proposed.