Seeing Candidates at Scale: Multimodal LLMs for Visual Political Communication on Instagram
For political communication researchers, this demonstrates that multimodal LLMs can scale and refine visual content analysis, though the improvement is incremental over existing methods.
This paper evaluates multimodal LLMs (GPT-4o) against traditional computer vision models for analyzing visual political communication on Instagram, finding GPT-4o achieves macro F1-scores of 0.89 for face recognition and 0.86 for person counting.
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.