A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection

• URL: http://arxiv.org/abs/2602.22449v1
• Date: Wed, 25 Feb 2026 22:24:05 GMT
• Title: A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection
• Authors: Mirza Raquib, Asif Pervez Polok, Kedar Nath Biswas, Rahat Uddin Azad, Saydul Akbar Murad, Nick Rahimi,
• Abstract summary: We propose a fusion architecture that combines BanglaBERT-Large with a two-layer stacked LSTM.<n>We analyze their behavior to jointly model context and sequence.<n> Evaluation uses multiple metrics, including accuracy, precision, recall, F1-score, Hamming loss, Cohens kappa, and AUC-ROC.
• Score: 2.0524609401792397
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks [53.97948802255959]
  We propose a framework that trains a multi-turn attacker without relying on any existing strategies or external data.<n>Prefilling self-tuning enables usable rollouts by fine-tuning on non-refusal, well-structured, multi-turn adversarial prompts.<n>We anchor harmful intent in multi-turn jailbreaks via an intent-drift-aware reward that combines intent alignment, compliance risk, and level of detail.
  arXiv  Detail & Related papers  (2026-02-06T16:44:57Z)
• Debiased Dual-Invariant Defense for Adversarially Robust Person Re-Identification [52.63017280231648]
  Person re-identification (ReID) is a fundamental task in many real-world applications such as pedestrian trajectory tracking.<n>Person ReID models are highly susceptible to adversarial attacks, where imperceptible perturbations to pedestrian images can cause entirely incorrect predictions.<n>We propose a dual-invariant defense framework composed of two main phases.
  arXiv  Detail & Related papers  (2025-11-13T03:56:40Z)
• Enhanced Arabic-language cyberbullying detection: deep embedding and transformer (BERT) approaches [0.0]
  Methods for detecting Arabic-language cyberbullying are scarce.<n>This paper aims to enhance the effectiveness of methods for detecting cyberbullying in Arabic-language content.
  arXiv  Detail & Related papers  (2025-10-02T17:20:02Z)
• Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning [58.16354555208417]
  PAD and FFD are proposed to protect face data from physical media-based Presentation Attacks and digital editing-based DeepFakes, respectively.<n>The lack of a Unified Face Attack Detection model to simultaneously handle attacks in these two categories is mainly attributed to two factors.<n>We present a novel Visual-Language Model-based Hierarchical Prompt Tuning Framework that adaptively explores multiple classification criteria from different semantic spaces.
  arXiv  Detail & Related papers  (2025-05-19T16:35:45Z)
• Detecting harassment and defamation in cyberbullying with emotion-adaptive training [10.769252194833625]
  cyberbullying encompasses various forms, such as denigration and harassment, which celebrities frequently face.<n>We first develop a celebrity cyberbullying dataset that encompasses two distinct types of incidents: harassment and defamation.<n>We propose an emotion-adaptive training framework (EAT) that helps transfer knowledge from the domain of emotion detection to the domain of cyberbullying detection.
  arXiv  Detail & Related papers  (2025-01-28T13:15:07Z)
• The Use of a Large Language Model for Cyberbullying Detection [0.0]
  cyberbullying (CB) is the most prevalent phenomenon in todays cyber world. It is a severe threat to the mental and physical health of citizens. This opens the need to develop a robust system to prevent bullying content from online forums, blogs, and social media platforms.
  arXiv  Detail & Related papers  (2024-02-06T15:46:31Z)
• Explain Thyself Bully: Sentiment Aided Cyberbullying Detection with Explanation [52.3781496277104]
  Cyberbullying has become a big issue with the popularity of different social media networks and online communication apps. Recent laws like "right to explanations" of General Data Protection Regulation have spurred research in developing interpretable models. We develop first interpretable multi-task model called em mExCB for automatic cyberbullying detection from code-mixed languages.
  arXiv  Detail & Related papers  (2024-01-17T07:36:22Z)
• A Trustable LSTM-Autoencoder Network for Cyberbullying Detection on Social Media Using Synthetic Data [2.378735224874938]
  This paper proposes a trustable LSTM-Autoencoder Network for cyberbullying detection on social media. We have demonstrated a cutting-edge method to address data availability difficulties by producing machine-translated data. We carried out experimental identification of aggressive comments on Hindi, Bangla, and English datasets.
  arXiv  Detail & Related papers  (2023-08-15T17:20:05Z)
• Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck [77.37409441129995]
  In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition. We consider an adversarial threat model under a mutual information constraint to cover a wider class of perturbations in training. We propose an autoencoder-based training to implement the objective, as well as practical encoder designs to facilitate the proposed hybrid discriminative-generative training.
  arXiv  Detail & Related papers  (2023-03-24T16:03:21Z)
• Analysing Cyberbullying using Natural Language Processing by Understanding Jargon in Social Media [4.932130498861987]
  In our work, we explore binary classification by using a combination of datasets from various social media platforms. We experiment through multiple models such as Bi-LSTM, GloVe, state-of-the-art models like BERT, and apply a unique preprocessing technique by introducing a slang-abusive corpus.
  arXiv  Detail & Related papers  (2021-04-23T04:20:19Z)
• Learning to Generate Noise for Multi-Attack Robustness [126.23656251512762]
  Adversarial learning has emerged as one of the successful techniques to circumvent the susceptibility of existing methods against adversarial perturbations. In safety-critical applications, this makes these methods extraneous as the attacker can adopt diverse adversaries to deceive the system. We propose a novel meta-learning framework that explicitly learns to generate noise to improve the model's robustness against multiple types of attacks.
  arXiv  Detail & Related papers  (2020-06-22T10:44:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.