Multi-Class Visual Cyberbullying Detection Using Deep Neural Networks and the CVID Dataset
Arshed, Muhammad Asad ; Samreen, Zunera ; Ahmad, Arslan ; Amjad, Laiba ; Muavia, Hasnain ; Dewi, Christine and Kabir, Muhammad LU
(2025)
In Information (Switzerland)
16(8).
- Abstract
In an era where online interactions increasingly shape social dynamics, the pervasive issue of cyberbullying poses a significant threat to the well-being of individuals, particularly among vulnerable groups. Despite extensive research on text-based cyberbullying detection, the rise of visual content on social media platforms necessitates new approaches to address cyberbullying using images. This domain has been largely overlooked. In this paper, we present a novel dataset specifically designed for the detection of visual cyberbullying, encompassing four distinct classes: abuse, curse, discourage, and threat. The initial prepared dataset (cyberbullying visual indicators dataset (CVID)) comprised 664 samples for training and validation,... (More)
In an era where online interactions increasingly shape social dynamics, the pervasive issue of cyberbullying poses a significant threat to the well-being of individuals, particularly among vulnerable groups. Despite extensive research on text-based cyberbullying detection, the rise of visual content on social media platforms necessitates new approaches to address cyberbullying using images. This domain has been largely overlooked. In this paper, we present a novel dataset specifically designed for the detection of visual cyberbullying, encompassing four distinct classes: abuse, curse, discourage, and threat. The initial prepared dataset (cyberbullying visual indicators dataset (CVID)) comprised 664 samples for training and validation, expanded through data augmentation techniques to ensure balanced and accurate results across all classes. We analyzed this dataset using several advanced deep learning models, including VGG16, VGG19, MobileNetV2, and Vision Transformer. The proposed model, based on DenseNet201, achieved the highest test accuracy of 99%, demonstrating its efficacy in identifying the visual cues associated with cyberbullying. To prove the proposed model’s generalizability, the 5-fold stratified K-fold was also considered, and the model achieved an average test accuracy of 99%. This work introduces a dataset and highlights the potential of leveraging deep learning models to address the multifaceted challenges of detecting cyberbullying in visual content.
(Less)
- author
- Arshed, Muhammad Asad
; Samreen, Zunera
; Ahmad, Arslan
; Amjad, Laiba
; Muavia, Hasnain
; Dewi, Christine
and Kabir, Muhammad
LU
- organization
- publishing date
- 2025-08
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- convolutional neural network, cyberbullying, deep learning, image-based dataset, pretrained models, transfer learning, transformer
- in
- Information (Switzerland)
- volume
- 16
- issue
- 8
- article number
- 630
- publisher
- MDPI AG
- external identifiers
-
- scopus:105014325032
- ISSN
- 2078-2489
- DOI
- 10.3390/info16080630
- language
- English
- LU publication?
- yes
- id
- 471dfe00-999e-4237-a9aa-e0ae247c7aa5
- date added to LUP
- 2025-11-07 10:23:55
- date last changed
- 2025-11-07 10:24:57
@article{471dfe00-999e-4237-a9aa-e0ae247c7aa5,
abstract = {{<p>In an era where online interactions increasingly shape social dynamics, the pervasive issue of cyberbullying poses a significant threat to the well-being of individuals, particularly among vulnerable groups. Despite extensive research on text-based cyberbullying detection, the rise of visual content on social media platforms necessitates new approaches to address cyberbullying using images. This domain has been largely overlooked. In this paper, we present a novel dataset specifically designed for the detection of visual cyberbullying, encompassing four distinct classes: abuse, curse, discourage, and threat. The initial prepared dataset (cyberbullying visual indicators dataset (CVID)) comprised 664 samples for training and validation, expanded through data augmentation techniques to ensure balanced and accurate results across all classes. We analyzed this dataset using several advanced deep learning models, including VGG16, VGG19, MobileNetV2, and Vision Transformer. The proposed model, based on DenseNet201, achieved the highest test accuracy of 99%, demonstrating its efficacy in identifying the visual cues associated with cyberbullying. To prove the proposed model’s generalizability, the 5-fold stratified K-fold was also considered, and the model achieved an average test accuracy of 99%. This work introduces a dataset and highlights the potential of leveraging deep learning models to address the multifaceted challenges of detecting cyberbullying in visual content.</p>}},
author = {{Arshed, Muhammad Asad and Samreen, Zunera and Ahmad, Arslan and Amjad, Laiba and Muavia, Hasnain and Dewi, Christine and Kabir, Muhammad}},
issn = {{2078-2489}},
keywords = {{convolutional neural network; cyberbullying; deep learning; image-based dataset; pretrained models; transfer learning; transformer}},
language = {{eng}},
number = {{8}},
publisher = {{MDPI AG}},
series = {{Information (Switzerland)}},
title = {{Multi-Class Visual Cyberbullying Detection Using Deep Neural Networks and the CVID Dataset}},
url = {{http://dx.doi.org/10.3390/info16080630}},
doi = {{10.3390/info16080630}},
volume = {{16}},
year = {{2025}},
}