随着互联网的发展，越来越多的人在社交网络表达自己的情感，其中包括自杀意愿，这就为自杀预防创造了新机遇。如果自杀风险可以利用微博进行自动识别，就可以为自杀预防工作开辟新方向。本文立足于使用深度学习建立社交媒体自杀识别器，探讨通过社交平台实时评估个体用户自杀可能性。为验证这种算法模型的有效性，对算法所使用的关键词属性进行统计学分析，并与另外两种算法模型的预测结果进行比较。实验结果表明基于深度学习的算法模型可更有效地对微博用户的自杀风险进行预测。
With the development of internet, more and more people express their emotion and feeling in social media, including suicidal ideation. There is a new opportunity for suicide prevention, if people with high suicidal risks can be identified through social media like microblog. In this work we attempt to set up the suicidal ideation recognizer with deep learning model, and address the possibility of suicidal risk assessment in social media. In order to verify the validity of the algorithm model,we also conduct statistical analysis of the key word features, and compare the incorrectly classified instances with other two algorithms. The results indicate that deep learning algorithm works more effectively for suicide risk identification.
[1] 阚双余,郑小方.大学生自杀意念与家庭环境关系[J].中国公共卫生,2013,29(2):167-168.
[2] Yip P S F,Liu K Y,Hu J,et al. Suicide rates in China during a decade of rapid social changes[J]. Social Psychiatry and Psychiatric Epidemiology, 2005, 40(10):792-798.
[3] 艾琳.每年28.7万人死于自杀意味着什么[EB/OL]. 中国网(2007-09-11)[2016-11-15].http://www.china.com.cn/review/txt/2007-09/11/content_8857789.htm.
[4] 中国互联网络信息中心. 2015年中国社交应用用户行为研究报告[R]. 中国互联网络信息中心官网(2016-04)[2016-11-15]. http://www.cnnic.cn/hlwfzyj/hlwxzbg/sqbg/201604/P020160722551429454480.pdf.
[5] Fu K, Cheng Q, Wong P W C, et al. Responses to a self-presented suicide attempt in social media; a social network analysis[J]. Crisis the Journal of Crisis Intervention & Suicide Prevention,2013,34(6):1-7.
[6] Shen Q. Live online suicide raises concerns in China[EB/OL]. 新华网(2014-12-01)[2016-11-15]. http://news.xinhuanet.com/english/china/2014-12/01/c_133826060.htm.
[7] Rudd M D,Berman A L,Jr J T, et al.Warning signs for suicide:theory, research, and clinical applications[J]. Suicide and Life-Threatening Behavior, 2006,36(3):255-262.
[8] Mandrusiak M,Rudd M D,Jr J T,et al. Warning signs for suicide on the internet:a descriptive study[J]. Suicide and Life-Threatening Behavior, 2006,36(3):263-271.
[9] Cheng Q,Chang S S,Yip P S. Opportunities and challenge of online data collection for suicide prevention[J]. Lancet, 2012,379:e53-e54.
[10] Chang S S, Kwok S S, Cheng Q, et al. The association of trends in charcoal-burning suicide with Google search and newspaper reporting in Taiwan:a time series analysis[J]. Social Psychiatry and Psychiatric Epidenmiology, 2015,50(9):1451-1461.
[11] 邸鹏,段利国.一种新型朴素贝叶斯文本分类算法[J]. 数据采集与处理, 2014, 29(1):71-75.
[12] 李琼,陈利.一种改进的支持向量机文本分类方法[J]. 计算机应用, 2014, 34(8):2317-2321.
[13] 钟将,杨思源,孙启干. 基于文本分类的商品评价情感分析[J]. 计算机应用, 2014, 34(8):2317-2321.
[14] 申莹,徐东平,庞俊. 基于概念的中文博客情感极性聚类分析[J]. 计算机系统应用, 2011, 20(8):72-75.
[15] 吴连海,王萍,王磊,等. 心理健康症状对大学生自杀倾向预测模型的构建[J]. 中国健康心理学杂志, 2010, 18(1):99-100.
[16] 蒋怀滨,张斌,李强,等. 消极完美主义对自杀态度预测机制的内隐实验研究[J]. 现代预防医学, 2015, 42(6):1038-1041.
[17] 张训保,黄水平,卓朗,等. 人工神经网络在失去土地农民心理健康调查中的应用[J]. 中华流行病学杂志, 2008, 29(10):1038-1041.
[18] 魏丙刚,胡志刚. 基于BP神经网络的大学生心理健康状况预测与分析[J]. 科技致富向导, 2010(9):78-81.
[19] Li A, Huang X, Hao B, et al. Attitudes towards suicide attempts broadcast on social media:an exploratory study of Chinese microblogs[J]. Peerj, 2015, 3(9):e1209.
