a new Chinese Weibo comments dataset collected from Sina Weibo comment specifically for cyberbullying detection
A Weibo comment is labeled as bullying if it
- uses a sexist, racial or geographical slur.
- uses swear words or humiliation to blame someone without a well founded argument.
- blatantly misrepresents truth or seeks to distort views on a minority with unfounded claims.
- expresses a tendency to violence or curse on a minority.
- contains attacks on appearance, body or family members.
- is one of repeated negative comments, or call others to join the attack.
- imposes a nickname that others are unwilling to accept or insulting.
PLEASE CITE:
Nijia Lu, Guohua Wu, Zhen Zhang, Yitao Zheng, Yizhi Ren, Kim-Kwang Raymond Choo (2019), Cyberbullying Detection in Social Media Text Based on Character-level Convolutional Neural Networks with Shortcuts
email:lunijia@hdu.edu.cn
Thanks: B. Zhang, Y. Wang, J. Zhong, X. Fan