Análisis comparativo sobre modelos de redes neuronales profundas para la detección de ciberbullying en redes sociales
Department of Computer Science and Engineering, Vignan’s Foundation for Science, Technology & Research (Deemed to be University), Vadlamudi, Guntur, A.P., India.
email: drsivadibalakrishna@gmail.com
Department of Computer Science and Engineering, Vignan’s Foundation for Science, Technology & Research (Deemed to be University), Vadlamudi, Guntur, A.P., India
email: ygopi091@gmail.com
Department of Computer Science and Engineering, CMR Institute of Technology, Hyderabad, India.
email: spesinfo@yahoo.com
Introducción: el uso de las redes sociales se ha incrementado y tiene efectos tanto positivos como negativos.
Al considerar el uso indebido de las plataformas de redes sociales a través de varios métodos de acoso cibernético, como el acecho y el acoso, debe haber métodos preventivos para controlarlos y evitar el estrés mental.
Problema: estas palabras adicionales ampliarán el tamaño del vocabulario e influirán en el rendimiento del algoritmo.
Objetivo: Detectar el ciberacoso en las redes sociales.
Metodología: en este documento, presentamos variantes de modelos de aprendizaje profundo como la memoria a largo plazo (LSTM), memoria bidireccional a largo plazo (BI-LSTM), redes neuronales recurrentes (RNN), redes neuronales recurrentes bidireccionales (BI-RNN), unidad recurrente cerrada (GRU) y unidad recurrente cerrada bidireccional (BI-GRU) para detectar el ciberacoso en las redes sociales.
Resultados: El mecanismo propuesto ha sido realizado, analizado e implementado sobre datos de Twitter con Accuracy, Precision, Recall y F-Score como medidas. Los modelos de aprendizaje profundo como LSTM, BI-LSTM, RNN, BI-RNN, GRU y BI-GRU se aplican en Twitter a los datos de comentarios públicos y se observó el rendimiento de estos modelos, obteniendo una precisión mejorada del 90,4 %.
Conclusiones: Los resultados indican que el mecanismo propuesto es eficiente en comparación con los es-quemas del estado del arte.
Originalidad: la aplicación de modelos de aprendizaje profundo para realizar un análisis comparativo de los datos de las redes sociales es el primer enfoque para detectar el ciberacoso.
Restricciones: estos modelos se aplican solo en comentarios de datos textuales. El trabajo propio no se ha concentrado en datos multimedia como audio, video e imágenes.
P.K. Smith, J. Mahdavi, M. Carvalho, S. Fisher, S. Russell, and N. Tippett, “Cyberbullying: Its nature and impact in secondary school pupils,” Journal of child psychology and psychiatry, vol.49, no. 4, pp. 376-385. doi: 10.1111/j.1469-7610.2007.01846.x
P. Sayanta, and S. Sriparna, “CyberBERT: BERT for cyberbullying identification,” Multimedia Systems, 2020, pp. 1-8. doi: https://doi.org/10.1007/s00530-020-00710-4
X. Jun-Ming, J. Kwang-Sung, Z. Xiaojin, and A. Bellmore, “Learning from bullying traces in social media,” In Proceedings of the 2012 conference of the North American chapter of the as-sociation for computational linguistics: Human language technologies, pp. 656-666. 2012. doi: https://aclanthology.org /N12-1084
V. S. Subrahmanian, and K. Srijan, “Predicting human behavior: The next frontiers,” Science, vol. 355, no. 6324, pp. 489-489. doi: 10.1126/science.aam7032
H. Lauw, J. C. Shafer, R. Agrawal, and A. Ntoulas, “Homophily in the digital world: A LiveJournal case study,” IEEE Internet Computing, vol.14, no. 2, pp. 15-23. [Online]. Available: Homophily in the Digital World: A LiveJournal Case Study (smu.edu.sg)
M.A. Al-Garadi, D. V. Kasturi, and R. Sri Devi, “Cybercrime detection in online communica-tions: The experimental case of cyberbullying detection in the Twitter network,” Computers in Human Behavior, vol.63, pp. 433-443. doi: https://doi.org/10.1016/j.chb.2016.05.051
P. Lawrence, C. Dowling, K. Shaffer, N. Hodas, and S. Volkova, “Using social media to predict the future: a systematic literature review,” arXiv preprint arXiv:1706.06134. doi: https://doi.org/10.48550/arXiv.1706.06134
S. Balakrishna, M. Thirumaran, and V. Kumar Solanki, “A Framework for IoT Sensor Data Acquisition and Analysis,” EAI Endorsed Transactions on Internet of Things, EAI, vol. 4, no. 16, pp. 1-13. doi: http://dx.doi.org/10.4108/eai.21-12-2018.159410
S. Balakrishna and M. Thirumaran, “Programming Paradigms for IoT Applications: An Exploratory Study”, In: Solanki, V. (Ed.), Díaz, V. (Ed.), Davim, J. (Ed.) Handbook of IoT and Big Data. Boca Raton: CRC Press, Taylor & Francis Group, Print. February 2019. doi: https://dx.doi.org/10.1201/9780429053290-2
S. Balakrishna, M. Thirumaran, R. Padmanaban, and V. Kumar Solanki, “An Efficient Incremental Clustering-based Improved K-Medoids for IoT Multivariate Data Cluster Analysis,” Peer-to-Peer Networking and Applications, Springer, vol.13, no.4, pp. 1152-1175. doi: https://dx.doi.org /10.1007/s12083-019-00852-x
S. Balakrishna and M. Thirumaran “Semantic Interoperability in IoT and Big Data for Health-care: A Collaborative Approach,” In: Balas V., Solanki V., Kumar R., Khari M. (eds) A Handbook of Data Science Approaches for Biomedical Engineering, Elsevier. January 2020. doi: https://dx.doi.org/10.1016/B978-0-12-818318-2.00007-6
D. J. Hemanth, and J. Anitha, “Brain signal based human emotion analysis by circular back propagation and Deep Kohonen Neural Networks,” Computers & Electrical Engineering, vol.68, pp. 170-180. doi: https://doi.org/10.1016/j.compeleceng.2018.04.006
Giap, Cu Nguyen, Le Hoang Son, and F. Chiclana, “Dynamic structural neural network,” Journal of Intelligent & Fuzzy Systems, vol. 34, no. 4, pp. 2479-2490. doi: https://doi.org/10.3233/jifs-171947
N. Kalchbrenner, E. Grefenstette, and P. Blunsom, “A convolutional neural network for mode-lling sentences,” arXiv preprint arXiv:1404.2188. (2014). doi: 10.3115/v1/P14-1062
I. Serban, A. Sordoni, Y. Bengio, A. Courville, and J. Pineau, “Building end-to-end dialo-gue systems using generative hierarchical neural network models,” In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30, no. 1. 2016. doi: https://doi.org/10.48550/arXiv.1507.04808
A. Rakhlin, “Convolutional Neural Networks for Sentence Classification,” GitHub. 2016. ht-tps://github.com/alexander-rakhlin/CNN-for-Sentence-Classification-in-Keras
R. Johnson, and T. Zhang, “Effective use of word order for text categorization with convolu-tional neural networks,” arXiv preprint arXiv:1412.1058. 2014.doi: https://doi.org/10.48550/arXiv.1412.1058
I. Sutskever, J. Martens, and G.E. Hinton, “Generating text with recurrent neural networks,” In ICML. 2011. doi: https://dl.acm.org/doi/10.5555/3104482.3104610
K. Nigam, J. Lafferty, and A. McCallum, “Using maximum entropy for text classification,” In IJCAI-99 workshop on machine learning for information filtering, vol. 1, no. 1, pp. 61-67. 1999. doi: maxent.dvi (kamalnigam.com)
L. Pengfei, X. Qiu, and X. Huang, “Recurrent neural network for text classification with multi-task learning,” arXiv preprint arXiv:1605.05101. doi: https://doi.org/10.48550/arXiv.1605.05101
A. Graves, “Generating sequences with recurrent neural networks,” arXiv preprint ar-Xiv:1308.0850. doi: https://doi.org /10.48550/arXiv.1308.0850
K. Cho, B. Van Merriënboer, D. Bahdanau, and Y. Bengio, “On the properties of neural machi-ne translation: Encoder-decoder approaches,” arXiv preprint arXiv:1409.1259. doi: https://doi.org/10.48550/arXiv.1409.1259
S. Subramani, S. Michalska, H. Wang, J. Du, Y. Zhang, and H. Shakeel, “Deep learning for mul-ti-class identification from domestic violence online posts,” IEEE Access 7, pp. 46210-46224. doi: 10.1109/ACCESS.2019.2908827
J. Risch, and R. Krestel, “Aggression identification using deep learning and data augmenta-tion,” In Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (TRAC-2018), pp. 150-158. 2018. doi: https://researchr.org /publication/RischK18-0
D. Nguyen, Kamela Ali Al Mannai, Shafiq Joty, H. Sajjad, M. Imran, and Prasenjit Mitra, “Robust classification of crisis-related data on social networks using convolutional neural networks,” In Proceedings of the International AAAI Conference on Web and Social Media, vol. 11, no. 1. 2017. doi: https://ntunlpsg.github.io/publication/2017_6/
S. Subramani, Hua Wang, Huy Quan Vu, and Gang Li, “Domestic violence crisis identifica-tion from Facebook posts based on deep learning,” IEEE access, vol. 6, pp.54075-54085. doi: 10.1109/ACCESS.2018.2871446
S. Salawu, Yulan He, and J. Lumsden, “Approaches to automated detection of cyberbullying: A survey,” IEEE Transactions on Affective Computing, vol. 11, no. 1 (2017): 3-24. doi: Transaction / Regular Paper Title (aston.ac.uk)
R. Zhao, A. Zhou, and Kezhi Mao, “Automatic detection of cyberbullying on social networks based on bullying features,” In Proceedings of the 17th international conference on distributed computing and networking, pp. 1-6. 2016. doi: https://research.aston.ac.uk/en/publications/approaches-to-automated-detection-of-cyberbullying-a-survey/fingerprints/
L. Cheng, Kai Shu, Siqi Wu, Yasin N. Silva, D. L. Hall, and Huan Liu, “Unsupervised cyberbu-llying detection via time-informed gaussian mixture model,” arXiv preprint arXiv:2008.02642. doi: arXiv:2008.02642v1
K. Kumari, Jyoti Prakash Singh, Yogesh Kumar Dwivedi, and Nripendra Pratap Rana. “Towards Cyberbullying-free social media in smart cities: a unified multi-modal approach,” Soft Computing, vol. 24, no. 15, pp. 11059-11070. doi: https://doi.org/10.1007/s00500-019-04550-x
M. A. Al-Garadi, M. Rashid Hussain, N. Khan, G. Murtaza, H. Friday Nweke, Ihsan Ali, Ghulam Mujtaba, Haruna Chiroma, H. A. Khattak, and A. Gani, “Predicting cyberbullying on social me-dia in the big data era using machine learning algorithms: Review of literature and open challenges,” IEEE Access, vol. 7, pp. 70701-70718. doi: 10.1109/ACCESS.2019.2918354
A. Kumar, and N. Sachdeva, “Multimodal cyberbullying detection using capsule network with dynamic routing and deep convolutional neural network,” Multimedia Systems, pp.1-10. doi: https://doi.org/10.1007/s00530-020-00747-5
P. Sayanta, and Sriparna Saha, “CyberBERT: BERT for cyberbullying identification,” Multimedia Systems, pp. 1-8. doi: https://doi.org/10.1007/s00530-020-00710-4
K. Kumari, and Jyoti Prakash Singh, “Identification of cyberbullying on multi-modal so-cial media posts using genetic algorithm,” Transactions on Emerging Telecommunications Technologies, vol. 32, no. 2, pp. e3907. doi: 10.1002/ett.3907
A. Muneer, and Suliman Mohamed Fati, “A Comparative Analysis of Machine Learning Techniques for Cyberbullying Detection on Twitter,” Future Internet, vol. 12, no. 11, pp. 187. doi: https://doi.org/10.3390/fi12110187
B.A. Talpur, and D. O’Sullivan, “Cyberbullying severity detection: A machine learning approach,” PloS one, vol. 15, no. 10. e0240924. doi: https://doi.org/10.1371/journal.pone.0240924
C. Iwendi, Gautam Srivastava, Suleman Khan, and Praveen Kumar Reddy Maddikunta. “Cyberbullying detection solutions based on deep learning architectures,” Multimedia Systems, pp. 1-14. doi: https://doi.org/10.1007/s00530-020-00701-5
N. Lu, Guohua Wu, Zhen Zhang, Yitao Zheng, Yizhi Ren, and Kim-Kwang Raymond Choo, “Cyberbullying detection in social media text based on character-level convolutional neural network with shortcuts,” Concurrency and Computation: Practice and Experience, vol. 32, no. 23, pp. e5627. doi: 10.1002/cpe.5627
P. Sayanta, and Sriparna Saha, “CyberBERT: BERT for cyberbullying identification,” Multimedia Systems, pp. 1-8. doi: https://doi.org/10.1007/s00530-020-00710-4
C. Van Hee, J. Gilles, C. Emmery, B. Desmet, E. Lefever, B. Verhoeven, G. Pauw, W. Daelemans, and V. Hoste, “Automatic detection of cyberbullying in social media text,” PloS one, vol. 13, no. 10, pp. e0203794. doi: 10.1371/journal.pone.0203794
D. Van Bruwaene, Qianjia Huang, and D. Inkpen, “A multi-platform dataset for detecting cy-berbullying in social media,” Language Resources and Evaluation, vol. 54, no. 4, pp. 851-874. doi: https://doi.org/10.1007/s10579-020-09488-3
H. Rosa, D. Matos, R. Ribeiro, L. Coheur, and J. P. Carvalho, “A “deeper” look at detecting cyber-bullying in social networks,” In 2018 international joint conference on neural networks (IJCNN), pp. 1-8. IEEE. doi: 10.1109/IJCNN.2018.8489211
A. Kumar, and N. Sachdeva, “Cyberbullying detection on social multimedia using soft com-puting techniques: a meta-analysis,” Multimedia Tools and Applications, vol. 78, no. 17, pp. 23973-24010. doi: https://doi.org/10.1007/s11042-019-7234-z
M. Dadvar, and Kai Eckert, “Cyberbullying detection in social networks using deep learning based models; a reproducibility study,” arXiv preprint arXiv:1812.08046. doi: https://doi.org /10.48550/arXiv.1812.08046
Derechos de autor 2022 Ingeniería Solidaria

Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
Compromiso ético y cesión de derechos
El autor debe declarar que su trabajo es original e inédito y que no se ha postulado a evaluación simultánea para su publicación por otro medio. Además, debe asegurar que no tiene impedimentos de ninguna naturaleza para la concesión de los derechos previstos en el contrato.
El autor se compromete a esperar el resultado de evaluación de la revista Ingeniería Solidaria, antes de considerar su presentación a otro medio; en caso de que la respuesta de publicación sea positiva, adicionalmente, se compromete a responder por cualquier acción de reivindicación, plagio u otra clase de reclamación que al respecto pudiera sobrevenir por parte de terceros.
Asimismo, debe declarar que, como autor o coautor, está de acuerdo por completo con los contenidos presentados en el trabajo y ceder todos los derechos patrimoniales, es decir, su reproducción, comunicación pública, distribución, divulgación, transformación, puesta a disposición y demás formas de utilización de la obra por cualquier medio o procedimiento, por el término de su protección legal y en todos los países del mundo, al Fondo Editorial de la Universidad Cooperativa de Colombia, de manera gratuita y sin contraprestación presente o futura.