Even machines are better than mental health professionals at spotting fake suicide notes, is one possible interpretation of a study by researchers at Cincinnati Children’s Hospital Medical Center, and Windsor, Canada. Other interpretations are possible, too. The study is:
“Suicide Note Classification Using Natural Language Processing: A Content Analysis,” John Pestian [pictured here], Henry Nasrallah, Pawel Matykiewicz, Aurora Bennett and Antoon Leenaars, Biomedical Informatics Insights, vol. 3, 2010, pp. 19-28. (Thanks to investigator Blaise Li for bringing this to our attention.) The authors, at , explain:
“The data used are comprised of suicide notes from 33 suicide completers and matched to 33 elicited notes from healthy control group members. Eleven mental health professionals and 31 psychiatric trainees were asked to decide if a note was genuine or elicited. Their decisions were compared to nine different machine-learning algorithms. The results indicate that trainees accurately classified notes 49% of the time, mental health professionals accurately classified notes 63% of the time, and the best machine learning algorithm accurately classified the notes 78% of the time. This is an important step in developing an evidence-based predictor of repeated suicide attempts because it shows that natural language processing can aid in distinguishing between classes of suicidal notes.”