DaWak, the annual International Conference on Big Data Analytics and Knowledge Discovery, is a high-quality forum for researchers, practitioners and developers in the field of Big Data Analytics, in a broad sense. This year, at DaWak2020, WISS contributed with a paper co-authord by Dr Maral Dadvar and Prof. Dr. Kai Eckert on Cyberbullying Detection in Social Networks Using Deep Learning Based Models .
In this paper, the findings of recent literature on automatic detection of cyberbullying using deep-learning-based models were reproduced using the same datasets namely; Wikipedia, Twitter and Formspring, and further expanded by applying the developed methods on a new dataset collected from YouTube to investigate the performance of the models in another social media platform. This study reconfirmed that the deep-learning-based models outperform the machine-learning models previously applied to the same dataset. Since the deep-learning-based models can also benefit from integrating other sources of information, in our future work we will be looking into the impact of profile information of the users in detecting the cyberbullying in social networks.
Author: Dr. Maral Dadvar
Date: Thu, 01 Oct 2020