Predicting National Suicide Numbers with Social Media Data

Abstract

Suicide is not only an individual phenomenon, but it is also influenced by social and environmental factors. With the high suicide rate and the abundance of social media data in South Korea, we have studied the potential of this new medium for predicting completed suicide at the population level. We tested two social media variables (suicide-related and dysphoria-related weblog entries) along with classical social, economic and meteorological variables as predictors of suicide over 3 years (2008 through 2010). Both social media variables were powerfully associated with suicide frequency. The suicide variable displayed high variability and was reactive to celebrity suicide events, while the dysphoria variable showed longer secular trends, with lower variability. We interpret these as reflections of social affect and social mood, respectively. In the final multivariate model, the two social media variables, especially the dysphoria variable, displaced two classical economic predictors – consumer price index and unemployment rate. The prediction model developed with the 2-year training data set (2008 through 2009) was validated in the data for 2010 and was robust in a sensitivity analysis controlling for celebrity suicide effects. These results indicate that social media data may be of value in national suicide forecasting and prevention.

Manifestation of Depression and Loneliness on Social Networks

“…A number of studies found online social links help maintain one's offline relationships better [2] and increase social capital, for individuals Moving beyond the debate of whether constant use of social networks is a benefit or a harm, recent studies have utilized data from online social networks to predict individual's wellbeing. For instance, population happiness [14], reactions to pandemics [17], unemployment or suicide rate [26,54] can be predicted from sentiments in social media. These studies investigate whether online activities and sentiments indicate the presence of a particular social trend and collective mood of individuals.…”

“…We chose depression because it is the most common mental disorder, affecting more than 350 million people worldwide of all ages [11]. Depression is also the leading cause of death in many developed countries, especially among young adults [54]. Despite the severity of the problem, existing diagnostic tools often face challenges in reaching vulnerable individuals due in part to the perceived stigma of acknowledging depressive symptoms and visiting psychiatrists [46,57].…”

Utilising Social Media for Intervening and Predicting Future Health in Societies

“…The included articles on utilising social media to predict health in populations were published between 2009-2013. The articles described identifying early warning signs with regard to health status in populations [24], predicting national suicide incidents [25], vaccination control [26] and introducing a new framework of infoepidemiology to predict relevant health events in populations [27]. The results suggested that social media may carry the potential of predicting health related issues in populations but the main conclusion is that more knowledge about utilising social media for preventing population health related issues is highly needed.…”

“…The researchers concluded that social media may be of great value in forecasting and preventing suicides on population levels. [25].…”

Suicidology Meets "Big Data"

“…A South Korean study analyzed 153,107,350 social media blog posts during a 3-year time period and found strong statistical associations between frequency of use of the Korean words for suicide and especially dysphoria with national suicide rates. 13 Another group, with personnel from the Dartmouth engineering and medical schools and the US Department of Veterans Affairs (VA) and funding from the Defense Advance Research Project Agency (DARPA), has partnered with Facebook to analyze veterans' social media posts as a means to predict suicide risk.…”