You are here

Xu, Jun-Ming; Kwang-Sung Jun; Xiaojin Zhu; and Amy Bellmore. Learning from bullying traces in social media. In Proceedings of the 2012 Conference of North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT), Montreal, Canada, 2012, pp.656-666.

The authors describe their use of a variety of natural language processing techniques to identify bullying traces (a new concept that refers to online references that can be bullying instances themselves or online references that refer to offline instances of bullying). They also use sentiment analysis features to identify bullying roles and Latent Dirichlet Analysis to identify topics/themes. The paper is designed to set baselines for a variety of tasks pertaining to bullying detection and a call for other researchers to improve upon these baseline techniques. The training data is available at: http://research.cs.wisc.edu/bullying.