Summary
This 2023 peer-reviewed study presents a curated dataset designed to advance cyberbullying detection systems by incorporating multiple behavioural and linguistic dimensions—aggressive language, repetition, peer dynamics, and demonstrated intent to harm. Published in Computers in Human Behavior, the work contributes to the growing field of automated harmful content identification by providing structured training data that captures the multifaceted nature of cyberbullying as a social phenomenon. The dataset and associated findings are intended to support more comprehensive machine learning approaches to online safety.
Regional applicability
This paper addresses online safety and cyberbullying detection—a policy area relevant across jurisdictions including the United Kingdom, where online harm regulation (Online Safety Bill / Online Safety Act 2023) increasingly emphasises platform accountability. The dataset and methods may have application value for UK-based researchers and safety technology developers working on harmful content detection.
Key measures
Dataset annotation for aggressive texts, repetition markers, peerness indicators, and intent to harm; classification performance metrics for cyberbullying detection models
Outcomes reported
The study developed and evaluated a dataset for cyberbullying detection that incorporates multiple linguistic and contextual features including aggressive language, repetition patterns, peer relationships, and intent to harm. The research appears to report classification performance metrics for automated cyberbullying identification.
Topic tags
Dig deeper with Pulse AI.
Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.