Can acute suicidality be predicted by Instagram data? Results from qualitative and quantitative language analyses

Social media has become increasingly important for communication among young people. It is also often used to communicate suicidal ideation. To investigate the link between acute suicidality and language use as well as activity on Instagram. A total of 52 participants, aged on average around 16 years, who had posted pictures of non-suicidal self-injury on Instagram, and reported a lifetime history of suicidal ideation, were interviewed using Instagram messenger. Of those participants, 45.5% reported suicidal ideation on the day of the interview (acute suicidal ideation). Quantitative text analysis of language use in the interviews and directly on Instagram (in picture captions) was performed using the Linguistic Inquiry and Word Count software. Language markers in the interviews and in picture captions, as well as activity on Instagram were added to regression analyses, in order to investigate predictors for current suicidal ideation. Most participants (80%) had come across expressions of active suicidal thoughts on Instagram and 25% had expressed active suicidal thoughts themselves.