A Deep Learning Approach for Dengue Tweet Classification

Dengue is one amongst the foremost widespread vector borne diseases best-known these days. According to National Institute of Allergy and Infectious Disease (NIAID), Dengue fever has been identified as a threat to public health [1]. More than 33% of the total world population is under risk, together with several cities of Asian nation. In recent years, the utilization of social media (from tweets to Facebook posts) in healthcare has risen tremendously because social media is the platform to point out growing want of patients who are suffering, to attach with one another. Tweets are too short to supply sufficient word occurrences for traditional classification methods to give results reliably. Also, natural language is extremely complicated creating classification of health connected problems difficult. The performance of most conventional classification systems depends on acceptable information illustration and tremendous effort in feature engineering. Deep Learning is new space of machine learning that do automatic feature extraction. In this study, Convolutional Neural Network (CNN) has been used to classify dengue related tweets extracted from twitter into seven multiple classes such as ‘Infected’, ‘Informative’, ‘Vaccination’, ‘News', ‘Awareness', ‘Concern’ and ‘Others'. From Experimental results, Deep Learning algorithm shows increased accuracy when put next to Machine Learning algorithms such as Support Vector Machine (SVM), Naïve Bayes(NB) and Decision Tree Classifier(DT).