• ISSN: 2010-3646
    • Abbreviated Title: Int. J. Social. Scienc. Humanit.
    • Frequency: Bimonthly (2011-2014); Monthly (2015-2018); Quarterly (Since 2019)
    • DOI: 10.18178/IJSSH
    • Editor-in-Chief: Prof. Aurica Briscaru
    • Executive Editor: Mr. Ron C. Wu
    • Abstracting/ Indexing: Google Scholar, Index Copernicus, Crossref, Electronic Journals Library
    • E-mail: ijssh@ejournal.net
IJSSH 2018 Vol.8(9): 255-260 ISSN: 2010-3646
doi: 10.18178/ijssh.2018.V9.970

Predicting Risk of Being Victims of Bullying for High School Students using Artificial Neural Network

Ziyue Zhang
Abstract—This study aims to 1) examine the predictors of the victims of bullying at high school 2) build a predictive model for victims of bullying using artificial neural network and compare its performance to logistic regression model. Youth Risk Behavior Surveillance System (YRBSS) 2015 data were used for this study. The YRBSS was developed in 1990 to monitor priority health risk behaviors that contribute markedly to the leading causes of death, disability, and social problems among youth and adults in the United States. All the participants who were eligible were randomly assigned into 2 groups: training sample and testing sample. Two models were built using training sample: artificial neural network and logistic regression, and later used to predict the risk of being victims of bullying in the testing sample. Receiver operating characteristic (ROC) were calculated and compared for these two models for their discrimination capability and a curve using predicted probability versus observed probability were plotted to demonstrate the calibration measure for these two models. In this study, we identified several important predictors for being a victim of bullying at high school e.g., sex orientation, smoking, drinking, or being Hispanic or Latino. This provided important information for educators as well as parents provide timely intervention. We built a predictive model using artificial neural network as well as logistic regression to provide a tool for early detection. As to performance of these two models, logistic regression had a better discriminating capability as well as a better calibration between predicted probability and observed probability.

Index Terms—Bully, attempt to intimidate someone with strength, logistic model, regression model with categorical dependent variable, predictive model, process predicting outcome using data mining, variable, factor affecting risks of being victims.

Ziyue Zhang is with Peddie School, USA (e-mail: ziyuezhang2000@outlook.com).


Cite: Ziyue Zhang, "Predicting Risk of Being Victims of Bullying for High School Students using Artificial Neural Network," International Journal of Social Science and Humanity vol. 8, no. 9, pp. 255-260, 2018.

Copyright © 2008-2019. International Journal of Social Science and Humanity. All rights reserved.
E-mail: ijssh@ejournal.net