GPT-4o for Visual Political Communication: Toward Automated Image Type Analysis

URN to cite this document:: urn:nbn:de:bvb:355-epub-774459
DOI to cite this document:: 10.5283/epub.77445

Achmann-Denkler, Michael

; Haim, Mario ; Wolff, Christian

License: Creative Commons Attribution 4.0
PDF - Published Version
(2MB)

Date of publication of this fulltext: 29 Jul 2025 04:28

Alternative links to fulltext:DOI Publisher

Details

Preview

Export bibliographical data

Abstract

This study explores the potential of multimodal large language models (LLMs), specifically GPT-4o, for automating visual political communication analysis on social media. Using a hierarchical decision tree, we guided non-expert annotators in categorizing Instagram campaign images, achieving reliable annotations (Krippendorff’s α = 0.66–0.86). The annotated dataset was used to test GPT-4o’s ...