Efficient Annotator Reliability Assessment and Sample Weighting for Knowledge-Based Misinformation Detection on Social Media

TL;DR

This paper introduces EffiARA, a framework for assessing annotator reliability in knowledge-based misinformation detection on social media, demonstrating that sample weighting improves classification performance.

Contribution

It presents a novel annotation framework and a new dataset, and shows that reliability-based sample weighting enhances misinformation classification accuracy.

Findings

Sample weighting with annotator reliability yields best results.

Achieved macro-F1 scores of 0.757 with Llama-3.2-1B.

Developed and released the RUC-MCD dataset.

Abstract

Misinformation spreads rapidly on social media, confusing the truth and targeting potentially vulnerable people. To effectively mitigate the negative impact of misinformation, it must first be accurately detected before applying a mitigation strategy, such as X's community notes, which is currently a manual process. This study takes a knowledge-based approach to misinformation detection, modelling the problem similarly to one of natural language inference. The EffiARA annotation framework is introduced, aiming to utilise inter- and intra-annotator agreement to understand the reliability of each annotator and influence the training of large language models for classification based on annotator reliability. In assessing the EffiARA annotation framework, the Russo-Ukrainian Conflict Knowledge-Based Misinformation Classification Dataset (RUC-MCD) was developed and made publicly available. This study finds that sample weighting using annotator reliability performs the best, utilising both inter- and intra-annotator agreement and soft-label training. The highest classification performance achieved using Llama-3.2-1B was a macro-F1 of 0.757 and 0.740 using TwHIN-BERT-large.