The week's pick
Reseach Article
Detecting Self-harm Content and Behavior in Tweets with SVM and Ensemble Classifiers: A Comparative Study
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 186 - Number 43 |
| Year of Publication: 2024 |
| Authors: Divya Dewangan, Smita Selot, Sreejit Panicker |
10.5120/ijca2024924044
|
Divya Dewangan, Smita Selot, Sreejit Panicker . Detecting Self-harm Content and Behavior in Tweets with SVM and Ensemble Classifiers: A Comparative Study. International Journal of Computer Applications. 186, 43 ( Sep 2024), 21-32. DOI=10.5120/ijca2024924044
Abstract
Suicide is a mental state when the person loses the will to live, and it is a crucial issue nowadays. A person who is at suicidal risk needs early detection and medication. Researchers have exposed that many people relish posting their emotions and thoughts on social networking sites. In the past few years, Support Vector Machine (SVM) has been one of the most capable and vigorous classifiers in many fields of applications. Few areas where SVMs do not perform well have impelled the advancement of other applications, to enhance the strength of classifiers and parameters. Researchers from various disciplines have considered and explored the use of combination methodology. The idea of combination methodology is to build a prediction model by an ensemble of multiple methods. The main intention of this study is to develop and evaluate a model for suicidal content and behavior detection using the Support Vector Machine and Ensemble Classifiers such as Random Forest classifier, XGBoosting Classifier, and Stacking classifier. This paper summarized a brief introduction of SVM and Ensemble classifier. In this study, different Feature Extraction techniques, and their combinations have been used to train the models, and the accuracy and the performance of the models are analyzed. The findings highlight the substantial potential of the SVM and Ensemble classifier for accurately predicting suicidal content and behavior.
References
- World Health Organization, Suicide; 2023 https://www.who.int/news-room/fact-sheets/detail/suicide. Accessed on 11 December 2023
- National Mental Health Survey of India, Prevalence, Patterns and Outcomes, Supported by Ministry of Health and Family Welfare, Government of India, and Implemented by National institute of Mental Health and Neurosciences (NIMHANS) Bengaluru: In Collaboration with Partner Institutions; 2015-2016: https://aiimsbhopal.edu.in/AIIMSFiles/officialDownload/nmhs.pdf..
- Burnap, P., Colombo, G., Amery, R., Hodorog, A. and Scourfield, J. 2017. Multi-class machine classification of suicide-related communication on twitter. Online Social Networks and Media, 2: 32-44.
- Cervantes, J., Garcia-Lamont, F., Rodríguez-Mazahua, L. and Lopez, A. 2019. A comprehensive survey on support vector machine classification: Applications, challenges and trends. Neurocomputing.
- Chadha, A. and Kaushik, B. (2019) A Survey on Prediction of Suicidal Ideation Using Machine and Ensemble Learning. The British Computer Society. Computational Intelligence, Machine learning and Data Analytics, the Computer Journal.
- Kaslow, N. J. 2014. Suicidal Behavior in Children and Adolescents-[APA]. Available at: https://www.apa.org/about/governance/president/suicidal-behavior-adolescents.pdf.Accessed: 21December2023.
- Dewangan, D., Selot, S. and Panicker, S. 2023. The accuracy analysis of Different Machine Learning Classifiers for Detecting Suicidal Ideation and Content. Asian Journal of Electrical Sciences, 12(1):46-56.
- Littilefield, A. K., Cooke, J. T., Bagge, C. L., Glenn, C. R., Kleiman, E. M., Jacobucci, R., Millner, A. J. and Steinley, D. 2021. Machine learning to classify Suicidal Thoughts and Behaviors: Implementation within the Common Data Elements Used by the Military Suicide Research Consortium. Clinical Psychological Science, 9(3):467-481.
- Ghosal, S. and Jain, A. 2023. Depression and Suicide Risk Detection on Social Media using FastText Embedding and XGBoost classifier. In Proceedings of International Conference on Machine Learning and Data Engineering, Procedia Computer Science, 2023, 218:1631-1639.
- Su, C., Aseltine, R., Doshi, R., Chen, K., Rogers, S. C. and Wang, F. 2020. Machine learning for suicide risk prediction in children and adolescents with electronic health records. Translation Psychiatry, 10(413).
- Lekkas, D., Klein, R. J. and Jacobson, N. C. 2021. Predicting acute suicidal ideation on instagram using ensemble machine learning models. Internet Interventions, 25(100424).
- Gandhi, A. 2021. Topic Modeling with LSA, PLSA, LDA & lda2Vec: Nanonets; 2021 https://nanonets.com/blog/topic-modeling-with-lsa-plsa-lda-lda2vec/#lda-in-deep-learning-lda2vec.
- Macalli, M., Navarro, M., Orri, M., Tournier, M., Thiébaut, R., Cٛté, S. M. and Tzourio, C. A. 2021. machine learning approach for predicting suicidal thought and behaviors among college students. Scientific Reports, 11(11363).
- Mahmud, S., Mohsin, M., Muyeed, A., Nazneen, S., Sayed, A., Murshed, N. and Tonmon, T. T. 2023. Islam A. Machine learning approaches for predicting suicidal behaviors among university students in Bangladesh during the COVID-19 pandemic-A cross-sectional study. Medicine, 102(28).
- Alexandropoulos, S. A. N., Aridas, C. K., Kotsiantis, S. B. and Vrahatis, M. N. 2019. Stacking Strong Ensembles of Classifier. In Proceedings of the International federation for Information Processing, 559:545-556.
- Ngo-Yel, T. and Dutt, A. 2009. A Study on Efficacy of Ensemble Methods for Classification Learning. In Proceedings of International Conference on Information Systems, Procedia ICIS 2009 Proceedings.
- Rabani, S. T., Khanday, A. M. U. D., Khan, Q. R., Hajam, U. A., Imran, A. S. and Kastrati, Z. 2023. Detecting suicidality on social meadia: Machine learning at rescue. Informatics Journal, 24:291-302.
- Rokach, L. 2010. Ensemble-based Classifiers. Artif Intell Rev, 33:1-39. DOI: 10.1007/s10462-009-9124-7.
- Selot, S. and Panicker, S. 2021. Comparative performance of Random Forest and Support vector Machine on Sentiment Analysis of Reviews of Indian Tourism. IT in Industry, 9(2).
- Salehi, M., Ghahari, S., Hosseinzadeh, M. and Ghalichi, L. 2023. Domestic violence risk prediction in Iran using a machine learning approach by analyzing Persian Textual content in social media. Heliyon, Vol. 9.
- Song, S., Hong, H. T., Lee, C. and Lee, S. B. 2022. A Machine learning approach for predicting suicidal ideation in post stroke patients. Scientific Reports, 12(15906).
- Chatterjee, M., Kumar, P., Samanta, P. and Sarkar, D. 2022. Suicide ideation detection from online social media: A multi-modal feature based technique, International Journal of Information Management Data Insights, 2(2).
- Al-Zahrani, F. A., Abdulrazak, L. F., Ali, M. M., Islam, M. N. and Ahmad, K. 2023. StackDPP: Stacking-Based Explainable Classifier for Depression prediction and Finding the risk Factors among Clinicians. Egyptian, Bioengineering, 10:858.
- Wu, Q. and Zhou, D. X. 2006. Analysis of support vector machine classification. Journal of Computational Analysis and Applications.
Index Terms
Keywords