Potential use of text classification tools as signatures of suicidal behavior: A proof-of-concept study using Virginia Woolf’s personal writings

• Published in: PloS one Vol. 13; no. 10; p. e0204820
• Main Authors: de Ávila Berni, Gabriela, Rabelo-da-Ponte, Francisco Diego, Librenza-Garcia, Diego, V. Boeira, Manuela, Kauer-Sant’Anna, Márcia, Cavalcante Passos, Ives, Kapczinski, Flávio
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 24.10.2018; Public Library of Science (PLoS)
• Subjects: Algorithms; Analysis; Artificial intelligence; Bayesian analysis; Behavior disorders; Biology and Life Sciences; Bipolar disorder; Classification; Computer and Information Sciences; Data processing; Diaries; Digital media; Electronic health records; Emotional disorders; Famous Persons; Feasibility studies; Female; Humans; Identification methods; Informatics; Laboratories; Learning algorithms; Machine Learning; Mathematical models; Medicine and Health Sciences; Mental disorders; Model accuracy; Neurosciences; Physical Sciences; Proof of Concept Study; Psychiatry; Psychoanalytic Interpretation; Research and Analysis Methods; Schizophrenia; Self Concept; Social networks; Social Sciences; Suicidal behavior; Suicidal Ideation; Suicide; Suicides & suicide attempts; Woolf, Virginia (1882-1941); Writing; United States; Brazil; Canada

The present study analyzes the feasibility of text classification to predict individual suicidal behavior. Entries from Virginia Woolf's diaries and letters were used to assess whether a text classification algorithm could identify written patterns associated with suicide. This is a text classi...