Email this article A Framework for Predicting Self-Harm Using Social Media Signals
Abstract
Mental health issues such as self-harm can be highly dangerous on a personal and societal level. Economic tolls are also considerable. People self harm due to psychological discomfort or deep distress. Automated processes that solely look at historical information have shown, time and time again, to completely miss consideration of emotions. Emotions play an essential role in the manner in which individuals function. Untapped socioeconomic potential of nations can be provided through interventions targeted at social media analysis, including social indicators in data analysis, and refining self-harm prediction models on a national scale. This model has successfully conducted emotion recognition, transforming emotions such as sadness, anxiety, and experiences of suicidal thoughts into time series data from various social media platforms enabling the prediction and detection of self-harm patterns with adequate time. Subsequent testing showed significant improvements to the framework when implemented with Decision Trees and XGBoost in conjunction with machine learning algorithms. Thailand proved to be an excellent candidate, showcasing over 40% improvement relative to previous frameworks utilizing conventional methodologies.
References
(May 2023). Suicide Rates for Girls Are Rising. Are Smartphones to Blame? [Online]. Available: https://www.economist.com/graphic-detail/ 2023/05/03/suicide-rates-for-girls-are-rising-are-smartphones-to-blame
J. Adam-Troian and T. Arciszewski, ‘‘Absolutist words from search volume data predict state-level suicide rates in the United States,’’ Clin. Psychol. Sci., vol. 8, no. 4, pp. 788–793, Jul. 2020.
A. E. Aiello, A. Renson, and P. Zivich, ‘‘Social media-and Internet-based disease surveillance for public health,’’ Annu. Rev. Public Health, vol. 41, p. 101, Apr. 2020.
M. Akyuz and C. Karul, ‘‘The effect of economic factors on suicide: An analysis of a developing country,’’ Int. J. Hum. Rights Healthcare, Jul. 2022.
S. Z. Alavijeh, F. Zarrinkalam, Z. Noorian, A. Mehrpour, and K. Etminani, ‘‘What users’ musical preference on Twitter reveals about psychological disorders,’’ Inf. Process. Manage., vol. 60, no. 3, May 2023, Art. no. 103269.
A. Aldayel and W. Magdy, ‘‘Stance detection on social media: State of the art and trends,’’ Inf. Process. Manage., vol. 58, no. 4, Jul. 2021, Art. no. 102597.
P. Angelov and A. Sperduti, ‘‘Challenges in deep learning,’’ in Proc. 24th Eur. Symp. Artif. Neural Netw. (ESANN), 2016, pp. 489–496.
A. Apisarnthanarak, P. Apisarnthanarak, C. Siripraparat, P. Saengaram, N. Leeprechanon, and D. J. Weber, ‘‘Impact of anxiety and fear for COVID-19 toward infection control practices among Thai healthcare workers,’’ Infection Control Hospital Epidemiol., vol. 41, no. 9, pp. 1093–1094, Sep. 2020.
S. Arunpongpaisal, S. Assanagkornchai, V. Chongsuvivatwong, and N. Jampathong, ‘‘Time-series analysis of trends in the incidence rates of successful and attempted suicides in Thailand in 2013–2019 and their predictors,’’ BMC Psychiatry, vol. 22, no. 1, pp. 1–11, Aug. 2022.
J. M. Barros, R. Melia, K. Francis, J. Bogue, M. O’Sullivan, K. Young, R. A. Bernert, D. Rebholz-Schuhmann, and J. Duggan, ‘‘The validity of Google trends search volumes for behavioral forecasting of national suicide rates in Ireland,’’ Int. J. Environ. Res. Public Health, vol. 16, no. 17, p. 3201, Sep. 2019.
B. E. Belsher, D. J. Smolenski, L. D. Pruitt, N. E. Bush, E. H. Beech, D. E. Workman, R. L. Morgan, D. P. Evatt, J. Tucker, and N. A. Skopp, ‘‘Prediction models for suicide attempts and deaths: A systematic review and simulation,’’ JAMA Psychiatry, vol. 76, no. 6, pp. 642–651, 2019.
L. Braghieri, R. Levy, and A. Makarin, ‘‘Social media and mental health,’’ Amer. Econ. Rev., vol. 112, no. 11, pp. 3660–3693, 2022.
R. G. Brereton and G. R. Lloyd, ‘‘Support vector machines for classification and regression,’’ Analyst, vol. 135, no. 2, pp. 230–267, 2010.
J. A. Bridge, M. Olfson, J. M. Caterino, S. W. Cullen, A. Diana, M. Frankel, and S. C. Marcus, ‘‘Emergency department management of deliberate selfharm: A national survey,’’ JAMA Psychiatry, vol. 76, no. 6, pp. 652–654, 2019.
L. Cao, H. Zhang, and L. Feng, ‘‘Building and using personal knowledge graph to improve suicidal ideation detection on social media,’’ IEEE Trans. Multimedia, vol. 24, pp. 87–102, 2022.
M. K. Y. Chan, H. Bhatti, N. Meader, S. Stockton, J. Evans, R. C. O’Connor, N. Kapur, and T. Kendall, ‘‘Predicting suicide following self-harm: Systematic review of risk factors and risk scales,’’ Brit. J. Psychiatry, vol. 209, no. 4, pp. 277–283, Oct. 2016.
Y. S. Chang and J. Lee, ‘‘Is forecasting future suicide rate possible?— Application of experience curve,’’ Eng. Manag. Res., vol. 1, no. 1, p. 10, 2012.
T. Chen, T. He, M. Benesty, V. Khotilovich, Y. Tang, and H. Cho, ‘‘XGBoost: Extreme gradient boosting,’’ R Package Version 0.4-2, Microsoft, Tech. Rep., 2015, pp. 1–4, vol. 1, no. 4.
R. Cholakov and T. Kolev, ‘‘TheGatedTabTransformer. An enhanced deep learning architecture for tabular modeling,’’ 2022, arXiv:2201.00199.
D. Demszky, D. Movshovitz-Attias, J. Ko, A. Cowen, G. Nemade, and S. Ravi, ‘‘GoEmotions: A dataset of fine-grained emotions,’’ in Proc. 58th Annu. Meeting Assoc. Comput. Linguistics, Jul. 2020, pp. 4040–4054. [Online]. Available: https://aclanthology.org/2020.aclmain.372, doi: 10.18653/v1/2020.acl-main.372.
Refbacks
- There are currently no refbacks.
Copyright © 2013, All rights reserved.| ijseat.com
International Journal of Science Engineering and Advance Technology is licensed under a Creative Commons Attribution 3.0 Unported License.Based on a work at IJSEat , Permissions beyond the scope of this license may be available at http://creativecommons.org/licenses/by/3.0/deed.en_GB.
Â