Advanced search
Add to list

Proof-of-concept experiments for the fine-grained classification of cyberbullying events

Author
Organization
Project
  • LT3
Abstract
In the current era of online interactions, both positive and negative experiences are abundant on the web. As in real life, these negative experiences can have a serious impact on youngsters. Recent research reports cybervictimization rates among teenagers between 3% and 24% (Olweus, 2012; Hinduja & Patchin, 2012). In the research project AMiCA, we strive to automatically detect harmful content such as cyberbullying on social networks. We collected data from social networking sites and by simulating cyberbullying events with volunteer youngsters. This dataset was annotated for a number of fine-grained categories related to cyberbullying such as insults and threats. More broadly, the severity of cyberbullying, as well as the author's role (harasser, victim or bystander) were defined. We present the results of our preliminary experiments where we try to determine whether an online message is part of a cyberbullying event. Moreover, we explore the feasibility to classify online posts in five more fine-grained categories. For the binary classification task of cyberbullying detection, we obtain an F-score of 54.71%. F-scores for the more fine-grained classification tasks vary between 20.51% and 55.07%.

Citation

Please use this url to cite or link to this publication:

MLA
Van Hee, Cynthia, Ben Verhoeven, Els Lefever, et al. “Proof-of-concept Experiments for the Fine-grained Classification of Cyberbullying Events.” Computational Linguistics in the Netherlands. 2015. Print.
APA
Van Hee, C., Verhoeven, B., Lefever, E., De Pauw, G., Hoste, V., & Daelemans, W. (2015). Proof-of-concept experiments for the fine-grained classification of cyberbullying events. Computational Linguistics in the Netherlands. Presented at the Computational Linguistics in the Netherlands (CLIN25).
Chicago author-date
Van Hee, Cynthia, Ben Verhoeven, Els Lefever, Guy De Pauw, Veronique Hoste, and Walter Daelemans. 2015. “Proof-of-concept Experiments for the Fine-grained Classification of Cyberbullying Events.” In Computational Linguistics in the Netherlands.
Chicago author-date (all authors)
Van Hee, Cynthia, Ben Verhoeven, Els Lefever, Guy De Pauw, Veronique Hoste, and Walter Daelemans. 2015. “Proof-of-concept Experiments for the Fine-grained Classification of Cyberbullying Events.” In Computational Linguistics in the Netherlands.
Vancouver
1.
Van Hee C, Verhoeven B, Lefever E, De Pauw G, Hoste V, Daelemans W. Proof-of-concept experiments for the fine-grained classification of cyberbullying events. Computational Linguistics in the Netherlands. 2015.
IEEE
[1]
C. Van Hee, B. Verhoeven, E. Lefever, G. De Pauw, V. Hoste, and W. Daelemans, “Proof-of-concept experiments for the fine-grained classification of cyberbullying events,” in Computational Linguistics in the Netherlands, Antwerp, Belgium, 2015.
@inproceedings{7197487,
  abstract     = {In the current era of online interactions, both positive and negative experiences are abundant on the web. As in real life, these negative experiences can have a serious impact on youngsters. Recent research reports cybervictimization rates among teenagers between 3% and 24% (Olweus, 2012; Hinduja & Patchin, 2012). In the research project AMiCA, we strive to automatically detect harmful content such as cyberbullying on social networks. We collected data from social networking sites and by simulating cyberbullying events with volunteer youngsters. This dataset was annotated for a number of fine-grained categories related to cyberbullying such as insults and threats. More broadly, the severity of cyberbullying, as well as the author's role (harasser, victim or bystander) were defined. We present the results of our preliminary experiments where we try to determine whether an online message is part of a cyberbullying event. Moreover, we explore the feasibility to classify online posts in five more fine-grained categories. For the binary classification task of cyberbullying detection, we obtain an F-score of 54.71%. F-scores for the more fine-grained classification tasks vary between 20.51% and 55.07%.},
  author       = {Van Hee, Cynthia and Verhoeven, Ben and Lefever, Els and De Pauw, Guy and Hoste, Veronique and Daelemans, Walter},
  booktitle    = {Computational Linguistics in the Netherlands},
  language     = {eng},
  location     = {Antwerp, Belgium},
  title        = {Proof-of-concept experiments for the fine-grained classification of cyberbullying events},
  year         = {2015},
}