Preliminary Flu Outbreak Prediction Using Twitter Posts Classification and Linear Regression With Historical Centers for Disease Control and Prevention Reports: Prediction Framework Study

Background: Social networking sites (SNSs) such as Twitter are widely used by diverse demographic populations. The amount of data within SNSs has created an efficient resource for real-time analysis. Thus, data from SNSs can be used effectively to track disease outbreaks and provide necessary warnings. Current SNS-based flu detection and prediction frameworks apply conventional machine learning approaches that require lengthy training and testing, which is not the optimal solution for new outbreaks with new signs and symptoms. Objective: The objective of this study was to propose an efficient and accurate framework that uses data from SNSs to track disease outbreaks and provide early warnings, even for newest outbreaks, accurately. Methods: We presented a framework of outbreak prediction that included 3 main modules: text classification, mapping, and linear regression for weekly flu rate predictions. The text classification module used the features of sentiment analysis and predefined keyword occurrences. Various classifiers, including FastText (FT) and 6 conventional machine learning algorithms, were evaluated to identify the most efficient and accurate one for the proposed framework. The text classifiers were trained and tested using a prelabeled dataset of flu-related and unrelated Twitter postings. The selected text classifier was then used to classify over 8,400,000 tweet documents. The flu-related documents were then mapped on a weekly basis using a mapping module. Finally, the mapped results were passed together with historical Centers for Disease Control and Prevention (CDC) data to a linear regression module for weekly flu rate predictions. Results: The evaluation of flu tweet classification showed that FT, together with the extracted features, achieved accurate results with an F-measure value of 89.9% in addition to its efficiency. Therefore, FT was chosen to be the classification module to work together with the other modules in the proposed framework, including a regression-based estimator, for flu trend predictions. The estimator was evaluated using several regression models. Regression results show that the linear regression-based estimator achieved the highest accuracy results using the measure of Pearson correlation. Thus, the linear regression model was used for the module of weekly flu rate estimation. The prediction results were compared with the available recent data from CDC as the ground truth and showed a strong correlation of 96.29%. Conclusions: The results demonstrated the efficiency and the accuracy of the proposed framework that can be used even for new outbreaks with new signs and symptoms. The classification results demonstrated that the FT-based framework improves the accuracy and the efficiency of flu disease surveillance systems that use unstructured data such as data from SNSs.