Abstract
Of the many social media sites available, users prefer microblogging services such as Twitter to learn about product services, social events, and political trends. Twitter is considered an important source of information in sentiment analysis applications. Supervised and unsupervised machine learning-based techniques for Twitter data analysis have been investigated in the last few years, often resulting in an incorrect classification of sentiments. In this paper, we focus on these issues and present a unified framework for classifying tweets using a hybrid classification scheme. The proposed method aims at improving the performance of Twitter-based sentiment analysis systems by incorporating 4 classifiers: (a) a slang classifier, (b) an emoticon classifier, (c) the SentiWordNet classifier, and (d) an improved domain-specific classifier. After applying the preprocessing steps, the input text is passed through the emoticon and slang classifiers. In the next stage, SentiWordNet-based and domain-specific classifiers are applied to classify the text more accurately. Finally, sentiment classification is performed at sentence and document levels. The findings revealed that the proposed method overcomes the limitations of previous methods by considering slang, emoticons, and domain-specific terms.