Text analysis of Suicidal Thoughts and Behaviors in Adolescents and Young Adults

Julianne Kimmel and Jia-Wen Guo, PhD, RN, College of Nursing, University of Utah, 201 Presidents' Cir, Salt Lake City, UT 84112

Suicide is a major public health concern for adolescent and young adults (AYAs). According to Three-step Theory of suicide, strong suicidal ideation progresses to action. The younger generation use social media as their primary means of communication and they may use the social media platforms to express their suicidal thoughts and intentions; therefore, social media data have potential to support early detection of suicide ideation and intention in AYAs. Understanding what theme topics and languages used by AYAs to describe suicide-related thoughts and behaviors is an essential step for detecting suicide ideation and prevention on social media. However, there is a lack of this knowledge. The purpose of this study is to bridge this knowledge gap by analyzing texts collected from 263 AYAs with ages between 12 and 25, who were asked to provide descriptions of how they and their peers expressed their experiences of self-harm, suicidal thinking and attempts. A total of 9647 words from 687 statements were analyzed by using KH Coder, a textual analysis software. Five themes were identified: “physical marks” (e.g., scar), “description of self-harm or suicide” (e.g., suicidal thinking), “methods” (e.g., overdose), “outcomes” (e.g., end life), and “motivation” (e.g., helpless). Regarding the languages use, the most frequently used words in texts were cut (126 uses) and kill (110 uses). Several generational slang words, including social media terms, were found to imply killing oneself such as KMS or KYS (i.e., kill myself or kill yourself), yeet, and kermit sewage slide. In summary, this study discovered that a “motivation” theme, a precursor of suicide, was mentioned and can be utilized for the early detection of suicide-related actions. Generational slang words including social media terms were found in this study can be utilized to identify individual’s suicidal intention from the social media sources or other textual data.

Additional Abstract Information

Presenter: Julianne Kimmel

Institution: University of Utah

Type: Poster

Subject: Nursing & Public Health

Status: Approved

Time and Location

Session: Poster 9
Date/Time: Wed 12:00pm-1:00pm
Session Number: 6079