Supervised Learning for Suicidal Ideation Detection in Online User Content

<table class="table-group" id="tab1"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left">Categories</td><td class="align_left">Rules</td><td class="align_center">Examples</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left" rowspan="2">Suicide text</td><td class="align_left">(i) Expressing suicidal thoughts</td><td class="align_center"><i>I want to end my life tonight.</i></td></tr><tr><td class="align_left">(ii) Including potential suicidal actions</td><td class="align_center"><i>Yesterday, I tried to cut my wrist, but failed.</i></td></tr><tr><td class="align_center" colspan="3"><hr/></td></tr><tr><td class="align_left" rowspan="3">Nonsuicide text</td><td class="align_left">(i) Formally discussing suicide</td><td class="align_center"><i>The global suicide rate is increasing.</i></td></tr><tr><td class="align_left">(ii) Referring to other’s suicide</td><td class="align_center"><i>I am so sad to hear that Robin Williams ended his life.</i></td></tr><tr><td class="align_left">(iii) Not relevant to suicide</td><td class="align_center"><i>I love this TV show and watch every week.</i></td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Annotation rules and examples of social texts.</div>

Complexity

tab1

Table 1

Table 1: Supervised Learning for Suicidal Ideation Detection in Online User Content 