The Study into cyberbullying identification has expanded as of years, due to some portion to the multiplication of cyberbullying crosswise over internet-based life and its adverse impact on youngsters. An emerging collection of work is rising on mechanized ways to deal with cyberbullying identification. These methodologies use machine learning and natural language processing techniques to distinguish the attributes of a cyber bullying trade and naturally identify cyberbullying by matching textual data to the identified traits.Based on our general literature review, we arrange existing methodologies into 4 primary classes, (a) Supervised learning-based approaches typically use classifiers such as SVM and Naïve Bayes to develop predictive models for cyberbullying detection. (b) Lexicon based systems utilize word lists and use the presence of words within the lists to detect cyberbullying. (c) Rules-based approaches match text to predefined rules to identify bullying and (d) mixed-initiatives approaches combine human-based reasoning with one or more of the aforementioned approaches. We discovered absence of value agent named datasets and non-holistic thought of cyberbullying by study when creating location frameworks are two key challenges facing cyberbullying detection study. This paper basically maps out the best in class in cyberbullying discovery research and fills in as an asset for specialists to figure out where to best direct their future research endeavor’s in this field.

Machine Learning, Natural Language Processing Techniques, SVM, Navie Bayes

[1] Cynthia Van Hee, Gilles Jacobs, Chris Emmery, Bart Desmet, Els Lefever, Ben Verhoeven, Guy De Pauw, Walter Daelemans, Veronique Hoste, “Automatic Detection of Cyberbullying in Social Media Text”, arXiv:1801.05617v1 [cs.CL], 17 jan 2018.
[2] Semiu Salawu, Yulan He, Joanna Lemsden,“Approaches to Automated Detection of Cyberbullying: A Survey”, IEEE Transactions on effective Computing, ISSN: 1949-3045, October, 2017.
[3] Nikita Hatwar, Ashwini Patil, Diksha Gondane, “AI Based Chatbot”, International Journal of Emerging Trends in Engineering and Basic Sciences (IJEEBS), ISSN (Online) 2349-6967, Volume 3, PP.85-87, Issue 2 (March-April 2016).
[4] Noora AI Mutawa, Joanne Bryce, Virgina N.L. Franqueira, Andrew Marrington, “Forensic investigation of cyberstalking cases using Behavioral Evidence Analysis” DFRWS 2016 Europe; Volume 16, Supplement, Pages S96-S103, 29 March 2016.
[5] Zinnar Ghasem, Ingo Frommholz, Carsten Maple (2015),“A Machine Learning Framework to Detect And Document Text-based Cyberstalking”, R. Bergmann, S. Gorg, G. Muller (Eds.): Proceedings of the LWA 2015 Workshops: KDML, FGWM, IR, and FGDB. Trier, Germany, 7.-9. October 2015, published at http://ceur-ws.org
[6] Zinnar Ghasem, Ingo Frommholz, Carsten maple (2015),“Machine Learning Solutions for controlling Cyberbullying and Cyberstalking”, vol : 7-9, 2015.
[7] Rekha Sugandhi, Anurag Pande, Siddhant Chawla, Abhishek Agrawal, Husen Bhagat,“Methods for detection of cyberbullying : A survey”,Intelligent Systems Design and Applications (ISDA), 2015.
[8] Dadvar, M., Ordelman, R., Jong, F. D. (2012). Trieschnigg. D. “Towards User Modelling in the Combat against Cyberbullying, in Natural Language Processing and Information Systems”, Springer-Verlag Berlin Heidelberg, 277–283, 2012.
[9] Dinakar, K,“Modeling the Detection of Textual Cyberbullying”, in The Social Mobile Web, 11–17. 2011.
[10] Ingo Frommholz, Haider M. al-Khateeb, Martin Potthast, Zinnar Ghasem, Mitul Shukla, Emma Short,“Textual Analysis and Machine Learning for Cyberstalking Detection”, 2009.