Abstract
Cyberbullying has become a serious and growing concern in todays virtual world. When left unnoticed, it can have adverse consequences for social and mental health. Researchers have explored various types of cyberbullying, but most approaches use single-label classification, assuming that each comment contains only one type of abuse. In reality, a single comment may include overlapping forms such as threats, hate speech, and harassment. Therefore, multilabel detection is both realistic and essential. However, multilabel cyberbullying detection has received limited attention, especially in low-resource languages like Bangla, where robust pre-trained models are scarce. Developing a generalized model with moderate accuracy remains challenging. Transformers offer strong contextual understanding but may miss sequential dependencies, while LSTM models capture temporal flow but lack semantic depth. To address these limitations, we propose a fusion architecture that combines BanglaBERT-Large with a two-layer stacked LSTM. We analyze their behavior to jointly model context and sequence. The model is fine-tuned and evaluated on a publicly available multilabel Bangla cyberbullying dataset covering cyberbully, sexual harassment, threat, and spam. We apply different sampling strategies to address class imbalance. Evaluation uses multiple metrics, including accuracy, precision, recall, F1-score, Hamming loss, Cohens kappa, and AUC-ROC. We employ 5-fold cross-validation to assess the generalization of the architecture.
Abstract (translated)
网络欺凌已成为当今虚拟世界中一个严重且日益增长的问题。如果被忽视，它会对社会和心理健康产生不利影响。研究人员已经探索了各种类型的网络欺凌，但大多数方法采用单标签分类，假设每个评论只包含一种形式的滥用行为。实际上，一条单独的评论可能包括多种形式的重叠内容，如威胁、仇恨言论和骚扰。因此，多标签检测既现实又至关重要。然而，多标签网络欺凌检测在资源较少的语言中（例如孟加拉语）受到了相对较少的关注，而这些语言中稳健的预训练模型也较为稀缺。开发一个具有适度准确性的通用模型仍然是一项挑战。Transformer 模型提供强大的上下文理解能力，但可能会错过序列依赖性；而LSTM 模型可以捕捉时间流程，但在语义深度方面有所欠缺。 为了解决这些问题，我们提出了一种融合架构，结合了BanglaBERT-Large与两层堆叠的LSTM模型。我们分析这两种模型的行为，并共同建模上下文和序列关系。该模型在公开可用的多标签孟加拉语网络欺凌数据集上进行微调和评估，该数据集涵盖了网络欺凌、性骚扰、威胁以及垃圾信息等类别。为了应对类不平衡问题，我们采用了不同的抽样策略。评估指标包括准确性、精确度、召回率、F1 值、汉明损失、Cohen's Kappa 和 AUC-ROC 等多项标准。采用五倍交叉验证来评估该架构的泛化能力。
URL
https://arxiv.org/abs/2602.22449
