Hybrid deep learning model-based prediction of images related to cyberbullying

• Autorzy: Elmezain Mahmoud , Malki Amer , Gad Ibrahim , Atlam El-Sayed

Identyfikatory

DOI

10.34768/amcs-2022-0024

• Języki publikacji: EN

Abstrakty

EN

Cyberbullying has become more widespread as a result of the common use of social media, particularly among teenagers and young people. A lack of studies on the types of advice and support available to victims of bullying has a negative impact on individuals and society. This work proposes a hybrid model based on transformer models in conjunction with a support vector machine (SVM) to classify our own data set images. First, seven different convolutional neural network architectures are employed to decide which is best in terms of results. Second, feature extraction is performed using four top models, namely, ResNet50, EfficientNetB0, MobileNet and Xception architectures. In addition, each architecture extracts the same number of features as the number of images in the data set, and these features are concatenated. Finally, the features are optimized and then provided as input to the SVM classifier. The accuracy rate of the proposed merged models with the SVM classifier achieved 96.05%. Furthermore, the classification precision of the proposed merged model is 99% in the bullying class and 93% in the non-bullying class. According to these results, bullying has a negative impact on students’ academic performance. The results help stakeholders to take necessary measures against bullies and increase the community’s awareness of this phenomenon.

Słowa kluczowe

EN

cyberbullying; ResNet50; MobileNetV2; support vector machine

PL

cyberprzemoc; ResNet50; MobileNetV2; maszyna wektorów wsparcia

• Wydawca: Oficyna Wydawnicza Uniwersytetu Zielonogórskiego
• Czasopismo: International Journal of Applied Mathematics and Computer Science
• Rocznik: 2022
• Tom: Vol. 32, no. 2
• Strony: 323--334
• Opis fizyczny: Bibliogr. 39 poz., rys., tab., wykr.

Twórcy

autor

Elmezain Mahmoud

• Faculty of Science, Tanta University, Tanta 31527, Egypt
• College of Computer Science and Engineering, Taibah University, Yanbu 966144, Saudi Arabia

autor

Malki Amer

• College of Computer Science and Engineering, Taibah University, Yanbu 966144, Saudi Arabia

autor

Gad Ibrahim

• Faculty of Science, Tanta University, Tanta 31527, Egypt

autor

Atlam El-Sayed

• Faculty of Science, Tanta University, Tanta 31527, Egypt
• College of Computer Science and Engineering, Taibah University, Yanbu 966144, Saudi Arabia

Bibliografia

• [1] Abaido, G.M. (2019). Cyberbullying on social media platforms among university students in the United Arab Emirates, International Journal of Adolescence and Youth 25(1): 407–420.
• [2] Alim, S. (2015). Analysis of tweets related to cyberbullying, International Journal of Cyber Behavior, Psychology and Learning 5(4): 31–52.
• [3] Atlam, E.-S., Ewis, A., El-Raouf, M.A., Ghoneim, O. and Gad, I. (2022). A new approach in identifying the psychological impact of COVID-19 on university student’s academic performance, Alexandria Engineering Journal 61(7): 5223–5233.
• [4] Atlam, E.-S., Fuketa, M., Morita, K. and Ichi Aoe, J. (2000). Similarity measurement using term negative weight and its application to word similarity, Information Processing and Management 36(5): 717–736.
• [5] Blachnik, M. (2019). Ensembles of instance selection methods: A comparative study, International Journal of Applied Mathematics and Computer Science 29(1): 151–168, DOI: 10.2478/amcs-2019-0012.
• [6] Boulton, M.J. and Underwood, K. (1992). Bully/victim problems among middle school children, British Journal of Educational Psychology 62(1): 73–87.
• [7] Cleetus, L., Sukumar, A.R. and Hemalatha, N. (2021). Computational prediction of disease detection and insect identification using xception model, bioRxiv, DOI: 10.1101/2021.08.10.455608, (preprint).
• [8] Cortis, K. and Handschuh, S. (2015). Analysis of cyberbullying tweets in trending world events, Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business, Graz, Austria, Article no. 7, pp.1–8.
• [9] Delprato, M., Akyeampong, K. and Dunne, M. (2017). The impact of bullying on students’ learning in Latin America: A matching approach for 15 countries, International Journal of Educational Development 52: 37–57.
• [10] Devidas, S., Rao, Y.V.,S. and Rekha, N.R. (2021). A decentralized group signature scheme for privacy protection in a blockchain, International Journal of Applied Mathematics and Computer Science 31(2): 353–364, DOI: 10.34768/amcs-2021-0024.
• [11] Elmezain, M. (2016). 3D fingertip detection on multi-class support vector machine based hand gesture recognition, Kasmera 44(8): 83–89.
• [12] Elmezain, M. and Ibrahem, H.M. (2021). Retrieving semantic image using shape descriptors and latent-dynamic conditional random fields, The Computer Journal 64(12): 1876–1885.
• [13] Elmezain, M., Othman, E.A. and Ibrahim, H.M. (2021). Temporal degree-degree and closeness-closeness: A new centrality metrics for social network analysis, Mathematics 9(22): 2850.
• [14] Emine Cengil, A.C. (2019). Multiple classification of flower images using transfer learning, International Artificial Intelligence and Data Processing Symposium (IDAP), Malatya, Turkey, pp. 1–6.
• [15] Eroğlu, Y., Yildirim, M. and Çinar, A. (2021). Convolutional neural networks based classification of breast ultrasonography images by hybrid method with respect to benign, malignant, and normal using mRMR, Computers in Biology and Medicine 133, Paper ID: 104407.
• [16] Fekkes, M. (2006). Do bullied children get ill, or do ill children get bullied? A prospective cohort study on the relationship between bullying and health-related symptoms, Pediatrics 117(5): 1568–1574.
• [17] Gad, I. and Hosahalli, D. (2020). A comparative study of prediction and classification models on NCDC weather data, International Journal of Computers and Applications 44(5): 414–425.
• [18] Harjoseputro, Y., Yuda, I.P. and Danukusumo, K.P. (2020). MobileNets: Efficient convolutional neural network for identification of protected birds, International Journal on Advanced Science, Engineering and Information Technology 10(6): 2290.
• [19] Hark, K. and Turgut Özal, E.S. (2019). Extractive text summarization via graph entropy (Çizge Entropi ile Çıkarıcı Metin Özetleme), 2019 International Artificial Intelligence and Data Processing Symposium (IDAP), Malatya, Turkey, pp. 1–5.
• [20] Hellsten, L., Crespi, I., Hendry, B. and Fermani, A. (2021). Extending the current theorization on cyberbullying: Importance of including socio-psychological perspectives, Italian Journal of Sociology of Education 13(3): 85–110.
• [21] Hinton, G.E., Osindero, S. and Teh, Y.-W. (2006). A fast learning algorithm for deep belief nets, Neural Computation 18(7): 1527–1554.
• [22] Ibrahem, H.M., Elmezain, M. and Shoman, S. (2020). Adaptive image enhancement approach based on double-plateaus histogram, Journal of Theoretical and Applied Information Technology 98(10): 1675–1685.
• [23] Kibriya, S., Xu, Z.P. and Zhang, Y. (2015). The impact of bullying on educational performance in Ghana: A bias-reducing matching approach, 2015 AAEA & WAEA Joint Annual Meeting, San Francisco, USA, Paper no. 205409.
• [24] Kosciw, J.G., Palmer, N.A., Kull, R.M. and Greytak, E.A. (2012). The effect of negative school climate on academic outcomes for LGBT youth and the role of in-school supports, Journal of School Violence 12(1): 45–63.
• [25] Le, A.T., Miller, P.W., Heath, A.C. and Martin, N. (2005). Early childhood behaviours, schooling and labour market outcomes: Estimates from a sample of twins, Economics of Education Review 24(1): 1–17.
• [26] Longobardi, C., Thornberg, R. and Morese, R. (2022). Cyberbullying and mental health: An interdisciplinary perspective, Frontiers in Psychology 12, Article ID: 827106.
• [27] Malki, Z., Atlam, E.-S., Hassanien, A.E., Dagnew, G., Elhosseini, M.A. and Gad, I. (2020). Association between weather data and COVID-19 pandemic predicting mortality rate: Machine learning approaches, Chaos, Solitons & Fractals 138, Article ID: 110137.
• [28] McGuire, L. and Norman, J. (2018). Parents coping with cyberbullying: A bioecological analysis, in M. Campbell and S. Bauman (Eds), Reducing Cyberbullying in Schools, Elsevier, Amsterdam, pp. 61–72.
• [29] Mingxing Tan, Q.V.L. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks, International Conference on Machine Learning, Long Beach, USA, pp. 6105–6114.
• [30] Ponzo, M. (2013). Does bullying reduce educational achievement? An evaluation using matching estimators, Journal of Policy Modeling 35(6): 1057–1078.
• [31] Radhika, K., Devika, K., Aswathi, T., Sreevidya, P., Sowmya, V. and Soman, K.P. (2020). Performance analysis of NASNet on unconstrained ear recognition, in M. Rout et al. (Eds), Nature Inspired Computing for Data Science, Springer International Publishing, Cham, pp. 57–82.
• [32] Redi, M. and Merialdo, B. (2012). A multimedia retrieval framework based on automatic graded relevance judgments, International Conference on Multimedia Modeling, Klagenfurt, Austria, pp. 300–311.
• [33] Rui Zhao, Y.Z. and Chen, Z. (2019). Deep learning and its applications to machine health monitoring, Mechanical Systems and Signal Processing 115(3): 1568–1574.
• [34] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A. and Chen, L.-C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, pp. 4510–4520.
• [35] Sarzosa M. and Urzúa S. (2015). Bullying among Adolescents: The Role of Cognitive and Non-Cognitive Skills, National Bureau of Economic Research 5(4): 10–14.
• [36] Setiana, D. and Besar, N. (2021). ICT emerging technology impact within learning ecosystem cyberbullying among students, in P. Ordóñez de Pablos et al. (Eds), Handbook of Research on Analyzing IT Opportunities for Inclusive Digital Learning, IGI Global, Hershey, pp. 154–171.
• [37] Tripathi, K., Gupta, A.K. and Vyas, R.G. (2020). Deep residual learning for image classification using cross validation, International Journal of Innovative Technology and Exploring Engineering 9(4): 1525–1530.
• [38] Zhang, H., Liu, C., Zhang, Z., Xing, Y., Liu, X., Dong, R., He, Y., Xia, L. and Liu, F. (2021). Recurrence plot-based approach for cardiac arrhythmia classification using inception-ResNet-v2, Frontiers in Physiology 12: 1–12, Paper ID: 648950.
• [39] Zohair, Elsayed, Ewis, A., Dagnew, G., Reda, A., Elmarhomy, G., Elhosseini, M.A., Hassanien, A.E. and Gad, I. (2021). ARIMA models for predicting the end of COVID-19 pandemic and the risk of a second rebound, Neural Computing and Applications 33(7): 2929–2948.