Identification of suicide risk through social networks

Social networks such as Twitter may become helpful tools to detect mental health status of people.

Social networks have transformed the way we see the world and the way we communicate. A multitude of users expresses their thoughts and emotions at a same moment and can make relationships with each other in a simpler and faster way.

Recent studies have highlighted the potential of virtual social networks to detect how feel people and their mental statuses, by means of machine learning algorithms. Several techniques based on those algorithms may effectively differentiate people at risk of suicide.

A study conducted in Spain, led by Ms Claudia Garcia-Martinez, from the University of Zaragoza, analyzed the risk of engagement in suicide behavior among Twitter users who posted in Spanish. Relevant posts were identified thanks to Affective Norms for English Words (Spanish adaptation) and Linguistic Inquiry and Word Count software to assess positive and negative emotions. Each tweet was randomly assigned to 3 psychologists with expertise in suicidal behavior who analyzed suicide risk in real time, in addition to different related variables, such as emotional content, personality traits, feelings of defeat, and social support.

216 tweets out of the pool of analyzed tweets were considered relevant for the analysis of suicidal behavior. Those tweets mainly conveyed sadness and hopelessness. Correlations were also observed between the severity of suicide risk at the time of posting the tweet and sadness, general risk and intensity of suicidal thoughts. Likewise, greater severity was observed in people who expressed feelings of defeat, rejection, helplessness, lack of social support and recurrent thoughts.

The findings of this study reveal that virtual social networks may be used to help identify at-risk individuals, as well as to provide a list of important factors to consider for suicide risk assessment and monitoring.

Reference to original paper: García-Martínez C, Oliván-Blázquez B, Fabra J, Martínez-Martínez AB, Pérez-Yus MC, López-Del-Hoyo Y. Exploring the Risk of Suicide in Real Time on Spanish Twitter: Observational Study. JMIR Public Health Surveill. 2022 May 17;8(5):e31800. https://publichealth.jmir.org/2022/5/e31800