Advanced Daily Prediction Model for National Suicide Numbers with Social Media Data
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Objective Suicide is a significant public health concern worldwide. Social media data have a potential role in identifying high suicide risk individuals and also in predicting suicide rate at the population level. In this study, we report an advanced daily suicide prediction model using social media data combined with economic/meteorological variables along with observed suicide data lagged by 1 week. Methods The social media data were drawn from weblog posts. We examined a total of 10,035 social media keywords for suicide prediction. We made predictions of national suicide numbers 7 days in advance daily for 2 years, based on a daily moving 5-year prediction modeling period. Results Our model predicted the likely range of daily national suicide numbers with 82.9% accuracy. Among the social media variables, words denoting economic issues and mood status showed high predictive strength. Observed number of suicides one week previously, recent celebrity suicide, and day of week followed by stock index, consumer price index, and sunlight duration 7 days before the target date were notable predictors along with the social media variables. Conclusion These results strengthen the case for social media data to supplement classical social/economic/climatic data in forecasting national suicide events.
Abstract
Objective Suicide is a significant public health concern worldwide. Social media data have a potential role in identifying high suicide risk individuals and also in predicting suicide rate at the population level. In this study, we report an advanced daily suicide prediction model using social media data combined with economic/meteorological variables along with observed suicide data lagged by 1 week. Methods The social media data were drawn from weblog posts. We examined a total of 10,035 social media keywords for suicide prediction. We made predictions of national suicide numbers 7 days in advance daily for 2 years, based on a daily moving 5-year prediction modeling period. Results Our model predicted the likely range of daily national suicide numbers with 82.9% accuracy. Among the social media variables, words denoting economic issues and mood status showed high predictive strength. Observed number of suicides one week previously, recent celebrity suicide, and day of week followed by stock index, consumer price index, and sunlight duration 7 days before the target date were notable predictors along with the social media variables. Conclusion These results strengthen the case for social media data to supplement classical social/economic/climatic data in forecasting national suicide events.
참고문헌 (64)
- OECD, "Health at a Glance 2015", ~ (2015)
- 임달오, "Trends in the Leading Causes of Death in Korea, 1983-2012", Journal of Korean Medical Science, 29(12), pp.1597~1603 (2014), 대한의학회
- Saxena S, "World health assembly adopts comprehensive mental health action plan 2013-2020", Lancet, 381, pp.1970~1971 (2013)[DOI]
- Caldwell CB, "Schizophrenics kill themselves too: a review of risk factors for suicide", Schizophr Bull, 16, pp.571~589 (1990)[DOI]
- Fawcett J, "Clinical predictors of suicide in patients with major affective disorders: a controlled prospective study", Am J Psychiatry, 144, pp.35~40 (1987)[DOI]
- Large M, "Systematic review and meta-analysis of the clinical factors associated with the suicide of psychiatric in-patients", Acta Psychiatr Scand, 124, pp.18~29 (2011)[DOI]
- Cash SJ, "Adolescent suicide statements on MySpace", Cyberpsychol Behav Soc Netw, 16, pp.166~174 (2013)[DOI]
- Huang YP, "Hunting suicide notes in web 2.0-preliminary findings", Ninth IEEE International Symposium on Multimedia Workshops, pp.517~521 (2007)
- O'Dea B, "Detecting suicidality on Twitter", Internet Interv, 2, pp.183~188 (2015)[DOI]
- Burnap P, "Machine classification and analysis of suicide-related communication on twitter", Proceedings of the 26th ACM Conference on Hypertext & Social Media, pp.75~84 (2015)
- Jashinsky J, "Tracking suicide risk factors through Twitter in the US", Crisis, 35, pp.51~59 (2014)[DOI]
- Won HH, "Predicting national suicide numbers with social media data", PLoS One, 8, pp.e61809~ (2013)[DOI]
- Yamashita T, "A stepwise AIC method for variable selection in linear regression", Commun Stat-Theor Meth, 36, pp.2395~2403 (2007)[DOI]
- Kim YH, "Association between daily environmental temperature and suicide mortality in Korea (2001-2005)", Psychiatry Res, 186, pp.390~396 (2011)[DOI]
- 박인조, "한국어 감정단어의 목록과 정서 차원 탐색", 한국심리학회지: 사회및성격, 19(1), pp.109~129 (2005), 한국사회및성격심리학회
- 이준웅, "정서 단어 분류를 통한 정서의 구성 차원 및 위계적 범주에 관한 연구", 한국언론학보, 52(1), pp.85~116 (2008), 한국언론학회
- Bollen J, "Twitter mood predicts the stock market", J Comput Sci, 2, pp.1~8 (2011)[DOI]
- Ceccherini-Nelli A, "Economic factors and suicide rates: associations over time in four countries", Soc Psychiatry Psychiatr Epidemiol, 46, pp.975~982 (2011)[DOI]
- Inoue K, "Study of an economic issue as a possible indicator of suicide risk: a discussion of stock prices and suicide", J Forensic Sci, 57, pp.783~785 (2012)[DOI]
- Tsai JF, "Temperature change dominates the suicidal seasonality in Taiwan: a time-series analysis", J Affect Disord, 136, pp.412~418 (2012)[DOI]
- Kim Y, "Association between air pollution and suicide in South Korea: a nationwide study", PLoS One, 10, pp.e0117929~ (2015)[DOI]
- Phillips DP, "The influence of suggestion on suicide: substantive and theoretical implications of the Werther effect", Am Sociol Rev, 39, pp.340~354 (1974)[DOI]
- Maldonado G, "Variation in suicide occurrence by time of day, day of the week, month, and lunar phase", Suicide Life Threat Behav, 21, pp.174~187 (1991)
- Lester D, "Temporal variation in suicide and homicide", Am J Epidemiol, 109, pp.517~520 (1979)[DOI]
- Clifford AC, "A systematic review of suicide prevention interventions targeting indigenous peoples in Australia, United States, Canada and New Zealand", BMC Public Health, 13, pp.463~ (2013)[DOI]
- Robinson J, "A systematic review of school-based interventions aimed at preventing, treating, and responding to suicide- related behavior in young people", Crisis, 34, pp.164~182 (2013)[DOI]
- Szumilas M, "Post-suicide intervention programs: a systematic review", Can J Public Health, 102, pp.18~29 (2011)
- Lapierre S, "A systematic review of elderly suicide prevention programs", Crisis, 32, pp.88~98 (2011)[DOI]
- Mann JJ, "Suicide prevention strategies: a systematic review", JAMA, 294, pp.2064~2074 (2005)[DOI]
- Jobes DA, "The Kurt Cobain suicide crisis: perspectives from research, public health, and the news media", Suicide Life Threat Behav, 26, pp.260~269 (1996)
- Martin G, "Celebrity suicide: did the death of Kurt Cobain influence young suicides in Australia?", Arch Suicide Res, 3, pp.187~198 (1997)
- Gould MS, "Suicide and the media", Ann N Y Acad Sci, 932, pp.200~221 (2001)
- Luxton DD, "Technology-based suicide prevention: current applications and future directions", Telemed J E Health, 17, pp.50~54 (2011)[DOI]
- Krysinska KE, "Telecommunication and suicide prevention: hopes and challenges for the new century", Omega (Westport), 55, pp.237~253 (2007)[DOI]
- Whittaker R, "Mobile phone-based interventions for smoking cessation", Cochrane Database Syst Rev, 11 (2012)
- Harrison V, "Mobile mental health: review of the emerging field and proof of concept study", J Ment Health, 20, pp.509~524 (2011)[DOI]
- Palmier-Claus JE, "Integrating mobile-phone based assessment for psychosis into people's everyday lives and clinical care: a qualitative study", BMC Psychiatry, 13, pp.34~ (2013)[DOI]
- Technological Innovations Enabling Automatic, Context-Sensitive Ecological Momentary Assessment;The Science of Real-Time Data Capture: Self-Reports in Health Research, "Intille SS", 308~337 (2007)
- Luxton DD, "mHealth for Mental Health: Integrating Smartphone Technology in Behavioral Healthcare", Prof Psychol Res Pr, 42, pp.505~512 (2011)[DOI]
- Kelly J, "Intelligent real-time therapy: harnessing the power of machine learning to optimise the delivery of momentary cognitive-behavioural interventions", J Ment Health, 21, pp.404~414 (2012)[DOI]
- Kramer I, "A therapeutic application of the experience sampling method in the treatment of depression: a randomized controlled trial", World Psychiatry, 13, pp.68~77 (2014)[DOI]
- Stuckler D, "The public health effect of economic crises and alternative policy responses in Europe: an empirical analysis", Lancet, 374, pp.315~323 (2009)[DOI]
- Gavrilova NS, "The response of violent mortality to economic crisis in Russia", Popul Res Policy Rev, 19, pp.397~419 (2000)[DOI]
- Chang SS, "Was the economic crisis 1997-1998 responsible for rising suicide rates in East", Southeast Asia? A time-trend analysis for Japan, Hong Kong, South Korea, Taiwan, Singapore and Thailand, 2009, pp.68, 1322~1331
- Jeon SY, "A population-based analysis of increasing rates of suicide mortality in Japan and South Korea, 1985-2010", BMC Public Health, 16, pp.356~ (2016)[DOI]
- Wada K, "Trends in cause specific mortality across occupations in Japanese men of working age during period of economic stagnation, 1980-2005: retrospective cohort study", BMJ, 344, pp.e1191~ (2012)[DOI]
- Economou M, "Increased suicidality amid economic crisis in Greece", Lancet, 378, pp.1459~ (2011)
- Watts J, "Seoul - Suicide rate rises as South Korea's economy falters", Lancet, 352, pp.1365~1365 (1998)
- 박종순, "우리나라에서 경제성장률과 실업률이 자살률에 미치는 영향", 예방의학회지, 36(1), pp.11~91 (2003), 대한예방의학회
- Kwon JW, "A closer look at the increase in suicide rates in South Korea from 1986-2005", BMC Public Health, 9, pp.72~ (2009)[DOI]
- Kim H, "Changes in mortality after the recent economic crisis in South Korea", Ann Epidemiol, 14, pp.442~446 (2004)[DOI]
- Chang SS, "Impact of 2008 global economic crisis on suicide: time trend study in 54 countries", BMJ, 347, pp.f5239~ (2013)[DOI]
- Berk M, "The effect of macroeconomic variables on suicide", Psychol Med, 36, pp.181~189 (2006)
- Zhang X, "Predicting stock market indicators through twitter "I hope it is not as bad as I fear"", Procedia Soc Behav Sci, 26, pp.55~62 (2011)[DOI]
- Platt S, "Unemployment and suicidal behaviour: a review of the literature", Soc Sci Med, 19, pp.93~115 (1984)[DOI]
- Wilson SH, "Unemployment and health: a review", Public Health, 107, pp.153~162 (1993)[DOI]
- Milner A, "Long-term unemployment and suicide: a systematic review and meta-analysis", PLoS One, 8, pp.e51333~ (2013)[DOI]
- Jin RL, "The impact of unemployment on health: a review of the evidence", CMAJ, 153, pp.529~540 (1995)
- Lambert G, "Increased suicide rate in the middle-aged and its association with hours of sunlight", Am J Psychiatry, 160, pp.793~795 (2003)[DOI]
- Page LA, "Relationship between daily suicide counts and temperature in England and Wales", Br J Psychiatry, 191, pp.106~112 (2007)[DOI]
- Bollen J, "Modeling public mood and emotion: Twitter sentiment and socio-economic phenomena", ICWSM, 11, pp.450~453 (2011)
- Woo H, "Public Trauma after the Sewol Ferry Disaster: The Role of Social Media in Understanding the Public Mood", Int J Environ Res Public Health, 12, pp.10974~10983 (2015)[DOI]
- Moreno MA, "Feeling bad on Facebook: depression disclosures by college students on a social networking site", Depress Anxiety, 28, pp.447~455 (2011)[DOI]
- Kumar M, "Detecting changes in suicide content manifested in social media following celebrity suicides", Proceedings of the 26th ACM Conference on Hypertext & Social Media, pp.85~94 (2015)
