Tracking Suicide Risk Factors Through Twitter in the US
Abstract
Background: Suicide is a leading cause of death in the United States. Social media such as Twitter is an emerging surveillance tool that may assist researchers in tracking suicide risk factors in real time. Aims: To identify suicide-related risk factors through Twitter conversations by matching on geographic suicide rates from vital statistics data. Method: At-risk tweets were filtered from the Twitter stream using keywords and phrases created from suicide risk factors. Tweets were grouped by state and departures from expectation were calculated. The values for suicide tweeters were compared against national data of actual suicide rates from the Centers for Disease Control and Prevention. Results: A total of 1,659,274 tweets were analyzed over a 3-month period with 37,717 identified as at-risk for suicide. Midwestern and western states had a higher proportion of suicide-related tweeters than expected, while the reverse was true for southern and eastern states. A strong correlation was observed between state Twitter-derived data and actual state age-adjusted suicide data. Conclusion: Twitter may be a viable tool for real-time monitoring of suicide risk factors on a large scale. This study demonstrates that individuals who are at risk for suicide may be detected through social media.
References
2012a). Risk factors for suicide. Retrieved from www.afsp.org/index.cfm?page_id=05147440-E24E-E376-BDF4BF8BA6444E76
. (2012b). Warning signs of suicide. Retrieved from www.afsp.org/index.cfm?fuseaction=home.viewPage&page_id=0519EC1A-D73A-8D90-7D2E9E2456182D66
. (2006). Odeo releases twttr. Retrieved from techcrunch.com/2006/07/15/is-twttr-interesting/
(2010). Predicting the future with social media. Retrieved from arxiv.org/abs/1003.5699
(2012). Twitter now seeing 400 million tweets per day, increased mobile ad revenue, says CEO. Retrieved from www.mediabistro.com/alltwitter/twitter-400-million-tweets_b23744
(2011). Harnessing context sensing to develop a mobile intervention for depression. Journal of Medical Internet Research, 13(3), e55
(2012). ”Right Time, Right Place Health” health communication on Twitter: Value and accuracy of location information. Journal of Medical Internet Research 14(6), e156.
(2013). WISQARS: Years of Potential Life Lost (YPLL) Reports, 1999–2010. Retrieved from webappa.cdc.gov/sasweb/ncipc/ypll10.html
. (2011). Suicidal thoughts and behaviors among adults aged >18 years – United States 2009. Morbidity and Mortality Weekly Report, 60(SS12), 1–22.
(2011). ArcGIS Desktop (Release 10) [Computer software]. Redlands, CA: Environmental Systems Research Institute.
(2002). Reducing suicide: A national imperative. Retrieved from site.ebrary.com/lib/byuprovo/docDetail.action
(2011). Twitter: Number of tweets tripled in past year. Retrieved from articles.cnn.com/2011-07-01/tech/twitter.tweets_1_tweets-twitter-kate-middleton?_s=PM:TECH
(2003). Suicide following deliberate self-harm: Long-term follow-up of patients who presented to a general hospital. British Journal of Psychiatry, 182, 537–542.
(2010, 6). How much is too much? Privacy issues on Twitter. Paper presented at the 60th Annual Conference of the International Communication Association, Singapore. Retrieved from www2.research.att.com/~bala/papers/ica10.pdf
(2010). Twitter study reveals interesting results about usage – 40% is ”pointless babble.” Retrieved from www.pearanalytics.com/blog/2009/twitter-study-reveals-interesting-results-40-percent-pointless-babble
(2001). Developing a comprehensive school suicide prevention program. Journal of School Health, 71(4), 132–137.
(2011). Bullying and suicide. Psychiatric Times, 28(2), 1–6.
(2011). National vital statistics report: Deaths. Retrieved from www.cdc.gov/nchs/data/nvsr/nvsr60/nvsr60_03.pdf
(2002). Psychiatric emergencies call for comprehensive assessment and treatment. Journal of the American Medical Association, 288(6), 686–687.
(1977). The measurement of observer agreement for categorical data. Biometrics, 33, 159–174.
(1994). Psychosocial risk factors for future adolescent suicide attempts. Journal of Consulting and Clinical Psychology, 62(2), 297–305.
(2013). Hip-hop artist Freddy E dead in apparent suicide. Retrieved from www.mtv.com/news/articles/1699754/freddy-e-dead.jhtml
(2007). Making it safer: A health centre’s strategy for suicide prevention. Psychiatry Quarterly, 78, 295–307.
(2008). Risk and protective facts for suicide and suicidal behavior: A literature review. Retrieved from www.scotland.gov.uk/Publications/2008/11/28141444/0
(2012). Suicide in the U.S.: Statistics and prevention. Retrieved from www.nimh.nih.gov/health/publications/suicide-in-the-us-statistics-and-prevention/index.shtml
. (2010). National hospital ambulatory medical care survey: 2007 emergency department visits. Retrieved from 198.246.98.21/nchs/data/nhsr/nhsr026.pdf
(2011). Suicide announcement on Facebook. Crisis, 32(5), 280–282.
(2011). The use of Twitter to track levels of disease activity and public concern in the U.S. during the influenza A H1N1 pandemic. PLoS One, 6(5), e19467.
(2012). Twitter use 2012. Retrieved from pewinternet.org/Reports/2012/Twitter-Use-2012/Findings.aspx
(1999). The Surgeon General’s call to action to prevent suicide. Retrieved from www.surgeongeneral.gov/library/calltoaction/default.htm
. (2011). Breastfeeding and blogging: Exploring the utility of blogs to promote breastfeeding. American Journal of Health Education, 42(2), 106–115.
(2012). Temporal variability of problem drinking on Twitter. Open Journal of Preventive Medicine, 2(1), 43–48.
(2004). Repetition of deliberate self-harm and subsequent suicide risk: Long-term follow-up study of 11,583 patients. The British Journal of Psychiatry, 185, 70–75.
(2011). Predicting stock market indicators through Twitter ”I hope it is not as bad as I fear.” Retrieved from dx.doi.org/10.1016/j.sbspro.2011.10.562
(