Multilingual Models for Check-Worthy Social Media Posts Detection

TL;DR

This paper develops and evaluates multilingual transformer models for detecting verifiable factual and harmful claims in social media posts across multiple languages, demonstrating robustness and efficiency.

Contribution

It introduces novel multi-label multilingual classification models capable of detecting both harmful and factual claims simultaneously in social media posts.

Findings

Models outperform state-of-the-art benchmarks

Effective in low-resource languages

Robust detection across multiple languages

Abstract

This work presents an extensive study of transformer-based NLP models for detection of social media posts that contain verifiable factual claims and harmful claims. The study covers various activities, including dataset collection, dataset pre-processing, architecture selection, setup of settings, model training (fine-tuning), model testing, and implementation. The study includes a comprehensive analysis of different models, with a special focus on multilingual models where the same model is capable of processing social media posts in both English and in low-resource languages such as Arabic, Bulgarian, Dutch, Polish, Czech, Slovak. The results obtained from the study were validated against state-of-the-art models, and the comparison demonstrated the robustness of the proposed models. The novelty of this work lies in the development of multi-label multilingual classification models that can simultaneously detect harmful posts and posts that contain verifiable factual claims in an efficient way.