# TWIGMA: A dataset of AI-Generated Images with Metadata From Twitter

arXiv: https://arxiv.org/abs/2306.08310 · HTML: https://mlsanity.com/paper/2306.08310/

## Key facts

- Cited by 19 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 14 Jun 2023.

## Built on by (most cited first, 19 of 19)

- [Real-Time Deepfake Detection in the Real-World](https://mlsanity.com/paper/2406.09398/) (2024)
- [GAIA: Rethinking Action Quality Assessment for AI-Generated Videos](https://mlsanity.com/paper/2406.06087/) (2024)
- [Position: Measure Dataset Diversity, Don't Just Claim It](https://mlsanity.com/paper/2407.08188/) (2024)
- [Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors](https://mlsanity.com/paper/2411.07472/) (2024)
- [SAGI: Semantically Aligned and Uncertainty Guided AI Image Inpainting](https://mlsanity.com/paper/2502.06593/) (2025)
- [TextureCrop: Enhancing Synthetic Image Detection through Texture-based Cropping](https://mlsanity.com/paper/2407.15500/) (2024)
- [OpenFake: An Open Dataset and Platform Toward Real-World Deepfake Detection](https://mlsanity.com/paper/2509.09495/) (2025)
- [Evolution of Detection Performance throughout the Online Lifespan of Synthetic Images](https://mlsanity.com/paper/2408.11541/) (2024)
- [PromptMap: An Alternative Interaction Style for AI-Based Image Generation](https://mlsanity.com/paper/2503.09436/) (2025)
- [Navigating the Challenges of AI-Generated Image Detection in the Wild: What Truly Matters?](https://mlsanity.com/paper/2507.10236/) (2025)
- [Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models](https://mlsanity.com/paper/2406.14599/) (2024)
- [A Critical Assessment of Modern Generative Models' Ability to Replicate Artistic Styles](https://mlsanity.com/paper/2502.15856/) (2025)
- [Zero-Shot Automatic Annotation and Instance Segmentation using LLM-Generated Datasets: Eliminating Field Imaging and Manual Annotation for Deep Learning Model Development](https://mlsanity.com/paper/2411.11285/) (2024)
- [A Comprehensive Dataset for Human vs. AI Generated Image Detection](https://mlsanity.com/paper/2601.00553/) (2026)
- [A Large-scale Universal Evaluation Benchmark For Face Forgery Detection](https://mlsanity.com/paper/2406.09181/) (2024)
- ["Humor, Art, or Misinformation?": A Multimodal Dataset for Intent-Aware Synthetic Image Detection](https://mlsanity.com/paper/2508.20670/) (2025)
- [Identifying Prompted Artist Names from Generated Images](https://mlsanity.com/paper/2507.18633/) (2025)
- [Extending a Parliamentary Corpus with MPs' Tweets: Automatic Annotation and Evaluation Using MultiParTweet](https://mlsanity.com/paper/2512.11567/) (2025)
- [Automated In-the-Wild Data Collection for Continual AI Generated Image Detection](https://mlsanity.com/paper/2605.02567/) (2026)

## Abstract (arXiv)

Recent progress in generative artificial intelligence (gen-AI) has enabled the generation of photo-realistic and artistically-inspiring photos at a single click, catering to millions of users online. To explore how people use gen-AI models such as DALLE and StableDiffusion, it is critical to understand the themes, contents, and variations present in the AI-generated photos. In this work, we introduce TWIGMA (TWItter Generative-ai images with MetadatA), a comprehensive dataset encompassing over 800,000 gen-AI images collected from Jan 2021 to March 2023 on Twitter, with associated metadata (e.g., tweet text, creation date, number of likes), available at https://zenodo.org/records/8031785. Through a comparative analysis of TWIGMA with natural images and human artwork, we find that gen-AI images possess distinctive characteristics and exhibit, on average, lower variability when compared to their non-gen-AI counterparts. Additionally, we find that the similarity between a gen-AI image and natural images is inversely correlated with the number of likes. Finally, we observe a longitudinal shift in the themes of AI-generated images on Twitter, with users increasingly sharing artistically sophisticated content such as intricate human portraits, whereas their interest in simple subjects such as natural scenes and animals has decreased. Our findings underscore the significance of TWIGMA as a unique data resource for studying AI-generated images.