PIXELMOD: Improving Soft Moderation of Visual Misleading Information on Twitter

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Paudel, Pujan, Ling, Chen, Blackburn, Jeremy, Stringhini, Gianluca
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910547090341888
author Paudel, Pujan
Ling, Chen
Blackburn, Jeremy
Stringhini, Gianluca
author_facet Paudel, Pujan
Ling, Chen
Blackburn, Jeremy
Stringhini, Gianluca
contents Images are a powerful and immediate vehicle to carry misleading or outright false messages, yet identifying image-based misinformation at scale poses unique challenges. In this paper, we present PIXELMOD, a system that leverages perceptual hashes, vector databases, and optical character recognition (OCR) to efficiently identify images that are candidates to receive soft moderation labels on Twitter. We show that PIXELMOD outperforms existing image similarity approaches when applied to soft moderation, with negligible performance overhead. We then test PIXELMOD on a dataset of tweets surrounding the 2020 US Presidential Election, and find that it is able to identify visually misleading images that are candidates for soft moderation with 0.99% false detection and 2.06% false negatives.
format Preprint
id arxiv_https___arxiv_org_abs_2407_20987
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PIXELMOD: Improving Soft Moderation of Visual Misleading Information on Twitter
Paudel, Pujan
Ling, Chen
Blackburn, Jeremy
Stringhini, Gianluca
Computer Vision and Pattern Recognition
Computers and Society
Images are a powerful and immediate vehicle to carry misleading or outright false messages, yet identifying image-based misinformation at scale poses unique challenges. In this paper, we present PIXELMOD, a system that leverages perceptual hashes, vector databases, and optical character recognition (OCR) to efficiently identify images that are candidates to receive soft moderation labels on Twitter. We show that PIXELMOD outperforms existing image similarity approaches when applied to soft moderation, with negligible performance overhead. We then test PIXELMOD on a dataset of tweets surrounding the 2020 US Presidential Election, and find that it is able to identify visually misleading images that are candidates for soft moderation with 0.99% false detection and 2.06% false negatives.
title PIXELMOD: Improving Soft Moderation of Visual Misleading Information on Twitter
topic Computer Vision and Pattern Recognition
Computers and Society
url https://arxiv.org/abs/2407.20987