Online social media platforms are central to everyday communication and information seeking. While these platforms serve positive purposes, they also provide fertile ground for the spread of hate speech, offensive language, and bullying content targeting individuals, organizations, and communities. Such content undermines safety, participation, and equity online. Reliable detection systems are therefore needed, especially for low-resource languages where moderation tools are limited. In Bangla, prior work has contributed resources and models, but most are single-task (e.g., binary hate/offense) with limited coverage of multi-facet signals (type, severity, target). We address these gaps by introducing the first multi-task Bangla hate-speech dataset, BanglaMultiHate, one of the largest manually annotated corpus to date. Building on this resource, we conduct a comprehensive, controlled comparison spanning classical baselines, monolingual pretrained models, and LLMs under zero-shot prompting and LoRA fine-tuning. Our experiments assess LLM adaptability in a low-resource setting and reveal a consistent trend: although LoRA-tuned LLMs are competitive with BanglaBERT, culturally and linguistically grounded pretraining remains critical for robust performance. Together, our dataset and findings establish a stronger benchmark for developing culturally aligned moderation tools in low-resource contexts. For reproducibility, we will release the dataset and all related scripts.
BanTH: A Multi-label Hate Speech Detection Dataset for Transliterated Bangla
Research and Development, Penta Global Limited(研发部,Penta全球有限公司);Islamic University of Technology(伊斯兰技术大学);CCDS Lab, Independent University(CCDS实验室,独立大学)
AbuseAnalyzer: Abuse Detection, Severity and Target Prediction for Gab Posts
International Institute of Information Technology Hyderabad(海得拉巴国际信息技术研究所);Indraprastha Institute of Information Technology Delhi(德里英德拉普拉斯塔信息技术研究所);Microsoft(微软)
DeepHateExplainer: Explainable Hate Speech Detection in Under-resourced Bengali Language
Fraunhofer FIT(弗劳恩霍夫应用信息技术研究所);RWTH Aachen University(亚琛工业大学);Noakhali Science and Technology University(诺亚克利科技大学);Begum Rokeya University(贝古姆·罗凯亚大学);The University of Alabama(阿拉巴马大学);National University of Ireland, Galway(爱尔兰国立高威大学);Islamic University of Technology(伊斯兰科技大学)
Multimodal Hate Speech Detection from Bengali Memes and Texts
Fraunhofer FIT(弗劳恩霍夫应用信息技术研究所);RWTH Aachen University(亚琛工业大学);Noakhali Science and Technology University(诺阿卡利科技大学);University of Siegen(锡根大学);University of Galway(戈尔韦大学)
Contextual-Lexicon Approach for Abusive Language Detection
Institute of Mathematical and Computer Sciences, University of São Paulo(圣保罗大学数学与计算机科学学院);Ribeirão Preto Medical School, University of São Paulo(圣保罗大学里贝朗普雷图医学院);Federal University of Minas Gerais(米纳斯吉拉斯联邦大学)
A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection
Department of Computer and Communication Engineering, International Islamic University Chittagong, Chattogram, Bangladesh(国际伊斯兰大学奇塔格ong分校计算机与通信工程系);Department of Information and Communication Engineering, Noakhali Science and Technology University, Noakhali, Bangladesh(诺阿克利科学与技术大学信息与通信工程系);mPower Social Enterprise(mPower社会企业);Department of Software Engineering, Daffodil International University, Bangladesh(达福尔国际大学软件工程系);School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS, USA(密西西比大学南方分校计算机科学与工程学院)