MisinfoTeleGraph: Network-driven Misinformation Detection for German Telegram Messages

TL;DR

This paper introduces MisinfoTeleGraph, a German-language Telegram dataset with over 5 million messages, and demonstrates that graph neural networks leveraging message forwarding outperform text-only models in misinformation detection.

Contribution

It provides the first German Telegram misinformation dataset with network and label annotations, and establishes baseline GNN models that improve detection accuracy over text-only approaches.

Findings

GraphSAGE with LSTM outperforms text-only models in MCC and F1-score.

Network structure enhances misinformation detection accuracy.

Weak supervision has potential but also presents challenges.

Abstract

Connectivity and message propagation are central, yet often underutilized, sources of information in misinformation detection -- especially on poorly moderated platforms such as Telegram, which has become a critical channel for misinformation dissemination, namely in the German electoral context. In this paper, we introduce Misinfo-TeleGraph, the first German-language Telegram-based graph dataset for misinformation detection. It includes over 5 million messages from public channels, enriched with metadata, channel relationships, and both weak and strong labels. These labels are derived via semantic similarity to fact-checks and news articles using M3-embeddings, as well as manual annotation. To establish reproducible baselines, we evaluate both text-only models and graph neural networks (GNNs) that incorporate message forwarding as a network structure. Our results show that GraphSAGE with LSTM aggregation significantly outperforms text-only baselines in terms of Matthews Correlation Coefficient (MCC) and F1-score. We further evaluate the impact of subscribers, view counts, and automatically versus human-created labels on performance, and highlight both the potential and challenges of weak supervision in this domain. This work provides a reproducible benchmark and open dataset for future research on misinformation detection in German-language Telegram networks and other low-moderation social platforms.