Year: 2008 Source: BioNLP 2008: Current Trends in Biomedical Natural Language Processing, (2008: Columbus, Ohio), p.96-97 SIEC No: 20090926

The authors hypothesized that machine-learning algorithms can classify genuine & simulated suicide notes as well as mental health professionals. 66 notes were classified. The mental health professionals were accurate 71% of the time; using the sequential minimization optimization algorithm, the machine-learning algorithms were accurate 78% of the time. There were no significant differences between the classifiers. It is concluded the results are an important first step in developing an evidence-based suicide predictor for emergency department use. (5 refs.)