Breaking the silence: leveraging social interaction data to identify high-risk suicide users online using network analysis and machine learning.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
20 08 2024
20 08 2024
Historique:
received:
02
02
2024
accepted:
14
08
2024
medline:
22
8
2024
pubmed:
22
8
2024
entrez:
21
8
2024
Statut:
epublish
Résumé
Suicidal thought and behavior (STB) is highly stigmatized and taboo. Prone to censorship, yet pervasive online, STB risk detection may be improved through development of uniquely insightful digital markers. Focusing on Sanctioned Suicide, an online pro-choice suicide forum, this work derived 17 egocentric network features to capture dynamics of social interaction and engagement within this uniquely uncensored community. Using network data generated from over 3.2 million unique interactions of N = 192 individuals, n = 48 of which were determined to be highest risk users (HRUs), a machine learning classification model was trained, validated, and tested to predict HRU status. Model prediction dynamics were analyzed using introspection techniques to uncover patterns in feature influence and highlight social phenomena. The model achieved a test AUC = 0.73 ([0.61, 0.85], 95% CI), suggesting that network-based socio-behavioral patterns of online interaction can signal for heightened suicide risk. Transitivity, density, and in-degree centrality were among the most important features driving this performance. Moreover, predicted HRUs tended to be targets of social exchanges with lesser frequency and possessed egocentric networks with "small world" network properties. Through the implementation of an underutilized method on an unlikely data source, findings support future incorporation of network-based social interaction features in descriptive, predictive, and preventative STB research.
Identifiants
pubmed: 39169143
doi: 10.1038/s41598-024-70282-0
pii: 10.1038/s41598-024-70282-0
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
19395Subventions
Organisme : NIDA NIH HHS
ID : NIDA-5P30DA02992610
Pays : United States
Organisme : NIDA NIH HHS
ID : NIDA-5P30DA02992610
Pays : United States
Informations de copyright
© 2024. The Author(s).
Références
World Health Organization. Suicide Fact Sheet. https://www.who.int/news-room/fact-sheets/detail/suicide (2022).
American Foundation for Suicide Prevention. Suicide Statistics. https://afsp.org/suicide-statistics/ (2023).
O’Connor, R. C. & Kirtley, O. J. The integrated motivational–volitional model of suicidal behaviour. Phil. Trans. R. Soc. B 373, 20170268 (2018).
pubmed: 30012735
pmcid: 6053985
De Choudhury, M. & Kıcıman, E. The Language of Social Support in Social Media and its Effect on Suicidal Ideation Risk. Proc Int AAAI Conf Weblogs Soc Media 2017, 32–41 (2017).
pubmed: 28840079
pmcid: 5565730
Carlyle, K. E., Guidry, J. P. D., Williams, K., Tabaac, A. & Perrin, P. B. Suicide conversations on Instagram™: contagion or caring?. J. Commun. Healthc. 11, 12–18 (2018).
Jashinsky, J. et al. Tracking suicide risk factors through Twitter in the US. Crisis 35, 51–59 (2014).
pubmed: 24121153
O’Dea, B., Larsen, M. E., Batterham, P. J., Calear, A. L. & Christensen, H. A linguistic analysis of suicide-related Twitter posts. Crisis J. Crisis Intervent. Suicide Prevent. 38, 319–329 (2017).
Renjith, S., Abraham, A., Jyothi, S. B., Chandran, L. & Thomson, J. An ensemble deep learning technique for detecting suicidal ideation from posts in social media platforms. Journal of King Saud University - Computer and Information Sciences 34, 9564–9575 (2022).
Roy, A. et al. A machine learning approach predicts future risk to suicidal ideation from social media data. npj Digital Medicine 3, 1–12 (2020).
Brown, R. C. et al. Can acute suicidality be predicted by Instagram data? Results from qualitative and quantitative language analyses. PLoS ONE 14, e0220623 (2019).
pubmed: 31504042
pmcid: 6736249
Kemp, C. G. & Collings, S. C. Hyperlinked suicide: Assessing the prominence and accessibility of suicide websites. Crisis 32, 143–151 (2011).
pubmed: 21616763
Tadesse, M. M., Lin, H., Xu, B. & Yang, L. Detection of suicide ideation in social media forums using deep learning. Algorithms 13, 7 (2020).
Unruh-Dawes, E. L., Smith, L. M., Krug Marks, C. P. & Wells, T. T. Differing relationships between Instagram and Twitter on suicidal thinking: The importance of interpersonal factors. Soc. Media Soc. 8, 20563051221077028 (2022).
Sierra, G. et al. Suicide risk factors: A language analysis approach in social media. J. Lang. Soc. Psychol. 41, 312–330 (2022).
Grant, R. N. et al. Automatic extraction of informal topics from online suicidal ideation. BMC Bioinform. 19, 211 (2018).
Ren, F., Kang, X. & Quan, C. Examining accumulated emotional traits in suicide blogs with an emotion topic model. IEEE J. Biomed. Health Inform. 20, 1384–1396 (2016).
pubmed: 26208372
Li, A. et al. An analysis of stigma and suicide literacy in responses to suicides broadcast on social media. Asia-Pacific Psych. 10, e12314 (2018).
Deas, N. et al. I just want to matter: Examining the role of anti-mattering in online suicide support communities using natural language processing. Comput. Human Behav. 139, 107499 (2023).
Spitzer, E. G., Crosby, E. S. & Witte, T. K. Looking through a filtered lens: Negative social comparison on social media and suicidal ideation among young adults. Psychol. Popular Media 12, 69–76 (2023).
de Beurs, D. et al. A network perspective on suicidal behavior: understanding suicidality as a complex system. Suicide Life-Threatening Behav. 51, 115–126 (2021).
Holman, M. S. & Williams, M. N. Suicide risk and protective factors: a network approach. Arch. Suicide Res. 26, 137–154 (2022).
pubmed: 32522102
De Choudhury, M., Gamon, M., Counts, S. & Horvitz, E. Predicting depression via social media. Proc. Int. AAAI Conf. Web Social Med. 7, 128–137 (2013).
Dutta, S. & De Choudhury, M. Characterizing Anxiety Disorders with Online Social and Interactional Networks. in HCI International 2020 – Late Breaking Papers: Interaction, Knowledge and Social Media (eds. Stephanidis, C. et al.) 249–264 (Springer International Publishing, Cham, 2020). https://doi.org/10.1007/978-3-030-60152-2_20 .
Abuhassan, M. et al. Classification of Twitter users with eating disorder engagement: learning from the biographies. Comput. Human Behav. 140, 107519 (2023).
Beeney, J. E., Hallquist, M. N., Clifton, A. D., Lazarus, S. A. & Pilkonis, P. A. Social disadvantage and borderline personality disorder: A study of social networks. Person. Disorders: Theory, Res. Treat. 9, 62–72 (2018).
Colombo, G. B., Burnap, P., Hodorog, A. & Scourfield, J. Analysing the connectivity and communication of suicidal users on twitter. Comput. Commun. 73, 291–300 (2016).
pubmed: 26973360
pmcid: 4784725
Wang, Z., Yu, G. & Tian, X. Exploring behavior of people with suicidal ideation in a Chinese online suicidal community. Int. J. Environ. Res. Public Health 16, 54 (2019).
Myers West, S. Censored, suspended, shadowbanned: User interpretations of content moderation on social media platforms. New Media Soc. 20, 4366–4383 (2018).
Cobbe, J. Algorithmic censorship by social platforms: Power and resistance. Philosophy Technol. 34, 739–766 (2021).
Gillespie, T. Custodians of the Internet: Platforms, Content Moderation, and the Hidden Decisions That Shape Social Media. (Yale University Press, 2018).
Das, S. & Kramer, A. Self-censorship on facebook. Proc. Int. AAAI Conf. Web Social Media 7, 120–127 (2021).
Powers, E., Koliska, M. & Guha, P. “Shouting matches and echo chambers”: perceived identity threats and political self-censorship on social media. Int. J. Commun. 13, 20 (2019).
Lekkas, D. & Jacobson, N. C. The hidden depths of suicidal discourse: Network analysis and natural language processing unmask uncensored expression. Digital Health 9, 20552076231210710 (2023).
pubmed: 37928333
pmcid: 10623973
Richardson, L. Beautiful soup documentation. (2007).
Barbaro, M. Kids Are Dying. How Are These Sites Still Allowed?
Rafaeli, S., Ravid, G. & Soroka, V. De-lurking in Virtual Communities: A Social Communication Network Approach to Measuring the Effects of Social and Cultural Capital. in Proceedings of the Hawaii International Conference on System Sciences (Honolulu, HI, 2004). https://doi.org/10.1109/HICSS.2004.1265478 .
da Silva, L. F. C., Barbosa, M. W. & Gomes, R. R. Measuring participation in distance education online discussion forums using social network analysis. J. Assoc. Inform. Sci. Technol. 70, 140–150 (2019).
Hecking, T., Chounta, I.-A. & Hoppe, H. U. Investigating social and semantic user roles in MOOC discussion forums. in Proceedings of the Sixth International Conference on Learning Analytics & Knowledge - LAK ’16 198–207 (ACM Press, Edinburgh, United Kingdom, 2016). https://doi.org/10.1145/2883851.2883924 .
Hagberg, A. A., Schult, D. A. & Swart, P. J. Exploring network structure, dynamics, and function using NetworkX. in Proceedings of the 7th Python in Science Conference (SciPy2008) 11–15 (Pasadena, CA USA, 2008).
Kuhn, M. Building Predictive Models in R Using the caret Package. J. Stat. Softw. 28, 1–26 (2008).
Friedman, J., Hastie, T. & Tibshirani, R. Regularization paths for generalized linear models via coordinate descent. J. Stat. Softw. 33, 1–22 (2010).
pubmed: 20808728
pmcid: 2929880
Chawla, N. V., Bowyer, K. W., Hall, L. O. & Kegelmeyer, W. P. SMOTE: synthetic minority over-sampling technique. Jair 16, 321–357 (2002).
John, C. R. MLeval: Machine Learning Model Evaluation. (2020).
Lundberg, S. & Lee, S.-I. A Unified Approach to Interpreting Model Predictions. arXiv:1705.07874 [cs, stat] (2017).
Shapley, L. S. A value for n-person games. Contribut. Theory Games 2, 307–317 (1953).
Humphries, M. D. & Gurney, K. Network ‘small-world-ness’: a quantitative method for determining canonical network equivalence. PLOS ONE 3, e0002051 (2008).
pubmed: 18446219
Joiner, T. E. Why People Die By Suicide. (Harvard University Press, 2005).
Klonsky, E. D. & May, A. M. The Three-Step Theory (3ST): A new theory of suicide rooted in the “ideation-to-action” framework. Int. J. Cognitive Therapy 8, 114–129 (2015).
Alvarez, M. “Life is about trying to find a better place to live”: Discourses of dwelling in a pro-recovery suicide forum. Qual. Res. Med. Healthc. 6, 10437 (2022).
pubmed: 37441057
pmcid: 10336861
Mazuz, K. & Yom-Tov, E. Analyzing trends of loneliness through large-scale analysis of social media postings: observational study. JMIR Ment. Health 7, e17188 (2020).
pubmed: 32310141
pmcid: 7199140