Bengali cyberbullying corpus improves context aware detection in politics
BenCoDiC: A Large-Scale Contextual Cyberbullying Corpus for Bengali Political News Discourse FULL VERSION
Computation and LanguageSocial and Information Networks
Summary
Cyberbullying is a big problem online, especially around political topics. The authors created a large collection of Bengali political news comments from YouTube, keeping the conversation structure intact to better understand bullying behaviors. They carefully labeled the data by hand to make it reliable. Their tests show that using the conversation context helps detect cyberbullying more accurately than just looking at isolated comments. This dataset can help build better tools to find and study online harassment in Bengali political discussions.
What this means in practice
- •For social media platform developers: Create tools to detect cyberbullying in Bengali political comment threads using context-aware models built on the BenCoDiC corpus.
- •For online community managers: Analyze user behaviors and interaction networks related to harassment in Bengali political discussions leveraging the corpus' rich contextual data.
Authors
Md. Nesarul Hoque, Rudra Pratap Deb Nath, Umme Salma, Shima Chakraborty, Md. Hanif Seddiqui
Abstract
Cyberbullying is a growing concern in online communities, yet existing Bengali corpora remain limited in contextual information, annotation transparency, scale, accessibility, and support for multidimensional analysis, thereby hindering robust detection and comprehensive study of harasser behaviors and networks. To address these gaps, we introduce the Bengali Contextual and Diverse Cyberbullying (\textit{BenCoDiC}) corpus, a publicly available contextual cyberbullying resource for Bengali political news discourse comprising 50,250 textual instances collected from 100 YouTube videos and their associated discussions. The corpus preserves caption--comment--reply relationships and is organized through a nine-dimensional star schema covering users, videos, textual content, context, time, engagement, political parties, target identities, and language categories. Five AI chatbots were initially evaluated for annotation but did not meet the predefined reliability criterion. Consequently, a two-tier human annotation process with expert verification was adopted, achieving Fleiss' $κ=0.86$ and Krippendorff's $α=0.86$. Statistical analyses characterize the corpus, while transformer-based experiments show that incorporating conversational context yields modest but consistent improvements over isolated-text classification. \textit{BenCoDiC} supports context-aware cyberbullying detection and perpetrator-oriented behavioral and network analysis. The corpus is available at https://github.com/bencodic/BenCoDiC-Corpus.