National health surveys are routinely conducted to provide value data about a country's health status and the health services being consumed by the population. This information is used for surveillance, research, and the planning of healthcare services at local and national levels. Although these national health surveys are viewed as important resources for public and population health, there is limited information as to the type of research being conducted with these surveys. This study investigates, through the use of automated text data mining, an approach to identify and collate the type of academic literature being published using national health surveys.
Keywords: Text data mining; algorithm; epidemiology; literature review; national health survey.