Can acute suicidality be predicted by Instagram data? Results from qualitative and quantitative language analyses
Autoři:
Rebecca C. Brown aff001; Eileen Bendig aff002; Tin Fischer aff003; A. David Goldwich aff004; Harald Baumeister aff002; Paul L. Plener aff001
Působiště autorů:
University of Ulm, Department of Child and Adolescent Psychiatry and Psychotherapy, Ulm, Germany
aff001; University of Ulm, Department of Clinical Psychology and Psychotherapy, Ulm
aff002; Independent Contributor, Freelancing Data Journalist, Berlin, Germany
aff003; Independent Contributor, Freelancing Software Developer, Berlin, Germany
aff004; Medical University of Vienna, Department for Child and Adolescent Psychiatry, Vienna, Austria
aff005
Vyšlo v časopise:
PLoS ONE 14(9)
Kategorie:
Research Article
doi:
https://doi.org/10.1371/journal.pone.0220623
Souhrn
Background
Social media has become increasingly important for communication among young people. It is also often used to communicate suicidal ideation.
Aims
To investigate the link between acute suicidality and language use as well as activity on Instagram.
Method
A total of 52 participants, aged on average around 16 years, who had posted pictures of non-suicidal self-injury on Instagram, and reported a lifetime history of suicidal ideation, were interviewed using Instagram messenger. Of those participants, 45.5% reported suicidal ideation on the day of the interview (acute suicidal ideation). Qualitative text analysis (software ATLAS.ti 7) was used to investigate experiences with expressions of active suicidal thoughts on Instagram. Quantitative text analysis of language use in the interviews and directly on Instagram (in picture captions) was performed using the Linguistic Inquiry and Word Count software. Language markers in the interviews and in picture captions, as well as activity on Instagram were added to regression analyses, in order to investigate predictors for current suicidal ideation.
Results
Most participants (80%) had come across expressions of active suicidal thoughts on Instagram and 25% had expressed active suicidal thoughts themselves. Participants with acute suicidal ideation used significantly more negative emotion words (Cohen’s d = 0.66, 95% CI: 0.088–1.232) and words expressing overall affect (Cohen’s d = 0.57, 95% CI: 0.001–1.138) in interviews. However, activity and language use on Instagram did not predict acute suicidality.
Conclusions
While participants differed with regard to their use of language in interviews, differences in activity and language use on Instagram were not associated with acute suicidality. Other mechanisms of machine learning, like identifying picture content, might be more valuable.
Klíčová slova:
Medicine and health sciences – Mental health and psychiatry – Suicide – Biology and life sciences – Neuroscience – Cognitive science – Cognitive psychology – Language – Psychology – Emotions – Social sciences – Sociology – Communications – Social communication – Social media – Linguistics – Cognitive linguistics – Psycholinguistics – Computer and information sciences – Network analysis – Social networks – People and places – Population groupings – Age groups – Children – Adolescents – Families
Zdroje
1. World Health Organization. Suicide data. 2018 [cited 2018 03/13/2018]; http://www.who.int/mental_health/prevention/suicide/suicideprevent/en/.
2. Kokkevi A, Rotsika V, Arapaki A, Richardson C. Adolescents’ self-reported suicide attempts, self-harm thoughts and their correlates across 17 European countries. J Child Psychol Psychiatry Allied Discip. 2012;53(4):381–9.
3. Donath C, Graessel E, Baier D, Bleich S, Hillemacher T. Is parenting style a predictor of suicide attempts in a representative sample of adolescents? BMC Pediatr. 2014 Dec;14(1):113.
4. Plener PL, Libal G, Keller F, Fegert JM, Muehlenkamp JJ. An international comparison of adolescent non-suicidal self-injury (NSSI) and suicide attempts: Germany and the USA. Psychol Med. 2009;39(9):1549–58. doi: 10.1017/S0033291708005114 19171079
5. Mortier P, Auerbach RP, Alonso J, Bantjes J, Benjet C, Cuijpers P, et al. Suicidal Thoughts and Behaviors Among First-Year College Students: Results From the WMH-ICS Project. J Am Acad Child Adolesc Psychiatry [Internet]. 2018 Apr 1 [cited 2018 Aug 29];57(4):263–273.e1. Available from: https://www.sciencedirect.com/science/article/pii/S0890856718300571 29588052
6. Brunner R, Kaess M, Parzer P, Fischer G, Carli V, Hoven CW, et al. Life-time prevalence and psychosocial correlates of adolescent direct self-injurious behavior: A comparative study of findings in 11 European countries. J Child Psychol Psychiatry. 2014 Apr;55(4):337–48. doi: 10.1111/jcpp.12166 24215434
7. Guimaraes T. Revealed: the demographic trends for every social network 2014. 2014.
8. Duggan M, Smith A. Social media update 2013. 2013.
9. Adrian M, Lyon AR. Social Media Data for Online Adolescent Suicide Risk Identification: Considerations for Integration Within Platforms, Clinics, and Schools. In: Technology and Adolescent Mental Health. 2018. p. 155–70.
10. Luxton DD, June JD, Kinn JT. Technology-Based Suicide Prevention: Current Applications and Future Directions. Telemed e-Health [Internet]. 2011 Jan [cited 2018 Jul 26];17(1):50–4. Available from: http://www.ncbi.nlm.nih.gov/pubmed/21214382
11. Dyson MP, Hartling L, Shulhan J, Chisholm A, Milne A, Sundar P, et al. A Systematic Review of Social Media Use to Discuss and View Deliberate Self-Harm Acts. Seedat S, editor. PLoS One [Internet]. 2016 May 18 [cited 2018 Jul 19];11(5):e0155813. Available from: http://dx.plos.org/10.1371/journal.pone.0155813 27191728
12. Marchant A, Hawton K, Stewart A, Montgomery P, Singaravelu V, Lloyd K, et al. A systematic review of the relationship between internet use, self-harm and suicidal behaviour in young people: The good, the bad and the unknown. Adolesc Ment Heal Serv Oxford Heal NHS Found Trust [Internet]. 2017 [cited 2018 May 9];1–26. Available from: http://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0181722&type=printable
13. Robinson J, Cox G, Bailey E, Hetrick S, Rodrigues M, Fisher S, et al. Social media and suicide prevention: A systematic review. Early Interv Psychiatry. 2016;10(2):103–21. doi: 10.1111/eip.12229 25702826
14. Luxton DD, June JD, Fairall JM. Social media and suicide: a public health perspective. Am J Public Health [Internet]. 2012 May [cited 2018 Jul 26];102 Suppl 2(Suppl 2):S195–200. Available from: http://www.ncbi.nlm.nih.gov/pubmed/22401525
15. Franklin JC, Ribeiro JD, Fox KR, Bentley KH, Kleiman EM, Huang X, et al. Risk factors for suicidal thoughts and behaviors: A meta-analysis of 50 years of research. Psychol Bull [Internet]. 2017 Feb [cited 2018 Aug 23];143(2):187–232. Available from: http://www.ncbi.nlm.nih.gov/pubmed/27841450
16. Nobles AL, Glenn JJ, Kowsari K, Teachman BA, Barnes LE. Identification of Imminent Suicide Risk Among Young Adults using Text Messages. Proc 2018 CHI Conf Hum Factors Comput Syst—CHI ‘18. 2018;1–11.
17. Braithwaite SR, Giraud-Carrier C, West J, Barnes MD, Hanson CL. Validating Machine Learning Algorithms for Twitter Data Against Established Measures of Suicidality. JMIR Ment Heal. 2016;3(2):e21.
18. De Choudhury M, Gamon M, Counts S, Horvitz E. Predicting Depression via Social Media. Proc Seventh Int AAAI Conf Weblogs Soc Media [Internet]. 2013;2:128–37. http://www.aaai.org/ocs/index.php/ICWSM/ICWSM13/paper/viewFile/6124/6351
19. De Choudhury M, Kiciman E, Dredze M, Coppersmith G, Kumar M. Discovering Shifts to Suicidal Ideation from Mental Health Content in Social Media. Proc SIGCHI Conf Hum factors Comput Syst CHI Conf [Internet]. 2016 May [cited 2018 May 9];2016:2098–110. Available from: http://www.ncbi.nlm.nih.gov/pubmed/29082385
20. Fu K, Cheng Q, Wong PWC, Yip PSF. Responses to a Self-Presented Suicide Attempt in Social Media. Crisis [Internet]. 2013 Nov 1 [cited 2018 Jul 20];34(6):406–12. Available from: http://www.ncbi.nlm.nih.gov/pubmed/23871954
21. O’Dea B, Wan S, Batterham PJ, Calear AL, Paris C, Christensen H. Detecting suicidality on Twitter. Internet Interv [Internet]. 2015 May 1 [cited 2018 May 9];2(2):183–8. Available from: https://www.sciencedirect.com/science/article/pii/S2214782915000160
22. Pennebaker JW, Boyd RL, Jordan K, Blackburn K. The Development and Psychometric Properties of LIWC2015. Austin, TX Univ Texas Austin. 2015;
23. Pennebaker JW, Mehl MR, Niederhoffer KG. Psychological Aspects of Natural Language Use: Our Words, Our Selves. Annu Rev Psychol [Internet]. 2003 Feb [cited 2018 Jul 25];54(1):547–77. Available from: http://www.ncbi.nlm.nih.gov/pubmed/12185209
24. Tausczik YR, Pennebaker JW. The Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods. J Lang Soc Psychol. 2010;29(1):24–54.
25. Venek V, Scherer S, Morency L-P, Rizzo AS, Pestian J. Adolescent Suicidal Risk Assessment in Clinician-Patient Interaction. IEEE Trans Affect Comput. 2017;8(2):204–15.
26. Gunn J.F. & Lester D. (2015). Twitter postings and suicide: an analysis of the postings of a fatal suicide in the 24 hours prior to death. Suicidologi, 17(3).
27. Poulin C., Shiner B., Thompson P., Vepstas L., Young-Xu Y., Goertzel B., … McAllister T. (2014). Predicting the risk of suicide by analyzing the text of clinical notes. PloS one, 9(1), e85733 doi: 10.1371/journal.pone.0085733 24489669
28. Flesch R. The art of readable reading. New York: Harper & Brothers; 1949.
29. Temnikova I, Vieweg S, Castillo C. The Case for Readability of Crisis Communications in Social Media. In: Proceedings of the 24th International Conference on World Wide Web—WWW ‘15 Companion [Internet]. New York, New York, USA: ACM Press; 2015 [cited 2018 Jul 26]. p. 1245–50. http://dl.acm.org/citation.cfm?doid=2740908.2741718
30. DuBay WH. The Principles of Readability. Online Submiss [Internet]. 2004 Aug 25 [cited 2018 Jul 26]; https://eric.ed.gov/?id=ED490073
31. Pestian J, Nasrallah H, Matykiewicz P, Bennett A, Leenaars A. Suicide Note Classification using natural language processing: A content analysis. Biomed Inf insights. 2010;6(9):19–28.
32. Batterham PJ, Ftanou M, Pirkis J, Brewer JL, Mackinnon AJ, Beautrais A, Fairweather-Schmidt AK, Christensen H. Psychological Assessment. 2015; 27(2):501–512.
33. Brown RC, Plener PL. Non-suicidal Self-Injury in Adolescence. Curr Psychiatry Rep [Internet]. 2017 Mar [cited 2018 Apr 30];19(3):20. Available from: http://www.ncbi.nlm.nih.gov/pubmed/28315191
34. Wolf M, Horn AB, Mehl MR, Haug S, Pennebaker JW, Kordy H. Computergest??tzte quantitative Textanalyse: ??quivalenz und Robustheit der deutschen Version des Linguistic Inquiry and Word Count. Diagnostica. 2008;54(2):85–98.
35. Amstad T. Wie verständlich sind unsere Zeitungen? Zürich; 1978.
36. R Core Team. R: A Language and Environment for Statistical Computing [Internet]. Vienna, Austria; 2017. https://www.r-project.org
37. Eichstaedt JC, Schwartz HA, Kern ML, Park G, Labarthe DR, Merchant RM, et al. Psychological Language on Twitter Predicts County-Level Heart Disease Mortality. Psychol Sci [Internet]. 2015 Feb 20 [cited 2018 Jul 24];26(2):159–69. Available from: http://journals.sagepub.com/doi/10.1177/0956797614557867 25605707
38. Reece AG, Danforth CM. Instagram photos reveal predictive markers of depression. EPJ Data Sci. 2017;6(1).
39. Pestian JP, Sorter M, Connolly B, Bretonnel Cohen K, McCullumsmith C, Gee JT, et al. A Machine Learning Approach to Identifying the Thought Markers of Suicidal Subjects: A Prospective Multicenter Trial. Suicide Life-Threatening Behav. 2017;47(1):112–21.
40. Venek V, Scherer S, Morency L-P, Rizzo AS, Pestian J. Adolescent Suicidal Risk Assessment in Clinician-Patient Interaction. IEEE Trans Affect Comput [Internet]. 2017;8(2):204–15. Available from: http://ieeexplore.ieee.org/document/7384418/
41. Conway M, O’Connor D. Social Media, Big Data, and Mental Health: Current Advances and Ethical Implications. Curr Opin Psychol [Internet]. 2016 Jun [cited 2018 Jul 25];9:77–82. Available from: http://www.ncbi.nlm.nih.gov/pubmed/27042689
42. Lewis SP, Seko Y, Joshi P. The impact of YouTube peer feedback on attitudes toward recovery from non-suicidal self-injury: An experimental pilot study. Digit Heal [Internet]. 2018 Jan 5 [cited 2018 Aug 23];4:205520761878049. Available from: http://journals.sagepub.com/doi/10.1177/2055207618780499
Článek vyšel v časopise
PLOS One
2019 Číslo 9
- S diagnostikou Parkinsonovy nemoci může nově pomoci AI nástroj pro hodnocení mrkacího reflexu
- Je libo čepici místo mozkového implantátu?
- Pomůže v budoucnu s triáží na pohotovostech umělá inteligence?
- AI může chirurgům poskytnout cenná data i zpětnou vazbu v reálném čase
- Nová metoda odlišení nádorové tkáně může zpřesnit resekci glioblastomů
Nejčtenější v tomto čísle
- Graviola (Annona muricata) attenuates behavioural alterations and testicular oxidative stress induced by streptozotocin in diabetic rats
- CH(II), a cerebroprotein hydrolysate, exhibits potential neuro-protective effect on Alzheimer’s disease
- Comparison between Aptima Assays (Hologic) and the Allplex STI Essential Assay (Seegene) for the diagnosis of Sexually transmitted infections
- Assessment of glucose-6-phosphate dehydrogenase activity using CareStart G6PD rapid diagnostic test and associated genetic variants in Plasmodium vivax malaria endemic setting in Mauritania
Zvyšte si kvalifikaci online z pohodlí domova
Všechny kurzy