Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

DETECTING CYBERBULLYING ACROSS NIGERIAN LANGUAGES: A MULTILINGUAL SYSTEM

Domaine:

natural language processing

Type de record:

papersoftware
Créateur:
IkeAmaAgbMad
Éditeur:
The
Hôte:avatar

ABSTRACT

As the digital world evolves, the issue of cyberbullying continues to escalate, affecting individuals across diverse cultural and linguistic contexts. While significant progress has been made in developing efficient cyberbullying detection systems primarily in English, these solutions have reached a saturation point, limiting their applicability and effectiveness in non-English speaking environments. This paper presents a comprehensive multilingual cyberbullying detection system designed to identify and address instances of online harassments in two languages used in Nigeria –Pidgin and Igbo. A prototype is developed that operates across data sets created for these two languages. Using this prototype, experiments are carried out with Multinomial Naive Bayes (MNB), Logistics Regression (LR), and Stochastic Gradient Descent (SGD) algorithms to detect cyberbullying in these two languages. The results of our experiments show an accuracy up-to 97% and F1-score up-to 96% on datasets for both the languages.

Visit

doi.org

Tasks

hate speech detectiontext classification

Languages

Ndasa

Licenses

info:eu-repo/semantics/openAccessCreative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similaires

Empirical Perspective on Significant Technological Barriers in Detecting Multilingual Cyberbullying in Nigerian Languageskhaoula-ghz/multilingual-cyberbullying-detectionDetecting Languages Unintelligible to Multilingual Models through Local Structure ProbesDocAtlas: Multilingual Document Understanding Across 80+ LanguagesMaking a MIRACL: Multilingual Information Retrieval Across a Continuum of LanguagesTowards Scalable Multilingual AI:Benchmarking CompressedTransformer Models Across Languages

Empirical Perspective on Significant Technological Barriers in Detecting Multilingual Cyberbullying in Nigerian Languages

Abstract: In recent years, the potential for cyberbullying has

khaoula-ghz/multilingual-cyberbullying-detection

Cyberbullying detection across English, Arabic, and Algerian Darija using Transformer-based hybrid m

Detecting Languages Unintelligible to Multilingual Models through Local Structure Probes

Providing better language tools for low-resource and endangered languages is imperative for equitabl

DocAtlas: Multilingual Document Understanding Across 80+ Languages

Multilingual document understanding remains limited for low-resource languages due to scarce trainin

Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languages

MIRACL (Multilingual Information Retrieval Across a Continuum of Languages) is a multilingual datase

Towards Scalable Multilingual AI:Benchmarking CompressedTransformer Models Across Languages

Large Language Models (LLMs) have demonstrated remarkable proficiency in natural language processing