Towards a Predictive Model of Suicide Using Internet Search Data

• In Event: 3129 - Section on Medical Sociology Refereed Roundtables (1 hour)
  In Refereed Roundtable 60min: Table 13. Suicide and Suicidality

Abstract

Research on suicide has been abundant in the last few decades within the fields of public health, epidemiology, psychiatry, and biomedicine. Lately, advances in suicidology and its underlying causes have been elusive in the field of sociology. This study aims to implement a big data approach to the study of suicide with the ultimate goal of developing a better predictive model of the suicide rate. Additionally, it aims to establish internet search term data as a legitimate, practical, and cost-effective methodological approach to studying large-scale sociological phenomena. This study examines the relationship between suicidal, depressive, and gun-related Google search terms and their association with the 50-state suicide rate from 2006 to 2016 using a fixed effects model. Suicidal, depressive, and gun-related search terms are found to be significantly associated with the suicide rate over the 11 year period. As fields such as public health, epidemiology, and psychiatry effectively incorporate internet and big data-driven methodologies, it is imperative that sociologists carefully consider its capabilities given its increasing utilization and promising potential.

Author

• Christian Guerra, University of California Riverside