Building a Classification Model for Diseases Discovery from Tweets

Abstract

Innovation in technology enables people to communicate, share information and look for their needs by just sitting in rooms and going through some clicks. While social media has played a very important role in connecting people worldwide, its potential has stretched beyond the innovative idea of connecting people through their social networks.While many thought there was no meeting point for the healthcare sector and social media, it was a surprise when research and innovations have shown that social media could lay a very significant role in the health care sector. Research has been done in building a classification model that could use social media (Twitter) as the data source for prediction diseases name based on text mining of tweets. The aim of this research is to building a classification model at the individual level using a sample of tweets that have been collected from the Twitter API using the query including keywords: “blood pressure, bone, cancer, diabetes, kidney, lung cancer and migraines” based on text mining of tweets. This thesis investigates the feasibility of monitor and classifying diseases via machine learning techniques, Support Vector Machine and Random Forest classifiers.The results of the classification models showed high accuracy rate in the prediction of diseases name.