Fraunhofer SIT at CheckThat! 2023: Mixing Single-Modal Classifiers to Estimate the Check-Worthiness of Multi-Modal Tweets

TL;DR

This paper introduces a novel multi-modal tweet check-worthiness detection method combining single-modal classifiers, achieving top performance in the CheckThat! 2023 challenge.

Contribution

It presents a new approach that leverages separate classifiers for different modalities and combines their outputs for improved check-worthiness estimation.

Findings

Achieved first place in CheckThat! 2023 Task 1A with an F1 score of 0.7297.

Using OCR to extract embedded text from images improves classification.

Combining single-modal classifiers enhances multi-modal tweet analysis.

Abstract

The option of sharing images, videos and audio files on social media opens up new possibilities for distinguishing between false information and fake news on the Internet. Due to the vast amount of data shared every second on social media, not all data can be verified by a computer or a human expert. Here, a check-worthiness analysis can be used as a first step in the fact-checking pipeline and as a filtering mechanism to improve efficiency. This paper proposes a novel way of detecting the check-worthiness in multi-modal tweets. It takes advantage of two classifiers, each trained on a single modality. For image data, extracting the embedded text with an OCR analysis has shown to perform best. By combining the two classifiers, the proposed solution was able to place first in the CheckThat! 2023 Task 1A with an F1 score of 0.7297 achieved on the private test set.