SCCD: A Session-based Dataset for Chinese Cyberbullying Detection

TL;DR

This paper introduces SCCD, a new Chinese cyberbullying dataset with detailed comment annotations, enabling better detection methods and addressing the lack of resources in this domain.

Contribution

The creation of SCCD, a comprehensive Chinese cyberbullying dataset with fine-grained comment labels, filling a critical gap in resources for research.

Findings

Baseline methods show significant challenges in detecting cyberbullying in SCCD.

Fine-grained annotations improve understanding of comment-level cyberbullying signals.

The dataset facilitates future research in Chinese cyberbullying detection.

Abstract

The rampant spread of cyberbullying content poses a growing threat to societal well-being. However, research on cyberbullying detection in Chinese remains underdeveloped, primarily due to the lack of comprehensive and reliable datasets. Notably, no existing Chinese dataset is specifically tailored for cyberbullying detection. Moreover, while comments play a crucial role within sessions, current session-based datasets often lack detailed, fine-grained annotations at the comment level. To address these limitations, we present a novel Chinese cyber-bullying dataset, termed SCCD, which consists of 677 session-level samples sourced from a major social media platform Weibo. Moreover, each comment within the sessions is annotated with fine-grained labels rather than conventional binary class labels. Empirically, we evaluate the performance of various baseline methods on SCCD, highlighting the challenges for effective Chinese cyberbullying detection.