Visualizing Health Tweets over Regions and Timestamps

Abstract

Social media has become one of the major data sources for social studies through users’ expressions, such as significant moments in their daily life or their feelings and perceptions toward specific discussion topics. In health care, social media is thoroughly used to study people’s discourse on ailments and derive insights into the impact of ailments on patients’ quality of life. Recently, there has been an increasing interest in applying machine learning algorithms to enhance the prediction of ailments through users’ social media data. In this study, nearly 800 million posts were retrieved from Twitter through preprocessing and running the time-aware ailment topic aspect model (T-ATAM) to predict diseases, symptoms, and remedies for two chronic conditions, namely sleep apnea and chronic liver diseases. The study was conducted on English tweets emitted during 2018, most of which were from European countries and the United States. The data were processed using T-ATAM by regions, timestamps, and treatment, namely continuous positive airway pressure (CPAP), to see the differences in the distributions of top diseases along with the top symptoms and remedies in different regions; timestamps; as well as before, during, and after CPAP was introduced. Based on approximately 331,000 tweets related to liver diseases and 1 million tweets on sleep apnea, various visualizations of statistics are displayed, including world maps, word clouds, and histograms. Results of this study indicate that depression and drinking are the leading symptoms of liver diseases; meanwhile, lack of nighttime sleep and overworking are considered the main factors of sleep apnea.

Keywords

• social media
• topic models
• visualization
• health data
• data analysis