Song Juyoung, Song Tae Min, Seo Dong-Chul, Jin Jae Hyun
Department of Administration of Justice, Pennsylvania State University, Schuylkill Haven, Pennsylvania.
Statistics and Information Department, Korea Institute for Health and Social Affairs, Sejong City, South Korea.
J Adolesc Health. 2016 Dec;59(6):668-673. doi: 10.1016/j.jadohealth.2016.07.025. Epub 2016 Sep 29.
To investigate online search activity of suicide-related words in South Korean adolescents through data mining of social media Web sites as the suicide rate in South Korea is one of the highest in the world.
Out of more than 2.35 billion posts for 2 years from January 1, 2011 to December 31, 2012 on 163 social media Web sites in South Korea, 99,693 suicide-related documents were retrieved by Crawler and analyzed using text mining and opinion mining. These data were further combined with monthly employment rate, monthly rental prices index, monthly youth suicide rate, and monthly number of reported bully victims to fit multilevel models as well as structural equation models.
The link from grade pressure to suicide risk showed the largest standardized path coefficient (beta = .357, p < .001) in structural models and a significant random effect (p < .01) in multilevel models. Depression was a partial mediator between suicide risk and grade pressure, low body image, victims of bullying, and concerns about disease. The largest total effect was observed in the grade pressure to depression to suicide risk. The multilevel models indicate about 27% of the variance in the daily suicide-related word search activity is explained by month-to-month variations. A lower employment rate, a higher rental prices index, and more bullying were associated with an increased suicide-related word search activity.
Academic pressure appears to be the biggest contributor to Korean adolescents' suicide risk. Real-time suicide-related word search activity monitoring and response system needs to be developed.
鉴于韩国的自杀率位居世界前列，通过对社交媒体网站进行数据挖掘，调查韩国青少年与自杀相关词汇的在线搜索活动。
在2011年1月1日至2012年12月31日这两年间韩国163个社交媒体网站上超过23.5亿条帖子中，通过爬虫程序检索到99,693份与自杀相关的文档，并使用文本挖掘和观点挖掘进行分析。这些数据进一步与月就业率、月租金价格指数、月青少年自杀率以及每月报告的欺凌受害者数量相结合，以拟合多层次模型和结构方程模型。
在结构模型中，从学业压力到自杀风险的链接显示出最大的标准化路径系数（β = 0.357，p < 0.001），在多层次模型中具有显著的随机效应（p < 0.01）。抑郁是自杀风险与学业压力、低身体意象、欺凌受害者以及对疾病的担忧之间的部分中介变量。在学业压力到抑郁再到自杀风险的过程中观察到最大的总效应。多层次模型表明，与自杀相关词汇的每日搜索活动中约27%的方差可由逐月变化来解释。较低的就业率、较高的租金价格指数以及更多的欺凌行为与与自杀相关词汇的搜索活动增加有关。
学业压力似乎是韩国青少年自杀风险的最大促成因素。需要开发与自杀相关词汇搜索活动的实时监测和应对系统。
