An Approach to Detect Suicidal Bengali Posts from Social Media Using Machine Learning Algorithms

An Approach to Detect Suicidal Bengali Posts from Social Media Using Machine Learning Algorithms
  IJETT-book-cover           
  
© 2024 by IJETT Journal
Volume-72 Issue-5
Year of Publication : 2024
Author : Shaikat Chandra Paul, Busrat Jahan, Abdullah Al Mamun, Md Jakir Hossen
DOI : 10.14445/22315381/IJETT-V72I5P105

How to Cite?

Shaikat Chandra Paul, Busrat Jahan, Abdullah Al Mamun, Md Jakir Hossen, "An Approach to Detect Suicidal Bengali Posts from Social Media Using Machine Learning Algorithms," International Journal of Engineering Trends and Technology, vol. 72, no. 5, pp. 43-50, 2024. Crossref, https://doi.org/10.14445/22315381/IJETT-V72I5P105

Abstract
In this modern era, suicide is one of the critical issues. According to the WHO, more than seven million people die due to suicide every year. Suicide is also the second cause of unnatural death for persons between the ages of 15 and 29. Youth in nations like Bangladesh struggle with schoolwork, employment, relationships, drug use, and family issues, all of which are significant or minor contributors on the road to depression. In Bangladesh, people are uncomfortable discussing this ailment openly and frequently mistake this problem as madness. Many at-risk persons use social platforms to talk about their issues or get knowledge on related topics. This study aims to prevent suicide by identifying suicidal posts on social media. We collected suicidal-related data from Kaggle. (We use nine algorithms for three features). The prediction model achieved good performance. Multinomial Naive Bayes is the best model with the highest accuracy for unigram features, 88.69%. For bigram features, the Stochastic Gradient Descent is the best model with the highest accuracy, 87.23%. The best model with the highest accuracy for trigram features, 86.13%, is Stochastic Gradient Descent. This research demonstrates the chance that a machine-learning strategy can reduce the risk of suicide. Hopefully, this model will serve as a guide for lowering potential suicide risk in the future. The study concludes with a summary of several practical concerns that may be considered to improve model performance.

Keywords
NLP, N-grams, Machine Learning Approaches, Social Media, Bengali Post.

References
[1] Suicide, World Health Organization, 2023. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/suicide
[2] Karen McVeigh, Facebook ‘Friends’ did not Act on Suicide Note, The Guardian, 2011. [Online]. Available: https://www.theguardian.com/technology/2011/jan/05/facebook-suicide-simone-back
[3] Andreas M. Kaplan, and Michael Haenlein, “Users of the World, Unite! The Challenges and Opportunities of Social Media,” Business Horizons, vol. 53, no. 1, pp. 59-68, 2010.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Thomas D. Ruder et al., “Suicide Announcement on Facebook,” Crisis, vol. 32, no. 5, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Shai Shalev-Shwartz, and Shai Ben-David, Understanding Machine Learning: From Theory to Algorithms, Cambridge University Press, pp. 1-397, 2014.
[Google Scholar] [Publisher Link]
[6] Juncheng Lyu, and Jie Zhang, “BP Neural Network Prediction Model for Suicide Attempt among Chinese Rural Residents,” Journal of Affective Disorders, vol. 246, pp. 465-473, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Dave Chaffey, Global Social Media Statistics Research Summary, Smartinsights, 2024, [Online]. Available: https://www.smartinsights.com/social-media-marketing/social-media-strategy/new-global-social-media-research/
[8] Number of Monthly Active Facebook Users Worldwide as of 4th Quarter 2023, Statista. [Online]. Available: https://www.statista.com/statistics/264810/number-of-monthly-active-facebookusers-worldwide/
[9] Social Media Stats Bangladesh, Statcounter, 2024. [Online]. Available: https://gs.statcounter.com/social-media-stats/all/bangladesh
[10] Bradley E. Belsher, Derek J. Smolenski, and Larry D. Pruitt, “Prediction Models for Suicide Attempts and Deaths A Systematic Review and Simulation,” JAMA Psychiatry, vol. 76, no. 6, pp. 642-651, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Pierre Lison, “An Introduction to Machine Learning,” University of Oslo, pp. 1-35, 2012.
[Google Scholar] [Publisher Link]
[12] George C. Patton et al., “Global Patterns of Mortality in Young People: A Systematic Analysis of Population Health Data,” The Lancet, vol. 374, no. 9693, pp. 881-892, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Soron Tanjir Rashid, “Decriminalizing Suicide in Bangladesh,” Asian Journal of Psychiatry, vol. 39, pp. 91-92, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Mental Health and Substance Use, World Health Organization. [Online]. Available: https://www.who.int/teams/mental-health-and-substance-use/data-research/suicide-data
[15] Sean D. Young, and Renee Garett, “Ethical Issues in Addressing Social Media Posts About Suicidal Intentions During an Online Study Among Youth: Case Study,” JMIR Mental Health, vol. 5, no. 2, pp. 1-5, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[16] David D. Luxton, Jennifer D. June, and Jonathan M. Fairall, “Social Media and Suicide: A Public Health Perspective,” American Journal of Public Health, vol. 102, no. S2, pp. S195-S200, 2012.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Rafia Tasnim et al., “Suicidal Ideation among Bangladeshi University Students Early during the COVID-19 Pandemic: Prevalence Estimates and Correlates,” Children and Youth Services Review, vol. 119, pp. 1-8, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Elizabeth D. Ballard et al., “Acute Risk Factors for Suicide Attempts and Death: Prospective Findings From the STEP-BD Study,” Bipolar Disorders, vol. 18, no. 4, pp. 363-372, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Marouane Birjali, Abderrahim Beni-Hssane, and Mohammed Erritali, “Machine Learning and Semantic Sentiment Analysis Based Algorithms for Suicide
Sentiment Prediction in Social Networks,” Procedia Computer Science, vol. 113, pp. 65-72, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Nuwan C. Hettige et al., “Classification of Suicide Attempters in Schizophrenia Using Sociocultural and Clinical Features: A Machine Learning Approach,” General Hospital Psychiatry, vol. 47, pp. 20-28, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Jun Su Jung et al., “Prediction Models for High Risk of Suicide in Korean Adolescents Using Machine Learning Techniques,” PLoS One, vol. 14, no. 6, pp. 1-12, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Seunghyong Ryu et al., “Use of a Machine Learning Algorithm to Predict Individuals with Suicide Ideation in the General Population,” Psychiatry Investigation, vol. 15, no. 11, pp. 1030-1036, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Arunima Roy et al., “A Machine Learning Approach Predicts Future Risk to Suicidal Ideation from Social Media Data,” NPJ Digital Medicine, vol. 3, no. 78, pp. 1-12, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Kasper van Mens et al., “Predicting Future Suicidal Behaviour in Young Adults, with Different Machine Learning Techniques: A Population-Based Longitudinal Study,” Journal of Affective Disorders, vol. 271, pp. 169-177, 2020.
[CrossRef] [Google Scholar] [Publisher Link]