ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Uncovering the heterogeneous effects of depression on suicide risk conditioned by linguistic features: A double machine learning approach

Li, Sijia; Pan, Wei*; Yip, Paul Siu Fai*; Wang, Jing; Zhou, Wenwei; Zhu, Tingshao中国科学院研究生院; 中国科学院
Computers in Human Behavior2024-3DOI: 10.1016/j.chb.2023.108080
6阅读
引用收藏
分享

摘要

Depression has been identified as a risk factor for suicide, yet limited evidence has elucidated the underlying pathways linking depression to subsequent suicide risk. Therefore, we aimed to examine the psychological mechanisms that connect depression to suicide risk via linguistic characteristics on Weibo. We sampled 487,251 posts from 3196 users who belong to the depression super-topic community (DSTC) on Sina Weibo as the depression group, and 357,939 posts from 5167 active users as the control group. We employed the double machine learning method (DML) to estimate the impact of depression on suicide risk, and interpreted the pathways from depression to suicide risk using SHapley Additive exPlanations (SHAP) values and tree in-terpreters. The results indicated an 18% higher likelihood of suicide risk in the depression group compared to people without depression. The SHAP values further revealed that Exclusive (M = 0.029) was the most critical linguistic feature. Meanwhile, the three-depth tree interpreter illustrated that the high suicide risk subgroup of the depression group (N = 1196, CATE = 0.32 +/- 0.04, 95%CI [0.20, 0.43]) was predicted by higher usage of Exclusive (>0.59) and Health (>-0.10). DML revealed pathways linking depression to suicide risk. The visualized tree interpreter showed cognitive complexity and physical distress might be positively associated with suicide risk in depressed populations. These findings have invigorated further investigation to elucidate the relationship between depression and suicide risk. Understanding the underlying mechanisms serves as a basis for future research on suicide prevention and treatment for individuals with depression.

学科与关键词

关键词
DepressionSuicide riskLinguistic featuresDouble machine learningWeibo
相关
加载中…
  • Anticipating Suicide Will Be Hard, But This Is Progress
    Chekroud, Adam M.*American Journal of Psychiatry, 2018, 175(10): 921-922.被引 1
  • The performance of machine learning models in predicting suicidal ideation, attempts, and deaths: A meta-analysis and systematic review
    Kusuma, Karen*; Larsen, Mark; Quiroz, Juan C.; Gillies, Malcolm; Burnett, Alexander; Qian, Jiahui; Torok, MichelleJournal of Psychiatric Research, 2022, 155: 579-588.被引 21
  • Creating a Chinese suicide dictionary for identifying suicide risk on social media
    Lv Meizhen; Li Ang*; Liu Tianli; Zhu TingshaoPeerJ, 2015, 3: e1455.被引 29
查看全部 →

发表信息

论文状态
公开发表
期刊
Computers in Human Behavior
发表日期
2024-03
卷期
第 152 卷
页码
108080
DOI
10.1016/j.chb.2023.108080
语言
ENGLISH
成果收录
SSCI
资助标注
Fundamental Research Funds for the Central Universities [CCNU21XJ021]; Knowledge Innovation Program of Wuhan-Shuguang Project [2022020801020288]; Research Program Funds of the Collaborative Innovation Center of Assessment toward Basic Education Quality [2022-04-030-BZPK01]; Major Program of the National Social Science Foundation of China [22 ZD187]

作者

  • L

    Li, Sijia (第一作者)

  • P

    Pan, Wei (通讯)

    univ hong kong · cent china normal univ

查看全部 6 位作者收起作者
  • Y

    Yip, Paul Siu Fai (通讯)

    univ hong kong

  • W

    Wang, Jing

    univ hong kong · cent china normal univ

  • Z

    Zhou, Wenwei

    univ hong kong · cent china normal univ

  • Z

    Zhu, Tingshao

    chinese acad sci · univ chinese acad sci · univ hong kong

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417