mlsanityData to 7 Oct 2026

Seeing Candidates at Scale: Multimodal LLMs for Visual Political Communication on Instagram

arXiv 2604.19489 ↗First posted 21 Apr 2026cs.CV cs.CYcited by 0

On the map: Multimodal LLMs / vision-language models → Social bias and fairness in VLMs

Abstract (arXiv)

This paper presents a computational case study that evaluates the capabilities of specialized machine learning models and emerging multimodal large language models for Visual Political Communication (VPC) analysis. Focusing on concentrated visibility in Instagram stories and posts during the 2021 German federal election campaign, we compare the performance of traditional computer vision models (FaceNet512, RetinaFace, Google Cloud Vision) with a multimodal large language model (GPT-4o) in identifying front-runner politicians and counting individuals in images. GPT-4o outperformed the other models, achieving a macro F1-score of 0.89 for face recognition and 0.86 for person counting in stories. These findings demonstrate the potential of advanced AI systems to scale and refine visual content analysis in political communication while highlighting methodological considerations for future research.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Social bias and fairness in VLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 8 of its 72 references that are in the map. First posted on arXiv 21 Apr 2026.

Builds on

8 of 72 references.

References · 8

  1. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  2. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  3. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 628
  4. 2018Deep Face Recognition: A Surveycited by 275
  5. 2023Can Large Language Models Transform Computational Social Science?cited by 245
  6. 2024Best Practices for Text Annotation with Large Language Modelscited by 34
  7. 2019Understanding the Political Ideology of Legislators from Social Media Imagescited by 9
  8. 2024Detecting Calls to Action in Multimodal Content: Analysis of the 2021 German Federal Election Campaign on Instagramcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023GPT-4V(ision) as A Social Media Analysis Engine
  2. 2023Detecting and Correcting Hate Speech in Multimodal Memes with Large Visual Language Model
  3. 2025Large Language Model-Informed Feature Discovery Improves Prediction and Interpretation of Credibility Perceptions of Visual Content
  4. 2026Token-Region Guided Cross-Attention Fusion for Multimodal Affect Interpretation
  5. 2026Perceive, Refine, Reason: A Calibrated Pipeline for Measuring Indicators in Strategic Visual Communication on Social Media
  6. 2025Is GPT-4o mini Blinded by its Own Safety Filters? Exposing the Multimodal-to-Unimodal Bottleneck in Hate Speech Detection
  7. 2026The Paradigm Shift: A Comprehensive Survey on Large Vision Language Models for Multimodal Fake News Detection
  8. 2024Mobilizing Waldo: Evaluating Multimodal AI for Public Mobilization