"Image, Tell me your story!" Predicting the original meta-context of visual misinformation

TL;DR

This paper introduces the task of automated image contextualization to help fact-checkers identify the true meta-context of images, creating a dataset and baseline methods to improve misinformation detection.

Contribution

It presents the 5Pils dataset with fact-checked images and question-answer pairs, and a baseline model for grounding images in their original meta-context.

Findings

Promising baseline results in image contextualization

Highlights challenges in retrieval and reasoning tasks

Provides publicly available code and dataset

Abstract

To assist human fact-checkers, researchers have developed automated approaches for visual misinformation detection. These methods assign veracity scores by identifying inconsistencies between the image and its caption, or by detecting forgeries in the image. However, they neglect a crucial point of the human fact-checking process: identifying the original meta-context of the image. By explaining what is actually true about the image, fact-checkers can better detect misinformation, focus their efforts on check-worthy visual content, engage in counter-messaging before misinformation spreads widely, and make their explanation more convincing. Here, we fill this gap by introducing the task of automated image contextualization. We create 5Pils, a dataset of 1,676 fact-checked images with question-answer pairs about their original meta-context. Annotations are based on the 5 Pillars fact-checking framework. We implement a first baseline that grounds the image in its original meta-context using the content of the image and textual evidence retrieved from the open web. Our experiments show promising results while highlighting several open challenges in retrieval and reasoning. We make our code and data publicly available.