Cyber Bullying Detection and Classification using Multinomial Naïve Bayes and Fuzzy Logic

Full Text (PDF, 411KB), PP.1-12

Views: 0 Downloads: 0


Arnisha Akhter 1 Uzzal K. Acharjee 1 Md Masbaul A. Polash 1

1. Jagannath University, Dhaka-1100, Bangladesh

* Corresponding author.


Received: 3 Jul. 2019 / Revised: 20 Jul. 2019 / Accepted: 11 Aug. 2019 / Published: 8 Nov. 2019

Index Terms

Cyber Bullying, Multinomial naïve bayes classifier, Support vector machine, Fuzzy logic.


The advent of different social networking sites has enabled people to easily connect all over the world and share their interests. However, Social Networking Sites are providing opportunities for cyber bullying activities that poses significant threat to physical and mental health of the victims. Social media platforms like Facebook, Twitter, Instagram etc. are vulnerable to cyber bullying and incidents like these are very common now-a-days. A large number of victims may be saved from the impacts of cyber bullying if it can be detected and the criminals are identified. In this work, a machine learning based approach is proposed to detect cyber bullying activities from social network data. Multinomial Naïve Bayes classifier is used to classify the type of bullying. With training, the algorithm classifies cyber bullying as- Shaming, Sexual harassment and Racism. Experimental results show that the accuracy of the classifier for considered data set is 88.76%. Fuzzy rule sets are designed as well to specify the strength of different types of bullying.

Cite This Paper

Arnisha Akhter, Uzzal K. Acharjee, Md Masbaul A. Polash," Cyber Bullying Detection and Classification using Multinomial Naïve Bayes and Fuzzy Logic", International Journal of Mathematical Sciences and Computing(IJMSC), Vol.5, No.4, pp.1-12, 2019. DOI: 10.5815/ijmsc.2019.04.01


[1]The daily star: 

[2]Kids health:

[3]J. B.Sri Nandhini, “Online social network bullying detection using intelligence techniques", Advanced Computing Technologies and Applications, Procedia Computer Science, vol. 1215, pp. 485{492, 2015.

[4]Hosseinmardi, Homa, A. Mattson, Sabrina, Ra_q, R. Ibn, Han, Richard, L. Qin, Mishra, and Shivakant, “Detection of cyberbullying incidents on the instagram social network." 2015. 

[5]R. O. M. Dadvar, F. d. Jong and D. Trieschnigg, “Improved cyberbullying detection using gender information", Twelfth Dutch-Belgian Information Retrieval Workshop, pp. 23-25, 2012. 

[6]Charles E. Notar , Sharon Padgett, Jessica Roden, “Cyberbullying: A Review of the Literature" Universal Journal of Educational Research 1(1): 1-9, 2013. 

[7]I. McGhee, J. Bayzick, A. Kontostathis, L. Edwards, A. Mcbride, , and E. Jakubowski, “Learning to identify internet sexual predation," International Journal on Electronic Commerce 2011, vol. 15, pp. 103-122, 2011. 

[8]H. Hosseinmardi, S. A. Mattson, R. IbnRa_q, R. Han, Q. Lv, and S. Mishra, “Detection of cyberbullying incidents on the instagram social net-work," 2015. 

[9]K. Dinakar, R. Reichart, and H. Lieberman, “Modeling the detection of textual cyberbullying," 2011.

[10]K. Reynolds, A. Kontostathis, and L. Edwards, “Using machine learning to detect cyberbullying," Machine Learning and Applications and Workshops (ICMLA), vol. 2, pp. 241-244, 2011. 

[11]K. D. Gorro, M. J. G. Sabellano, K. Gorro, C.Maderazo, and K. Capao, “Classification of cyberbullying in facebook using selenium and svm," 3rd International Conference on Computer and Communication Systems, pp. 183-186, 2018.

[12]V. Nandakumar, B. C. Kovoor, and S. M. U, “Cyberbulling revelation in twitter data using naive bayes classifier algorithm," International Journal of Advanced Research in Computer Science, vol. 2, pp. 511{513, 



[14]Scikit learn: evaluation.html.