Mohammad Mosaffa, Omid Rafieian, Hema Yoganarasimhan
arXiv 13 Mar 2025 · cs.CV · 1 citations (OpenAlex)
arXiv:2503.10738 · PDF · DOI · OpenAlex · Extracted main text
Political polarization is a significant issue in American politics, influencing public discourse, policy, and consumer behavior. While studies on polarization in news media have extensively focused on verbal content, non-verbal elements, particularly visual content, have received less attention due to the complexity and high dimensionality of image data. Traditional descriptive approaches often rely on feature extraction from images, leading to biased polarization estimates due to information loss. In this paper, we introduce the Polarization Measurement using Counterfactual Image Generation (PMCIG) method, which combines economic theory with generative models and multi-modal deep learning to fully utilize the richness of image data and provide a theoretically grounded measure of polarization in visual content. Applying this framework to a decade-long dataset featuring 30 prominent politicians across 20 major news outlets, we identify significant polarization in visual content, with notable variations across outlets and politicians. At the news outlet level, we observe significant heterogeneity in visual slant. Outlets such as Daily Mail, Fox News, and Newsmax tend to favor Republican politicians in their visual content, while The Washington Post, USA Today, and The New York Times exhibit a slant in favor of Democratic politicians. At the politician level, our results reveal substantial variation in polarized coverage, with Donald Trump and Barack Obama among the most polarizing figures, while Joe Manchin and Susan Collins are among the least. Finally, we conduct a series of validation tests demonstrating the consistency of our proposed measures with external measures of media slant that rely on non-image-based sources.
appendix boundary found by appendix_command · 64% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Matthew Gentzkow, Jesse M Shapiro, and Matt Taddy (2019) Measuring group differences in high-dimensional choices: method and application to congressional speech | 0.928 | 4 | 3 | 100% |
| 2 | Yilang Peng (2018) Same candidates, different faces: Uncovering media bias in visual portrayals of presidential candidates with computer vision | 0.928 | 4 | 3 | 100% |
| 3 | Robert Faris, Hal Roberts, Bruce Etling, Nikki Bourassa, Ethan Zucke… (2017) Partisanship, propaganda, and disinformation: Online media and the 2016 us presidential election | 0.894 | 14 | 3 | 71% |
| 4 | Levi Boxell (2021) Slanted images: Measuring nonverbal media bias during the 2016 election | 0.866 | 20 | 5 | 65% |
| 5 | Yanhao Wei and Nikhil Malik (2022) Unstructured data, econometric models, and estimation bias | 0.843 | 4 | 4 | 75% |
| 6 | Giulia Caprini (2023) Visual bias | 0.843 | 3 | 3 | 100% |
| 7 | Matthew Gentzkow and Jesse M Shapiro (2010) What drives media slant? evidence from us daily newspapers | 0.843 | 3 | 3 | 100% |
| 8 | Seth Flaxman, Sharad Goel, and Justin M Rao (2016) Filter bubbles, echo chambers, and online news consumption | 0.727 | 13 | 5 | 38% |
| 9 | AllSides (2024) Media bias rating methods, 2024 | 0.659 | 7 | 2 | 43% |
| 10 | Thomas H Davenport (2017) How analytics has changed in the last 10 years (and how it’s stayed the same) | 0.644 | 2 | 2 | 100% |
Showing the top 10 of 77 scored citations.