Identification of Imminent Suicide Risk Among Young Adults using Text Messages

論文URL:http://dl.acm.org/citation.cfm?doid=3173574.3173987

論文アブストラクト:Suicide is the second leading cause of death among young adults but the challenges of preventing suicide are significant because the signs often seem invisible. Research has shown that clinicians are not able to reliably predict when someone is at greatest risk. In this paper, we describe the design, collection, and analysis of text messages from individuals with a history of suicidal thoughts and behaviors to build a model to identify periods of suicidality (i.e., suicidal ideation and non-fatal suicide attempts). By reconstructing the timeline of recent suicidal behaviors through a retrospective clinical interview, this study utilizes a prospective research design to understand if text communications can predict periods of suicidality versus depression. Identifying subtle clues in communication indicating when someone is at heightened risk of a suicide attempt may allow for more effective prevention of suicide.

日本語のまとめ:

自殺未遂歴がある個人のSNSのテキストデータを収集・分析し,うつ状態と自殺の期間が予測できることを明らかにした.特徴量指標としてTF-IDFとLIWCを使い,SVMとDNNを使って分類モデルを構築した.TF-IDFとDNNの組み合わせがベストであった.

(126文字)

発表スライド: