Cyberbullying Data Set with IPC Act Annotations

The rapid growth of social media platforms has led to a significant rise in cyberbullying incidents, necessitating robust datasets for developing automated detection and legal classification systems. This dataset presents a comprehensive collection of cyberbullying-related textual data annotated with relevant provisions of the Indian Penal Code (IPC). The dataset includes user-generated content from online platforms, systematically labeled into cyberbullying and non-cyberbullying categories, along with corresponding IPC sections such as IPC 153A, IPC 505, IPC 354A, and IPC 509, enabling both behavioral and legal analysis of online abuse.Each data instance undergoes preprocessing to handle informal language, slang, abbreviations, and contextual variations commonly found in digital communication. The dataset is designed to support multi-class and multi-label classification, facilitating research in cyberbullying detection, legal offense prediction, and explainable AI-driven moderation systems. By integrating legal annotations, the dataset bridges the gap between technical cyberbullying detection and judicial interpretability, making it valuable for developing AI models that align with real-world legal frameworks.This dataset can be effectively used for benchmarking traditional machine learning, deep learning, and hybrid models, including transformer-based architectures. It also supports research in sentiment analysis, attention-based interpretability, and ethical AI for online safety. The dataset aims to advance interdisciplinary research at the intersection of artificial intelligence, cyber law, and social media analytics, contributing toward transparent and accountable cyberbullying detection systems.