PSYCH OpenIR  > 社会与工程心理学研究室
基于社交媒体的自杀自动识别与 心理危机 主动 干
Alternative TitleAutomatic Suicide Identification and Proactive Crisis Management Based on Social Media
刘兴云
Subtype博士
Thesis Advisor朱廷劭
2020-06
Degree Grantor中国科学院心理研究所
Place of Conferral中国科学院心理研究所
Degree Name理学博士
Degree Discipline应用心理学
Keyword自杀 社交媒体 机器学习 自动识别 主动干预
Abstract

自杀是一个巨大的公共健康挑战。中国每年有二百万人尝试自杀。现有的自杀预防项目要求自杀者主动寻求帮助,但很多有自杀想法的人寻求帮助的动机较低。互联网已经成为我们生活中不可分割的一部分。然而,很少有研究调查自杀相关的社交媒体使用行为的影响。我们提出了一种基于社交媒体的新方法——网上主动自杀预防(Proactive Suicide Prevention Online, PSPO),将主动识别自杀者与主动的危机管理相结合。首先,采用问卷调查法确定与自杀风险相关的社交媒体使用行为,然后专家分析参与调查的用户对自杀遗言的评论,为自杀想法及自杀行为识别的机器学习模型提供训练样本,经过训练筛选出预测性能最优的模型来自动识别涉及自杀想法和行为的帖子。在此基础上,编辑形成了一条危机管理信息,它包括涉及自杀相关问题、抑郁、寻求帮助行为、可接受性以及社交媒体使用习惯的问卷等内容,通过微博私信发送给被模型识别为有自杀风险的用户。对于那些回复信息的人,训练有素的心理学志愿者会为他们提供定制的危机管理帮助。结果表明,自杀未遂者具有较高的自杀意念水平和更多与自杀相关的社交媒体使用行为。自杀意念通过关注自杀信息,评论或转发自杀信息和在网上谈论自杀这一链式中介模型影响自杀企图。通过分析2017年4月的27007条评论,其中2786例(10.32%)被归类为包含自杀思想和行为,结果显示该识别模型性能良好,识别精度高(0.88),召回率高(0.85),F测量值高(0.85),准确度高(0.86)。2017年7月3日至2018年7月3日,共向12486名社交媒体用户发送24727条微博私信,其中有5542(44.39%)人有所回应。超过三分之一的被联系用户完成了包含在私信中的问卷调查。在1403份有效回答中,1259名参与者(89.73%)报告有自杀意念,但超过一半(51.67%)报告他们没有寻求帮助。患者健康问卷(PHQ-9)平均得分为17.40(SD=5.98)。超过三分之二的参与者(968人,69.00%)认为PSPO这一方法是可以接受的。此外,2321名用户回复了这条私信。通过对比他们在与志愿者接触前一个月和接触后一个月在微博上不同词语的使用频率,发现死亡导向词的使用频率显著下降,而未来导向词的使用频率显著增加。基于自杀相关的社交媒体使用行为建立的PSPO模型适用于确定有自杀风险的人群。再结合主动的危机管理,它可能是对现有自杀预防方案的有益补充。因为它可能增加有自杀想法但寻求帮助的动机较低的人获得自杀干预信息的机会。

Other Abstract

Suicide is a great public health challenge. Two million people attempt suicide every year in China. Existing suicide prevention programs require the help-seeking initiative of suicidal individuals, but many of them have low motivation to seek help. The Internet has become an inseparable part of our life. However, little research has investigated the impact of suicide-related social media use behaviors and administrated proactive and targeted prevention based on them. To solve this problem and test the feasibility and acceptability of Proactive Suicide Prevention Online (PSPO), a new approach based on social media that combines proactive identification of suicidal individuals with specialized crisis management, firstly, we conducted a survey to identify suicide-related social media use behaviors that related to suicidal risk. Based on this study, we located a microblog group online. Next, those comments on a suicide note were analyzed by experts to provide a training set for machine learning models for suicide identification. Then the best-performing model was used to automatically identify posts that suggested suicidal thoughts and behaviors. Next, a microblog direct message containing crisis management information, including measures covering suicide-related issues, depression, help-seeking behavior, an acceptability test and social media usage habit test were sent to users who had been identified by the model as at risk of suicide. For those who replied to the message, trained counselors provided customized crisis management. Results showed that suicidal attempters showed significant higher level of suicidal ideation and more suicide-related social media use behaviours. Suicidal ideation affected suicidal attempt through the mediational chains of attended to suicidal information, commented on / reposted suicidal information or talked-about suicide online. Moreover, a total of 27,007 comments made in April 2017 were analyzed. Among these, 2,786 (10.32%) were classified as indicating suicidal thoughts and behaviors. The performance of the detection model was good, with high precision (0.88), recall (0.85), F-measure (0.85), and accuracy (0.86). Between July 3, 2017 and July 3, 2018, we totally sent out 24,727 direct messages to 12,486 social media users, and 5,542 (44.39%) responded. Over one third of the users who were contacted completed questionnaires included in the direct message. Out of the 1,403 valid responses, 1,259 participants (89.73%) reported suicidal ideation, but more than half (51.67%) reported that they had not sought help. The Patient Health Questionnaire- 9 (PHQ-9) mean score was 17.40 (SD = 5.98). More than two thirds of the participants (968, 69.00%) thought the PSPO approach was acceptable. In addition, a total of 2,321 users replied to the direct message. In Comparison of the frequency of word usage in their microblog posts one-month before and one-month after the consultation, we found that the frequency of death-oriented words significantly declined while the frequency of future-oriented words significantly increased. The PSPO model which is based on well-established suicide-related social media use behaviors is suitable for identifying populations at-risk of suicide. Followed-up with proactive crisis management, it may be a useful supplement to existing prevention programs as it may increase the accessibility of anti-suicide information to people with suicidal thoughts and behaviors but low motivation to seek help.

Pages97
Language中文
Document Type学位论文
Identifierhttp://ir.psych.ac.cn/handle/311026/31924
Collection社会与工程心理学研究室
Recommended Citation
GB/T 7714
刘兴云. 基于社交媒体的自杀自动识别与 心理危机 主动 干[D]. 中国科学院心理研究所. 中国科学院心理研究所,2020.
Files in This Item:
File Name/Size DocType Version Access License
刘兴云-博士学位论文.pdf(2991KB)学位论文 限制开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[刘兴云]'s Articles
Baidu academic
Similar articles in Baidu academic
[刘兴云]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[刘兴云]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.