Current Limitations in Cyberbullying Detection: on Evaluation Criteria, Reproducibility, and Data Scarcity

Chris Emmery*, Ben Verhoeven, Guy De Pauw, Gilles Jacobs, Cynthia Van Hee, Els Lefever, Bart Desmet, Véronique Hoste, Walter Daelemans

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

Abstract

The detection of online cyberbullying has seen an increase in societal importance, popularity in research, and available open data. Nevertheless, while computational power and affordability of resources continue to increase, the access restrictions on high-quality data limit the applicability of state-of-the-art techniques. Consequently, much of the recent research uses small, heterogeneous datasets, without a thorough evaluation of applicability. In this paper, we further illustrate these issues, as we (i) evaluate many publicly available resources for this task and demonstrate difficulties with data collection. These predominantly yield small datasets that fail to capture the required complex social dynamics and impede direct comparison of progress. We (ii) conduct an extensive set of experiments that indicate a general lack of cross-domain generalization of classifiers trained on these sources, and openly provide this framework to replicate and extend our evaluation criteria. Finally, we (iii) present an effective crowdsourcing method: simulating real-life bullying scenarios in a lab setting generates plausible data that can be effectively used to enrich real data. This largely circumvents the restrictions on data that can be collected, and increases classifier performance. We believe these contributions can aid in improving the empirical practices of future research in the field.
Original languageEnglish
Number of pages37
JournalLanguage Resources and Evaluation
Early online date25 Oct 2019
DOIs
Publication statusPublished - 16 Nov 2020

Keywords

  • cyberbullying detection
  • cybersecurity
  • machine learning
  • benchmarking
  • resource evaluation
  • cross-domain
  • reproducibility
  • crowdsourcing

Fingerprint Dive into the research topics of 'Current Limitations in Cyberbullying Detection: on Evaluation Criteria, Reproducibility, and Data Scarcity'. Together they form a unique fingerprint.

  • Automatic detection of cyberbullying in social media text

    Van Hee, C., Jacobs, G., Emmery, C., Desmet, B., Lefever, E., Verhoeven, B., De Pauw, G., Daelemans, W. & Hoste, V., 8 Oct 2018, In : PLoS ONE. 13, 10, p. e0203794 22 p., 0203794.

    Research output: Contribution to journalArticleScientificpeer-review

    Open Access
    45 Citations (Scopus)

Cite this