Topic adversarial neural network for cross-topic cyberbullying detection

With the proliferation of social media, cyberbullying has emerged as a pervasive threat, causing significant psychological harm to individuals and undermining social cohesion. Its linguistic expressions vary widely across topics, complicating automatic detection efforts. Most existing methods strugg...

Full description

Saved in:
Bibliographic Details
Main Authors: Shufeng Xiong, Wenzhuo Liu, Bingkun Wang, Yinchao Che, Lei Shi
Format: Article
Language:English
Published: PeerJ Inc. 2025-06-01
Series:PeerJ Computer Science
Subjects:
Online Access:https://peerj.com/articles/cs-2942.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850112849152573440
author Shufeng Xiong
Wenzhuo Liu
Bingkun Wang
Yinchao Che
Lei Shi
author_facet Shufeng Xiong
Wenzhuo Liu
Bingkun Wang
Yinchao Che
Lei Shi
author_sort Shufeng Xiong
collection DOAJ
description With the proliferation of social media, cyberbullying has emerged as a pervasive threat, causing significant psychological harm to individuals and undermining social cohesion. Its linguistic expressions vary widely across topics, complicating automatic detection efforts. Most existing methods struggle to generalize across diverse online contexts due to their reliance on topic-specific features. To address this issue, we propose the Topic Adversarial Neural Network (TANN), a novel end-to-end framework for topic-invariant cyberbullying detection. TANN integrates a multi-level feature extractor with a topic discriminator and a cyberbullying detector. It leverages adversarial training to disentangle topic-related information while retaining universal linguistic cues relevant to harmful content. We construct a multi-topic dataset from major Chinese social media platforms, such as Weibo and Tieba, to evaluate the generalization performance of TANN in real-world scenarios. Experimental results demonstrate that TANN outperforms existing methods in cross-topic detection tasks, significantly improving robustness and accuracy. This work advances cross-topic cyberbullying detection by introducing a scalable solution that mitigates topic interference and enables reliable performance across dynamic online environments.
format Article
id doaj-art-6c3310ce9ccd40e99317455efbb286f1
institution OA Journals
issn 2376-5992
language English
publishDate 2025-06-01
publisher PeerJ Inc.
record_format Article
series PeerJ Computer Science
spelling doaj-art-6c3310ce9ccd40e99317455efbb286f12025-08-20T02:37:17ZengPeerJ Inc.PeerJ Computer Science2376-59922025-06-0111e294210.7717/peerj-cs.2942Topic adversarial neural network for cross-topic cyberbullying detectionShufeng Xiong0Wenzhuo Liu1Bingkun Wang2Yinchao Che3Lei Shi4College of Information and Management Science, Henan Agricultural University, Zhengzhou, ChinaCollege of Information and Management Science, Henan Agricultural University, Zhengzhou, ChinaSchool of Information Engineering, Zhengzhou College of Finance and Economics, Zhengzhou, ChinaCollege of Information and Management Science, Henan Agricultural University, Zhengzhou, ChinaCollege of Information and Management Science, Henan Agricultural University, Zhengzhou, ChinaWith the proliferation of social media, cyberbullying has emerged as a pervasive threat, causing significant psychological harm to individuals and undermining social cohesion. Its linguistic expressions vary widely across topics, complicating automatic detection efforts. Most existing methods struggle to generalize across diverse online contexts due to their reliance on topic-specific features. To address this issue, we propose the Topic Adversarial Neural Network (TANN), a novel end-to-end framework for topic-invariant cyberbullying detection. TANN integrates a multi-level feature extractor with a topic discriminator and a cyberbullying detector. It leverages adversarial training to disentangle topic-related information while retaining universal linguistic cues relevant to harmful content. We construct a multi-topic dataset from major Chinese social media platforms, such as Weibo and Tieba, to evaluate the generalization performance of TANN in real-world scenarios. Experimental results demonstrate that TANN outperforms existing methods in cross-topic detection tasks, significantly improving robustness and accuracy. This work advances cross-topic cyberbullying detection by introducing a scalable solution that mitigates topic interference and enables reliable performance across dynamic online environments.https://peerj.com/articles/cs-2942.pdfCyberbullying detectionTopic adversarial neural networkTopic-invariant featuresCross-topic adaptationChinese social media
spellingShingle Shufeng Xiong
Wenzhuo Liu
Bingkun Wang
Yinchao Che
Lei Shi
Topic adversarial neural network for cross-topic cyberbullying detection
PeerJ Computer Science
Cyberbullying detection
Topic adversarial neural network
Topic-invariant features
Cross-topic adaptation
Chinese social media
title Topic adversarial neural network for cross-topic cyberbullying detection
title_full Topic adversarial neural network for cross-topic cyberbullying detection
title_fullStr Topic adversarial neural network for cross-topic cyberbullying detection
title_full_unstemmed Topic adversarial neural network for cross-topic cyberbullying detection
title_short Topic adversarial neural network for cross-topic cyberbullying detection
title_sort topic adversarial neural network for cross topic cyberbullying detection
topic Cyberbullying detection
Topic adversarial neural network
Topic-invariant features
Cross-topic adaptation
Chinese social media
url https://peerj.com/articles/cs-2942.pdf
work_keys_str_mv AT shufengxiong topicadversarialneuralnetworkforcrosstopiccyberbullyingdetection
AT wenzhuoliu topicadversarialneuralnetworkforcrosstopiccyberbullyingdetection
AT bingkunwang topicadversarialneuralnetworkforcrosstopiccyberbullyingdetection
AT yinchaoche topicadversarialneuralnetworkforcrosstopiccyberbullyingdetection
AT leishi topicadversarialneuralnetworkforcrosstopiccyberbullyingdetection