THE IMPACT OF JSON-LD METADATA ON CHATGPT VISIBILITY
DOI:
https://doi.org/10.61841/xt3he524Keywords:
ChatGPT, Artificial Intelligence, GEO, Generative Engine Optimization, online marketingAbstract
Purpose: This study examines whether implementing structured metadata (JSON-LD Schema.org markup) on websites can improve a business’s visibility in ChatGPT responses. We focus on real estate agencies as a case study, analyzing which site attributes correlate with an agency being “known” or referenced by ChatGPT.
Methods: We gathered public data on 1,508 real estate agents in Germany and identified which of these agents ChatGPT could provide information about (indicating ChatGPT visibility). For each agent’s website, we recorded the presence of Schema.org metadata (FAQPage, Organization, Product schemas), as well as SEO/technical factors like mobile optimization, robots.txt, sitemap, headings usage, image alt-text, internal links, and page load speed. A logistic regression was used to determine which factors significantly predict ChatGPT visibility, controlling for other variables.
Results: Agents whose websites included FAQPage schema markup were far more likely to be visible on ChatGPT (6.2% of visible agents had FAQ schema vs. only 0.8% of non-visible; p = 0.002). Presence of Product schema (e.g. schema for listings or services) also strongly correlated with visibility (17.2% vs 1.8%; p < 0.001). Key technical SEO features were likewise more common among ChatGPT-visible agents: nearly all had mobile-friendly sites (99.0% vs 88.8% of non-visible; p < 0.001) and a robots.txt file (92.3% vs 80.6%; p < 0.001). Visible agents’ sites were more likely to use structured headings (94.7% had an h2 tags vs 74.4% of non-visible; 86.6% had an h3 tags vs 61.4% of non-visible; p < 0.001), and their pages loaded faster on average (418 ms vs 623 ms; p = 0.014). A multivariate logistic regression confirmed FAQPage schema as the strongest positive predictor of ChatGPT visibility (odds ratio ≈ 13, p < 0.001), followed by Product schema (OR ≈ 4, p < 0.001). Other significant factors included mobile optimization (OR ≈ 5.2, p = 0.026), presence of a robots.txt (OR ≈ 3.4, p < 0.001), and the use of multiple heading levels (having h2 tags: OR ≈ 3.3; h3 tags: OR ≈ 2.3; both p < 0.001).
Conclusions: Our findings provide empirical support that adding Schema.org metadata – particularly FAQ schemas that supply question-answer pairs – is associated with significantly higher chances of being recognized or cited by AI chat systems like ChatGPT. In practice, this suggests that businesses can improve their AI-driven visibility by adopting structured data and following strong SEO practices. We discuss the implications for “Generative Engine Optimization” (GEO) and estimate the potential monetary benefits of increased AI visibility, which can be substantial given the high client value in real estate.
References
1. Dang, M. H., Pham, T. H. T., Molli, P., Skaf-Molli, H., & Gaignard, A. (2025). LLM4Schema. org: Generating Schema. org Markups with Large Language Models. Semantic Web–Interoperability, Usability, Applicability.
2. de Rosen, T. (2025). Methodology for AI Visibility Optimization Version 3.0. Available at SSRN 5431877.
3. Fernandez, R. C., Elmore, A. J., Franklin, M. J., Krishnan, S., & Tan, C. (2023). How large language models will disrupt data management. Proceedings of the VLDB Endowment, 16(11), 3302-3309.
4. Iliadis, A., Acker, A., Stevens, W., & Kavakli, S. B. (2025). One schema to rule them all: How Schema. org models the world of search. Journal of the Association for Information Science and Technology, 76(2), 460-523.
5. Mior, M. J. (2024). Large language models for json schema discovery. arXiv preprint arXiv:2407.03286.
6. Mussa, O., Rana, O., Goossens, B., Orozco-terWengel, P., & Perera, C. (2024, November). Towards Enhancing Linked Data Retrieval in Conversational UIs Using Large Language Models. In International Conference on Web Information Systems Engineering (pp. 246-261). Singapore: Springer Nature Singapore.
7. Scholl, H. (2023). Internet Marketing with ChatGPT Optimization. Estalontech.
8. Şentürk, E. E., Kartal, C., & İşcan, R. V. (2023). Visibility of Artificial Intelligence Applications in Digital Marketing on WOS. Scientific Journal of Innovation and Social Sciences Research, 3(1), 27-42.
9. Zhang, B., He, Y., Pintscher, L., Peñuela, A. M., & Simperl, E. (2025). Schema Generation for Large Knowledge Graphs Using Large Language Models. arXiv preprint arXiv:2506.04512.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Peter Schanbacher (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
