English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The detection of online cyberbullying has seen an increase in societalimportance, 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 ofstate-of-the-art techniques. Consequently, much of the recent research usessmall, heterogeneous datasets, without a thorough evaluation of applicability.In this paper, we further illustrate these issues, as we (i) evaluate manypublicly available resources for this task and demonstrate difficulties withdata collection. These predominantly yield small datasets that fail to capturethe required complex social dynamics and impede direct comparison of progress.We (ii) conduct an extensive set of experiments that indicate a general lack ofcross-domain generalization of classifiers trained on these sources, and openlyprovide this framework to replicate and extend our evaluation criteria.Finally, we (iii) present an effective crowdsourcing method: simulatingreal-life bullying scenarios in a lab setting generates plausible data that canbe effectively used to enrich real data. This largely circumvents therestrictions on data that can be collected, and increases classifierperformance. We believe these contributions can aid in improving the empiricalpractices of future research in the field.

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