BACKGROUND
Health-related social media data are increasingly being used in disease surveillance studies. In particular, surveillance of infectious diseases such as influenza has demonstrated high correlations between the number of social media posts mentioning the disease and the number of patients who went to the hospital and were diagnosed with the disease. However, the prevalence of some diseases, such as allergic rhinitis, cannot be estimated based on the number of patients alone. Specifically, patients with allergic rhinitis self-medicate by taking over-the-counter (OTC) medications without going to the hospital. Although allergic rhinitis is not a life-threatening disease, it is a major social problem because it reduces patients’ quality of life, making it essential to understand its prevalence and the motives for self-medication behavior.
OBJECTIVE
To help understand the prevalence of allergic rhinitis and the motives for self-care treatment using social media data, this study investigated the relationship between the number of social media posts mentioning the main symptoms of allergic rhinitis and the sales volume of OTC rhinitis medications in Japan.
METHODS
We collected tweets over four years from 2017 to 2020 that included keywords corresponding to the main nasal symptoms of allergic rhinitis: “sneezing,” “runny nose,” and “stuffy nose.” We also obtained the sales volume of OTC drugs, including oral medications and nasal sprays, for the same period. We then calculated the Pearson correlation coefficient between time series data on the number of tweets per week and time series data on the sales volume of OTC drugs per week.
RESULTS
The results showed a much higher correlation (0.8432) between the time series data on the number of tweets mentioning “stuffy nose” and the time series data on the sales volume of nasal sprays than for the other two symptoms. There was also a high correlation (0.9317) between the seasonal components of these time series data.
CONCLUSIONS
We investigated the relationships between social media data and behavioral patterns, such as OTC drug sales volume. Exploring these relationships would be useful as a marketing indicator to predict sales volume using social media data. In future, in-depth investigations are required to cover other diseases and countries. We investigated the relationships between social media data and behavioral patterns, such as OTC drug sales volume. Exploring these relationships would be useful as a marketing indicator to predict sales volume using social media data. In future, in-depth investigations are required to cover other diseases and countries.
A Predictive Meta Model for Forecasting Stock Price using Time Series Data
