Identifying Vulnerable Populations through a Combination of Big Data, Demographic and Qualitative Techniques

Despite long-standing interest in the health of the most vulnerable segments of the population, assessing the situation of hidden and hard to reach minority populations is impeded by a seeming lack of data. This perception persists, as social scientists have not fully tapped into our ongoing ‘big data revolution’: We are surrounded by individually generated digital data deposits; invisible to us, perpetually documenting our location, health, socioeconomic status, thoughts and habits. Yet, we do not routinely use this wealth of historic and live data available to us to address enduring gaps in social scientific research. In this article, I use a novel combination of research methods, relying on qualitative, machine learning and demographic techniques. I test my method through a case study of a high-profile, yet also highly stigmatized and vulnerable refugee population - the Hungarian Roma refugees of Canada. My work is guided by the following questions: (1) What are some shortfalls in the existing, commonly deployed methods of counting hard to reach populations such as the Roma? (2) How does my holistic methodological intervention differ when it comes to tangible differences in the population portraits uncovered? (3) How can researchers apply my proposed methodological intervention to other hidden and hard to reach populations? I illustrate that by using comprehensive sampling, data, and statistical techniques, in contrast to the existing crude population portraits of the Roma, we can arrive at a much more nuanced and ethically responsible representation of this population. My contribution extends beyond the descriptive, as I also examine and contrast the socio-demographic realities facing both the Hungarian and the Hungarian Roma populations of Canada. In an effort to aid the design of appropriate interventions, I highlight some ways in which the socioeconomic constraints the Roma contend with shape their survival strategies in their new homeland.