article · Neural Computing and Applications
Machine learning systems designed to identify cyberbullying frequently struggle with class imbalance, because instances of normal interaction vastly outnumber abusive occurrences. In binary datasets, this imbalance can lead standard classification models to miss minority cyberbullying cases. An experimental study evaluated how various data rebalancing approaches impact classification performance across four cyberbullying datasets. The evaluation tested four specific resampling methods, consisting of random undersampling, random oversampling, SMOTE, and a hybrid SMOTE and TOMEK method, across eight widely used classification algorithms following a data preprocessing stage. The analysis revealed that the effectiveness of these rebalancing techniques is contingent upon the size of the dataset, the ratio of imbalance present, and the chosen classification algorithm. The findings confirm that no single data rebalancing method uniformly outperforms the rest across all cyberbullying detection scenarios.
Online platforms increasingly rely on automated algorithms to detect abusive behaviour. Because cyberbullying occurs far less often than normal communication, models risk ignoring real abuse. Understanding how data balancing tools interact with different algorithms helps engineers design more dependable safety filters that better recognise harmful content without relying on generic, one-size-fits-all solutions.
This research provides applied comparative benchmarks for developers building automated content moderation and cyberbullying detection tools for social media or online community platforms. Because the findings are based on experimental testing of standard algorithms rather than a finished software product, the work sits at an applied and tested research stage, guiding algorithmic configuration rather than offering an immediate off-the-shelf commercial tool.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Cyberbullying detection systems rely increasingly on machine learning techniques. However, class imbalance in cyberbullying datasets, where the percentage of normal labeled classes is higher than that of abnormal labeled ones, presents a significant challenge for classification algorithms. This issue is particularly problematic in two-class datasets, where conventional machine learning methods tend to perform poorly on minority class samples due to the influence of the majority class. To address this problem, researchers have proposed various oversampling and undersampling techniques. In this paper, we investigate the effectiveness of such techniques in addressing class imbalance in cyberbullying datasets. We conduct an experimental study that involves a preprocessing step to enhance machine learning algorithm performance. We then examine the impact of imbalanced data on classification performance for four cyberbullying datasets. To study the classification performance on balanced cyberbullying datasets, we employ four resampling techniques, namely random undersampling, random oversampling, SMOTE, and SMOTE + TOMEK. We evaluate the impact of each rebalancing technique on classification performance using eight well-known classification algorithms. Our findings demonstrate that the performance of resampling techniques depends on the dataset size, imbalance ratio, and classifier used. The conducted experiments proved that there are no techniques that will always perform better the others.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s00521-023-09084-w
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
