Objective tools to assess suicide risk are needed to determine when someone is at imminent risk. In this pilot laboratory investigation, we used a within-subjects design to identify patterns in text messaging (short message service) unique to high-risk periods preceding suicide attempts. Individuals reporting a history of suicide attempt (N = 33) retrospectively identified past attempts and periods of lower risk (e.g., suicide ideation). Language analysis software scored 189,478 text messages to capture three psychological constructs: self-focus, sentiment, and social engagement. Mixed-effects models tested whether these constructs differed in general (means) and over time (slopes) 2 weeks before a suicide attempt relative to lower-risk periods. Regarding mean differences, no language features uniquely differentiated suicide attempts from other episodes. However, when examining patterns over time, anger increased and positive emotion decreased to a greater extent as participants approached a suicide attempt. Results suggest private electronic communication has the potential to provide real-time digital markers of suicide risk.
AmmermanB. A.KleimanE. M.UyejiL. L.KnorrA. C.McCloskeyM. S. (2015). Suicidal and violent behavior: The role of anger, emotion dysregulation, and impulsivity. Personality and Individual Differences, 79, 57–62.
2.
BaayenR. H.DavidsonD. J.BatesD. M. (2008). Mixed-effects modeling with crossed random effects for subjects and items. Journal of Memory and Language, 59, 390–412.
3.
BarrD. J.LevyR.ScheepersC.TilyH. J. (2013). Random effects structure for confirmatory hypothesis testing: Keep it maximal. Journal of Memory and Language, 68, 255–278.
4.
BatesD.MaechlerM.BolkerB.WalkerS. (2019). lme4: Linear mixed-effects models using Eigen and S4 (Version 1.1-21) [Computer software]. Retrieved from https://cran.r-project.org/package=lme4
5.
BaumeisterR. F. (1990). Suicide as escape from self. Psychological Review, 97, 90–113.
6.
BorgesG.NockM. K.AbadJ. M. H.HwangI.SampsonN. A.AlonsoJ.. . . BrometE. (2010). Twelve-month prevalence of and risk factors for suicide attempts in the World Health Organization World Mental Health Surveys. The Journal of Clinical Psychiatry, 71, 1617–1628.
7.
BraithwaiteS. R.Giraud-CarrierC.WestJ.BarnesM. D.HansonC. L. (2016). Validating machine learning algorithms for Twitter data against established measures of suicidality. JMIR Mental Health, 3(2), Article e21. doi:10.2196/mental.4822
8.
BrownT. A.ChorpitaB. F.BarlowD. H. (1998). Structural relationships among dimensions of the DSM-IV anxiety and mood disorders and dimensions of negative affect, positive affect, and autonomic arousal. Journal of Abnormal Psychology, 107, 179–192.
9.
BulikC. M.CarpenterL. L.KupferD. J.FrankE. (1990). Features associated with suicide attempts in recurrent major depression. Journal of Affective Disorders, 18, 29–37.
10.
BuschK. A.FawcettJ.JacobsD. G. (2003). Clinical correlates of inpatient suicide. Journal of Clinical Psychiatry, 64, 14–19.
11.
CambriaE.SchullerB.XiaY.HavasiC. (2013). New avenues in opinion mining and sentiment analysis. IEEE Intelligent Systems, 28(2), 15–21.
12.
Centers for Disease Control and Prevention. (2014). Web-based Injury Statistics Query and Reporting System (WISQARS). Retrieved from http://www.cdc.gov/ncipc/wisqars
13.
DanielS. S.GoldstonD. B.ErkanliA.FranklinJ. C.MayfieldA. M. (2009). Trait anger, anger expression, and suicide attempts among adolescents and young adults: A prospective study. Journal of Clinical Child & Adolescent Psychology, 38, 661–671.
14.
De ChoudhuryM.KicimanE.DredzeM.CoppersmithG.KumarM. (2016). Discovering shifts to suicidal ideation from mental health content in social media. CHI 2016: Proceedings of the 34th annual SIGCHI Conference on Human Factors in Computing Systems (pp. 2098–2110). doi:10.1145/2858036.2858207
15.
DeJongT. M.OverholserJ. C.StockmeierC. A. (2010). Apples to oranges?: A direct comparison between suicide attempters and suicide completers. Journal of Affective Disorders, 124, 90–97.
16.
DixonP. (2008). Models of accuracy in repeated-measures designs. Journal of Memory and Language, 59, 447–456.
17.
GouldM. S.MarroccoF. A.KleinmanM.ThomasJ. G.MostkoffK.CoteJ.DaviesM. (2005). Evaluating iatrogenic risk of youth suicide screening programs: A randomized controlled trial. JAMA, 293(13), 1635–1643.
18.
GunnJ. F.LesterD. (2012). Twitter postings and suicide: An analysis of the postings of a fatal suicide in the 24 hours prior to death. Suicidologi, 17(3), 28–30. doi:10.5617/suicidologi.2173
19.
HammondK. W.LaundryR. J. (2014January6–9). Application of a hybrid text mining approach to the study of suicidal behavior in a large population. Paper presented at the 47th Hawaii International Conference on System Sciences, Waikoloa, Hawaii.
20.
HawkinsK. A.CougleJ. R. (2013). A test of the unique and interactive roles of anger experience and expression in suicidality: Findings from a population-based study. The Journal of Nervous and Mental Disease, 201, 959–963.
21.
HawtonK.CasanasI. C. C.HawC.SaundersK. (2013). Risk factors for suicide in individuals with depression: A systematic review. Journal of Affective Disorders, 147(1–3), 17–28.
22.
JaegerT. F. (2008). Categorical data analysis: Away from ANOVAs (transformation or not) and towards logit mixed models. Journal of Memory and Language, 59, 434–446.
23.
JamesG.WittenD.HastieT.TibshiraniR. (2013). An introduction to statistical learning (Vol. 112). New York, NY: Springer.
24.
JoinerT. (2005). Why people die by suicide. Cambridge, MA: Harvard University Press.
25.
JoinerT. E.Jr.PettitJ. W.WalkerR. L.VoelzZ. R. (2002). Perceived burdensomeness and suicidality: Two studies on the suicide notes of those attempting and those completing suicide. Journal of Social and Clinical Psychology, 21, 531–545.
26.
KaganV.RossiniE.SapounasD. (2013). Sentiment analysis for PTSD signals. Berlin, Germany: Springer.
27.
KernM. L.ParkG.EichstaedtJ. C.SchwartzH. A.SapM.SmithL. K.UngarL. H. (2016). Gaining insights from social media language: Methodologies and challenges. Psychological Methods, 21, 507–525.
28.
KesslerR. C.AbelsonJ.DemlerO.EscobarJ. I.GibbonM.GuyerM. E.. . . WaltersE. E. (2004). Clinical calibration of DSM-IV diagnoses in the World Mental Health (WMH) version of the World Health Organization (WHO) Composite International Diagnostic Interview (WMH-CIDI). International Journal of Methods in Psychiatric Research, 13, 122–139.
29.
KesslerR. C.WarnerL. C. H.IvanyL. C.PetukhovaM. V.RoseS.BrometE. J.. . . UrsanoR. J. (2015). Predicting US Army suicides after hospitalizations with psychiatric diagnoses in the Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS). JAMA Psychiatry, 72, 49–57.
30.
MatuschekH.KlieglR.VasishthS.BaayenH.BatesD. (2017). Balancing Type I error and power in linear mixed models. Journal of Memory and Language, 94, 305–315.
31.
MayA. M.KlonskyE. D. (2016). What distinguishes suicide attempters from suicide ideators? A meta-analysis of potential factors. Clinical Psychology: Science and Practice, 23, 5–20.
32.
MillnerA. J.LeeM. D.NockM. K. (2015). Single-item measurement of suicidal behaviors: Validity and consequences of misclassification. PLOS ONE, 10(10), Article e0141606. doi:10.1371/journal.pone.0141606
33.
MillnerA. J.LeeM. D.NockM. K. (2016). Describing and measuring the pathway to suicide attempts: A preliminary study. Suicide and Life-Threatening Behavior, 47, 353–369.
34.
MurphyS. L.XuJ.KochanekK. D. (2013). Deaths: Final data for 2010. National Vital Statistics Reports, 61(4), 1–117.
35.
NoblesA. L.GlennJ. J.KowsariK.TeachmanB. A.BarnesL. E. (2018). Identification of imminent suicide risk among young adults using text messages. In CHI ’18: Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (Article 413). doi: 10.1145/3173574.3173987
36.
NockM. K.BorgesG.OnoY. (Eds.). (2012). Suicide: Global perspectives from the WHO World Mental Health Surveys. Cambridge, UK: Cambridge University Press.
37.
NockM. K.DemingC. A.ChaC. B.ChiuW. T.HwangI.SampsonN. A. . . . BeautraisA. (2012). Sociodemographic risk factors for suicidal behavior: Results from the WHO World Mental Health Surveys. In NockM. K.BorgesG.OnoY. (Eds.), Suicide: Global perspectives from the WHO World Mental Health Surveys (pp. 86–100). Cambridge, UK: Cambridge University Press.
38.
NockM. K.HolmbergE. B.PhotosV. I.MichelB. D. (2007). Self-Injurious Thoughts and Behaviors Interview: Development, reliability, and validity in an adolescent sample. Psychological Assessment, 19, 309–317.
39.
NockM. K.HwangI.SampsonN.KesslerR. C. (2010). Mental disorders, comorbidity, and suicidal behaviors: Results from the National Comorbidity Survey Replication. Molecular Psychiatry, 15, 868–876.
OnnelaJ.-P.RauchS. L. (2016). Harnessing smartphone-based digital phenotyping to enhance behavioral and mental health. Neuropsychopharmacology, 41(7), 1691–1696.
PestianJ. P.MatykiewiczP.Linn-GustM. (2012). What’s in a note: Construction of a suicide note corpus. Biomedical Informatics Insights, 5(5), 1–6.
44.
PeughJ. L. (2010). A practical guide to multilevel modeling. Journal of School Psychology, 48, 85–112.
45.
R Core Team. (2019). R: A language and environment for statistical computing (Version 3.6.1) [Computer software]. Vienna, Austria: R Foundation for Statistical Computing.
46.
ReynoldsS. K.LindenboimN.ComtoisK. A.MurrayA.LinehanM. M. (2006). Risky assessments: Participant suicidality and distress associated with research assessments in a treatment study of suicidal behavior. Suicide and Life-Threatening Behavior, 36, 19–34.
47.
RothmanK. J. (1990). No adjustments are needed for multiple comparisons. Epidemiology, 1, 43–46.
48.
SmithJ. M.AlloyL. B.AbramsonL. Y. (2006). Cognitive vulnerability to depression, rumination, hopelessness, and suicidal ideation: Multiple pathways to self-injurious thinking. Suicide and Life-Threatening Behavior, 36, 443–454.
49.
SohnS.ToriiM.LiD.WagholikarK.WuS.LiuH. (2012). A hybrid approach to sentiment sentence classification in suicide notes. Biomedical Informatics Insights, 5(Suppl 1), 43–50.
50.
StirmanS. W.PennebakerJ. W. (2001). Word use in the poetry of suicidal and nonsuicidal poets. Psychosomatic Medicine, 63, 517–522.
51.
ThompsonM. P.KaslowN. J.ShortL. M.WyckoffS. (2002). The mediating roles of perceived social support and resources in the self-efficacy-suicide attempts relation among African American abused women. Journal of Consulting and Clinical Psychology, 70, 942–949.
52.
TorousJ.KiangM. V.LormeJ.OnnelaJ.-P. (2016). New tools for new research in psychiatry: A scalable and customizable platform to empower data driven smartphone research. JMIR Mental Health, 3(2), Article e16. doi:10.2196/mental.5165
53.
Van OrdenK. A.WitteT. K.CukrowitzK. C.BrathewaiteS. R.SelbyE. A.JoinerT. E. (2010). The interpersonal theory of suicide. Psychological Review, 117, 575–600.
54.
VenekV.SchererS.MorencyL.-P.RizzoA.PestianJ. (2014). Adolescent suicidal risk assessment in clinician-patient interaction: A study of verbal and acoustic behaviors. In Proceedings of the 2014 IEEE Spoken Language Technology Workshop (pp. 277–282). doi:10.1109/SLT.2014.7078587
55.
WalshC. G.RibeiroJ. D.FranklinJ. C. (2017). Predicting risk of suicide attempts over time through machine learning. Clinical Psychological Science, 5, 457–469.
56.
World Health Organization. (2009). Global health risks: Mortality and burden of disease attributable to selected major risks. Geneva, Switzerland: Author.
57.
World Health Organization. (2014). The World Health Organization world mental health composite international diagnostic interview (WHO WMH-CIDI). Retrieved from https://www.hcp.med.harvard.edu/wmhcidi/
58.
YangH.WillisA.De RoeckA.NuseibehB. (2012). A hybrid model for automatic emotion recognition in suicide notes. Biomedical Informatics Insights, 5(Suppl 1), 17–30.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
