Emotional Impact of Suicide on Active Witnesses: Predicting with Machine Learning

Abstract

Predicting the impact of suicide on incidental witnesses at an early stage helps to avert the possible side effect. When suicide is committed in public, incidental observers are left to grapple with it. In many cases, these incidental witnesses tend to experience the emotional side effect with time. In this study, we employed a Machine learning algorithms to predict the impact of suicide and suicidal attempt on incidental witnesses. This prediction was based on the accounts of suicide given by selected participants who have witnessed the act. The accounts, which was pre-processed into a corpus, were manually annotated with predefined emotion categories. While sadness emerged as the most salient emotional impact on the witnesses, fear was found as the lowest of the emotional impact on the witnesses. However, the machine learning prediction yielded highest in predicting depression with insignificant variations in the other emotional categories. This nonetheless shows that people who have witnessed suicide or suicidal attempts are inherently affected by some form of emotions that may require urgent attention to alleviate. By evaluating the performance of the Machine learning algorithms, the Support Vector Machine was superior, in terms its prediction, then the Multinomial Naïve Bayes algorithm. The outcome of the study contributes to the pool of research that sought to advocate the use of Machine Learning for predicting social phenomenon.

Identifying Witnessed Suicides in National Violent Death Reporting System Narratives

“…While witnessed suicides are relatively rare in comparison to non-witnessed suicides, their impact on those who witness the death can be powerful and enduring [4][5][6]15,32]. In the current study, we developed criteria and a reliable coding scheme to classify suicides for being witnessed or not using information available in the law enforcement and medical/coroner narratives contained within the 2003-2017 NVDRS.…”

“…Although the majority of suicides occur in the decedent's home while alone and in private areas (e.g., bedrooms, closets, and bathrooms), increasingly a subset of suicides take place within view of others, such as using a firearm in the presence of other people, jumping in front of trains or subways, or leaping from bridges [3,4]. This has been referred to as witnessed suicide [5,6]. Studies have found that 4-10% of suicides are witnessed [5][6][7][8][9].…”

“…This has been referred to as witnessed suicide [5,6]. Studies have found that 4-10% of suicides are witnessed [5][6][7][8][9]. Although relatively rare, their impact on witnesses can be profound [10][11][12][13].…”

“…Although relatively rare, their impact on witnesses can be profound [10][11][12][13]. Studies documenting the mental health state of "survivor-victims," or those who have witnessed a suicide, have observed that these individuals commonly experience strong feelings of shame, guilt, and anger [5,6,14]. One study found that survivor-victims "are obsessed with thoughts of death, seeking reasons, casting blame, and often punishing themselves" [15].…”