CyDeBoost: A SHAP-Guided Boosting Strategy Framework for Cyberbullying Detection through Mistake-Driven Learning

The widespread use of online social media has increased the urgency of detecting and mitigating harmful language, such as cyberbullying. Traditional detection systems often struggle with semantically ambiguous and context-dependent expressions, leading to frequent misclassifications. This article presents CyDeBoost, a mistake-driven boosting framework for cyberbullying detection. The core idea of CyDeBoost is to identify and learn from misclassified instances by leveraging SHAP (SHapley Additive exPlanations) to uncover key lexical features responsible for prediction errors. Based on these insights, the framework uses large language models to generate semantically contrastive augmented samples, which are then used to fine-tune the model through a modular continual learning strategy. Specifically, lightweight adapter modules are stacked iteratively to simulate the boosting process while mitigating catastrophic forgetting. Experimental results demonstrate that CyDeBoost improves classification robustness across multiple cyberbullying categories and maintains generalization under low-resource settings. This framework aligns with the goals of content moderation on dynamic web platforms by offering interpretable, adaptive, and resource-efficient language safety solutions.

Authors

Institutions

Publication Details

Journal
ACM Transactions on the Web
Published
2026-11-18
DOI
https://doi.org/10.1145/3831585
Citations
1
Primary Topic
Hate Speech and Cyberbullying Detection
Type
article
Field-Weighted Citation Impact
0.97
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

CyDeBoost: A SHAP-Guided Boosting Strategy Framework for Cyberbullying Detection through Mistake-Driven Learning

Yao-Chung Fan, Shih-Wei Guo, Yao-Chung Fan
1 citations
ACM Transactions on the Web
Hate Speech and Cyberbullying Detection
0.97
article

CyDeBoost: A SHAP-Guided Boosting Strategy Framework for Cyberbullying Detection through Mistake-Driven Learning

Yao-Chung Fan, Shih-Wei Guo, Yao-Chung Fan
article en
1 citations

Abstract

The widespread use of online social media has increased the urgency of detecting and mitigating harmful language, such as cyberbullying. Traditional detection systems often struggle with semantically ambiguous and context-dependent expressions, leading to frequent misclassifications. This article presents CyDeBoost, a mistake-driven boosting framework for cyberbullying detection. The core idea of CyDeBoost is to identify and learn from misclassified instances by leveraging SHAP (SHapley Additive exPlanations) to uncover key lexical features responsible for prediction errors. Based on these insights, the framework uses large language models to generate semantically contrastive augmented samples, which are then used to fine-tune the model through a modular continual learning strategy. Specifically, lightweight adapter modules are stacked iteratively to simulate the boosting process while mitigating catastrophic forgetting. Experimental results demonstrate that CyDeBoost improves classification robustness across multiple cyberbullying categories and maintains generalization under low-resource settings. This framework aligns with the goals of content moderation on dynamic web platforms by offering interpretable, adaptive, and resource-efficient language safety solutions.

ACM Transactions on the WebVol. 21(1)
National Chung Hsing University (TW), Feng Chia University (TW), National Taipei University (TW)
Openalex Percentile: Top 23%
Hate Speech and Cyberbullying Detection
0.97
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon