Using a Hybrid-Classification Method to Analyze Twitter Data During Critical Events

• Published in: IEEE access Vol. 9; pp. 141023 - 141035
• Main Authors: Alhashmi, Saadat M., Khedr, Ahmed M., Arif, Ifra, El Bannany, Magdi
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Bayes factor tree augmented naive (BFTAN); Blogs; Classification; Classification algorithms; Coronaviruses; COVID-19; Data analysis; Data mining; Datasets; Empirical analysis; Expo2020; Machine learning; Sentences; Sentiment analysis; Social networking (online); Social networks; support vector machine (SVM); Support vector machines; Task analysis; Twitter data
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2021.3119063

In this paper, sentiment analysis of two critical events is presented using machine learning (ML) techniques. COVID-19 has put immense pressure across the globe and sentiment analysis of data from Twitter using ML techniques has become a hot topic. We extract the COVID-19 and Expo2020 data from twitter. First, we evaluate the Twitter data of these two significant events for sentiment analysis and then use the classification algorithm to find out the usefulness of the proposed methodology. A hybrid approach that uses supervised learning model Support Vector Machine (SVM) combined with Bayes Factor Tree Augmented Naive Bayes (BFTAN) technique is proposed to accurately classify the input tweet while keeping in mind the different challenges of sentiment analysis. Our study has four main contributions: a) hybrid classification techniques are thoroughly explored for sentiment analysis, b) a novel hybrid classification approach is proposed for sentiment analysis, c) a new Twitter dataset related to COVID-19 that can be used for future research, d) empirical study to show that the hybrid-classification approach can achieve comparable performance in improving accuracy, identifying the polarity of comparative sentences, distinguishing the intensity of opinion words, considering negative words, and handling sarcasm as well. The experimental results show that the proposed approach is robust in producing correct classification results with the tradeoff of poor time efficiency. Also, the accuracy of the proposed model is comparable to other classifiers, which is encouraging. Class distribution of each dataset demonstrates that more than 60% of tweets are negative.