Speaker: Dr Vinita Nahar (University of Wolverhampton, UK)
Date: 02 December 2014
Cyberbullying is widely regarded as a serious social menace which affects millions of people around the world, especially teenagers and adolescents. In the worst case scenario, cyberbullying activities result in the suicidal attempts by the victims. In this presentation, I will present the outcomes of my PhD work “On Detection of Cyberbullying in Social Networks”. The current studies on cyberbullying detection are largely constrained by a static nature. These are summarised into three categories: (i) manual labelling; (ii) keyword-based or rule-based approaches; and (iii) survey based approaches. However, due to the scarcity of labelled training data, most of the existing approaches remain impractical in the real world situation. In this research, we (i) identified subsistent problems and challenges in cyberbullying detection in streaming text; (ii) developed effective solutions to address the problems; and (iii) evaluated the proposed approaches in real-world streaming datasets.