Detection of Cyberbullying using Voting Classifier
DOI:
https://doi.org/10.26438/ijcse/v8i5.5360Keywords:
Cyberbullying, Machine Learning, Classification, Voting classifier, Social MediaAbstract
The advent of social media has changed the ways of human communication. It has brought people around the world closer to each other. Despite its innumerable benefits, social media is considered to be one of the harmful elements of society. Cyberbullying and online harassment are the most common negative effects of social media. Cyberbullying is a way of bullying someone with the use of technology and it can take place through many forms such as SMS, Apps, online gaming, social networking sites online forums, etc. The project aims at detecting cyberbullying content based on textual features. The system detects various language patterns often used by bullies. This is accomplished using machine learning. The proposed system uses voting classifier to classify the input text as „Bullying‟ or „Non-Bullying‟. It also compares the accuracies of various classifiers and introduces a framework of supervised machine learning to detect cyberbullying in textual data. It is observed that a voting classifier i.e. a combination of the Logistic Regression, Random Forest, Support Vector Machine, SGD classifier gives the highest accuracy and precision i.e. 74% and 77% respectively. This trained model is deployed on a webpage which makes the system user intuitive and user-friendly.
References
[1] L. Cheng, J. Li, Y. N. Silva, D. L. Hall, and H. Liu, "XBully: Cyberbullying Detection within a Multi-Modal Context.", WSDM 2019, pp. 339-347, 2019.
[2] R. I. Rafiq, H. Hosseinmardi, R. Han, Q. Lv, and S. Mishra, "Scalable and timely detection of cyberbullying in online social networks", In Proceedings of the 33rd Annual ACM Symposium on Applied Computing, ACM, pp. 1738-1747, 2018.
[3] R. Zhao, and K. Mao, "Cyberbullying detection based on semantic-enhanced marginalized denoising auto-encoder.", IEEE Transactions on Affective Computing , Vol.8, Issue.3, pp. 328-339, 2016.
[4] M. A. Al-garadi, K. D. Varathan, and S. D. Ravana, "Cybercrime detection in online communications: The experimental case of cyberbullying detection in the Twitter network.", Computers in Human Behavior, Vol.63, pp. 433-443, 2016.
[5] A. Mangaonkar, A. Hayrapetian, and R. Raje, "Collaborative detection of cyberbullying behavior in Twitter data.”, 2015 IEEE International Conference on Electro/Information Technology (EIT), pp. 611-616, 2015.
[6] V. Nahar, X. Li, H. L. Zhang, and C. Pang, "Detecting cyberbullying in social networks using multi-agent system." Web Intelligence and Agent Systems: An International Journal, Vol.12, Issue.4, pp. 375-388, 2014.
[7] K. Reynolds, A. Kontostathis, and L. Edwards, "Using machine learning to detect cyberbullying.”, In 2011 10th International Conference on Machine learning and applications and workshops, IEEE, Vol.2, pp. 241-244, 2011.
[8] K. Dinakar, R. Reichart, and H. Lieberman, "Modeling the detection of textual cyberbullying.", In fifth international AAAI conference on weblogs and social media, 2011.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
