Research map / Vision-language and multimodal / Human and embodied modeling
Predicting the Politics of an Image Using Webly Supervised Data
Christopher Thomas, Adriana Kovashka
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Ours instead of Resnet | Image political-leaning classification · Vaccines | average performance: 0.6768 -> 0.7422 | Improved |
| Use Ours instead of Resnet | Image political-leaning classification · Fracking | average performance: 0.6737 -> 0.7209 | Improved |
| Use Ours instead of Resnet | Image political-leaning classification · War on Drugs | average performance: 0.6684 -> 0.7128 | Improved |
| Use Ours instead of Resnet | Image political-leaning classification · Border Security | average performance: 0.6922 -> 0.7161 | Improved |
| Use Ours instead of Resnet | Image political-leaning classification · Black Lives Matter | average performance: 0.7026 -> 0.7269 | Improved |
| Use Ours instead of Resnet | Image political-leaning classification · Climate Change | average performance: 0.6934 -> 0.7179 | Improved |
| Use Ours instead of Resnet | Image political-leaning classification · Top-20 news sources | average performance: 0.697 -> 0.739 | Improved |
| Use Ours instead of Resnet | Image political-leaning classification · Top-100 news sources | average performance: 0.690 -> 0.724 | Improved |
| Use Ours instead of Resnet | Image political-leaning classification · The Sun | average performance: 0.627 -> 0.707 | Improved |
| Use Ours instead of Resnet | Image political-leaning classification · Change | average performance: 0.653 -> 0.690 | Improved |
| Use Ours instead of Resnet | Image political-leaning classification · Breitbart | average performance: 0.527 -> 0.607 | Improved |
| Use Ours instead of Resnet | Image political-leaning classification · NewSt | average performance: 0.821 -> 0.808 | Hurt |
Closest papers by meaning
- Political Bias Prediction Models Focus on Source Cues, Not Semantics (AAAI 2025 · similarity 0.88)
- FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models (NeurIPS 2025 · similarity 0.84)
- Understanding Bias in Large-Scale Visual Datasets (NeurIPS 2024 · similarity 0.84)
- Linear Representations of Political Perspective Emerge in Large Language Models (ICLR 2025 · similarity 0.83)
- Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers (CVPR 2025 · similarity 0.83)
- When Neutral Summaries Are Not That Neutral: Quantifying Political Neutrality in LLM-Generated News Summaries (Student Abstract) (AAAI 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
