Image of the City in the Age of Large Language Models: ChatGPT as a New Urban Observer

Öz

This research examines how city images of Istanbul’s Historic Peninsula are evolving with artificial intelligence and expanding user-generated content. City image refers to a mental representation of urban structure, and imageability to the ease of forming it. Using Lynch’s five-element framework (paths, edges, districts, nodes, landmarks), the study compares a classical verbal cognitive map based on 32 interviews with built-environment academics (noting possible sample bias) with ChatGPT’s reading of 210 citizen reviews from TripAdvisor and Ekşi Sözlük. A structured, multi-step prompting workflow, guided and checked by humans at each stage, prompts the model (not trained on the corpus) to extract, categorize, and summarize key locations and experiences in these informal narratives. While the model recognizes familiar Lynch elements, it also redistributes their prominence: iconic buildings become less dominant, while comfort, crowding, safety, and spatial atmosphere become more central. The findings suggest that large language models can function as urban observers capable of summarizing collective city images at scale. The method offers a reproducible way to connect interview-based cognitive mapping with platform narratives. It highlights the need for critical, human-led interpretation when applying language models to urban design.

Anahtar Kelimeler

• Image of the City
• Large Language Models (LLMs)
• Urban Perception
• Istanbul Historic Peninsula
• Kevin Lynch

Büyük Dil Modelleri Çağında Kent İmgesi: Yeni Bir Kentsel Gözlemci Olarak ChatGPT

Öz

Bu araştırma, yapay zekâ ve kullanıcı tarafından üretilen içeriğin genişlemesiyle birlikte İstanbul’un Tarihi Yarımadası’na ilişkin kent imgelerinin nasıl değiştiğini incelemektedir. “Kent imgesi”, kentsel yapının zihinsel bir temsiline; “imgelenebilirlik” ise bu temsilin ne kadar kolay oluştuğuna karşılık gelir. Lynch’in beş öğeli çerçevesi (yollar, sınırlar, bölgeler, düğümler, simgeler) kullanılarak çalışma, yapılı çevre alanındaki akademisyenlerle yapılan 32 görüşmeye dayanan klasik sözlü bilişsel haritalama temelini (örneklem yanlılığı olasılığı not edilerek) TripAdvisor ve Ekşi Sözlük’ten derlenen 210 yurttaş yorumunun ChatGPT tarafından okunmasıyla karşılaştırır. Her aşamada insan tarafından yönlendirilen ve kontrol edilen yapılandırılmış, çok aşamalı bir istemleme (prompting) iş akışı, modeli (korpus üzerinde eğitilmemiş) bu gayriresmî anlatılardaki kilit mekân ve deneyimleri çıkarmaya, sınıflandırmaya ve özetlemeye sevk eder. Model Lynch öğelerini tanırken, bunların göreli belirginliğini yeniden dağıtır: simgesel yapılar daha az baskın hâle gelirken, konfor, kalabalıklık, güvenlik ve mekânsal atmosfer daha merkezi bir konuma yerleşir. Bulgular, büyük dil modellerinin kolektif kent imgelerini ölçekte özetleyebilen kentsel gözlemciler olarak işlev görebileceğini göstermektedir. Yöntem, görüşmeye dayalı bilişsel haritalamayı platform anlatılarıyla ilişkilendirmek için yeniden üretilebilir bir yol sunar ve kentsel tasarımda dil modelleri uygulanırken eleştirel, insan-odaklı yorumlamanın gerekliliğini vurgular.

Anahtar Kelimeler

• Kentin İmgesi
• Büyük Dil Modelleri (LLM)
• Kentsel Algı
• İstanbul Tarihi Yarımadası
• Kevin Lynch

Kaynakça

1. Acar, M., & Ek, I. (2024). The Image of the City on Social Media: Case of İzmir City Centers (Instagram’da dijital olarak yeniden üretilen kentin imgesi: İzmir Kent Merkezleri Örneği). GRID - Architecture Planning and Design Journal, 7, 363-387. https://doi.org/10.37246/grid.1282193
2. Appleyard, D. (1970). Styles and Methods of Structuring a City. Environment and Behavior, 2(1), 100-117. https://doi.org/10.1177/001391657000200106
3. Atiyat, D. (2022). The Image of Amman City: Structure, Identity, and Meaning. International Journal of Sustainable Development and Planning, 17, 1931-1935. https://doi.org/10.18280/ijsdp.170628
4. Batty, M. (2018). Digital twins. Environment and Planning B: Urban Analytics and City Science, 45(5), 817-820. https://doi.org/10.1177/2399808318796416
5. Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021). On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? ? Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, Virtual Event, Canada. https://doi.org/10.1145/3442188.3445922
6. Boy, J., & Uitermark, J. (2016). How to Study the City on Instagram. PLoS ONE, 11, e0158161. https://doi.org/10.1371/journal.pone.0158161
7. Cao, Z., Mao, Y., Mustafa, M., & Mohd Isa, M. H. (2025). Future cities imagined by ChatGPT-4o: human evaluation using importance-performance analysis. Humanities and Social Sciences Communications, 12(1), 630. https://doi.org/10.1057/s41599-025-04941-6
8. Cranshaw, J., Schwartz, R., Hong, J., & Sadeh, N. (2021). The Livehoods Project: Utilizing Social Media to Understand the Dynamics of a City. Proceedings of the International AAAI Conference on Web and Social Media, 6(1), 58-65. https://doi.org/10.1609/icwsm.v6i1.14278

9. Cullen, G. (1995). The Concise Townscape. Architectural Press. https://books.google.com.tr/books?id=UoUJFju-10AC
10. Floridi, L., & Chiriatti, M. (2020). GPT-3: Its Nature, Scope, Limits, and Consequences. Minds and Machines, 30(4), 681-694. https://doi.org/10.1007/s11023-020-09548-1
11. Goodchild, M. F. (2007). Citizens as sensors: the world of volunteered geography. GeoJournal, 69(4), 211-221. https://doi.org/10.1007/s10708-007-9111-y
12. Graham, M., & Zook, M. (2013). Augmented Realities and Uneven Geographies: Exploring the Geolinguistic Contours of the Web. Environment and Planning A: Economy and Space, 45(1), 77-99. https://doi.org/10.1068/a44674
13. Hochman, N., & Manovich, L. (2013). Zooming into an Instagram City: Reading the local through social media. First Monday, 18. https://doi.org/10.5210/fm.v18i7.4711
14. Hou, C., Zhang, F., Li, Y., Li, H., Mai, G., Kang, Y., Yao, L., Yu, W., Yao, Y., Gao, S., Chen, M., & Liu, Y. (2025). Urban sensing in the era of large language models. The Innovation, 6(1). https://doi.org/10.1016/j.xinn.2024.100749 Hwang, Y., Lee, J. H., & Shin, D. (2023). What is prompt literacy? An exploratory study of language learners' development of new literacy skill using generative AI. ArXiv, abs/2311.05373 Karimimoshaver, M., Eris, B., & Parto, S. (2016). A Review of Mental Urbanscape* Using Map-Based Methods (Case study: Tehran Ferdowsi Square). Iran University of Science & Technology, 26, 61-70
15. Kılıçaslan, H., Uluçay Temel, M., & Taslı, P. (2024). Imaged Experiences: Mapping the Trabzon City Center [Imaged Experiences: Mapping the Trabzon City Center]. Black Sea Journal of Engineering and Science, 7(5), 1036-1049. https://doi.org/10.34248/bsengineering.1521928
16. Lynch, K. (1960). The image of the city / Kevin Lynch. MIT Press.
17. Mankuri, D. P. A., & Dönmez, Y. (2022). Assessment of Urban Identity and Its Components: A Case Study of Erbil [Kentsel Kimliğin ve Bileşenlerinin Değerlendirilmesi: Erbil Örneği]. Bartın Orman Fakültesi Dergisi, 24(1), 157-176. https://doi.org/10.24011/barofd.955905
18. Nasar, J. L. (1990). The Evaluative Image of the City. Journal of the American Planning Association, 56(1), 41-53. https://doi.org/10.1080/01944369008975742
19. Newton, P. (2000). Urban form and environmental performance. Achieving sustainable urban form, 2, 46-53. Ögçe, H., & Demir, Z. (2020). Evaluating the City Image of Istanbul Historic Peninsula Through Academicians’ Perspective. Chinese Journal of Urban and Environmental Studies, 08(03), 2050016. https://doi.org/10.1142/s2345748120500165
20. OpenAI. (2025). ChatGPT (GPT-5) [Large language model]. Retrieved 30.10.2025 from https://chat.openai.com/
21. Quercia, D., Capra, L., & Crowcroft, J. (2021). The Social World of Twitter: Topics, Geography, and Emotions. Proceedings of the International AAAI Conference on Web and Social Media, 6(1), 298-305. https://doi.org/10.1609/icwsm.v6i1.14254
22. Rapoport, A. (1977). Human Aspects of Urban Form: Towards a Man-environment Approach to Urban Form and Design. Elsevier Science & Technology. https://books.google.com.tr/books?id=OKJPAAAAMAAJ
23. Raymond, C. M., Nummi, P., von Wirth, T., Poom, A., Ahdekivi, A., Barthel, S., Delmelle, E., Dunkel, E., Fagerholm, N., Grêt-Regamey, A., Hallikainen, F., Heinilä, A., Käyhkö, J., Kotavaara, O., Kyttä, M., Magyar, M., Pesola, A. J., McPhearson, T., Mustafa, A., . . . Venuti, F. (2025). Uses, opportunities and risks of artificial intelligence in participatory urban planning. Discover Cities, 2(1), 93. https://doi.org/10.1007/s44327-025-00137-4
24. Sanchez, T. W., Brenman, M., & Ye, X. (2025). The Ethical Concerns of Artificial Intelligence in Urban Planning. Journal of the American Planning Association, 91(2), 294-307. https://doi.org/10.1080/01944363.2024.2355305 Sepe, M. (2013). Places and perceptions in contemporary city. URBAN DESIGN International, 18(2), 111-113. https://doi.org/10.1057/udi.2013.1
25. Shelton, T., Poorthuis, A., & Zook, M. (2015). Social media and the city: Rethinking urban socio-spatial inequality using user-generated geographic information. Landscape and Urban Planning, 142, 198-211. https://doi.org/https://doi.org/10.1016/j.landurbplan.2015.02.020
26. Whyte, W. H. (1980). The Social Life of Small Urban Spaces. Conservation Foundation. https://books.google.com.tr/books?id=ugexAAAAIAAJ
27. Xia, Y., Qu, A., Zheng, Y., Tang, Y., Zhuang, D., Liang, Y., Wu, C., Zimmermann, R., & Zhao, J. (2025). Reimagining Urban Science: Scaling Causal Inference with Large Language Models. ArXiv, abs/2504.12345.
28. Zhou, Z., Lin, Y., Jin, D., & Li, Y. (2024). Large Language Model for Participatory Urban Planning. ArXiv, abs/2402.17161.
29. Zhu, Y., Brenken, M., Biljecki, F., & Zhang, Y. (2025a). Unveiling the meaning in the image of the city: A novel approach using place reviews and large language models. Environment and Planning B: Urban Analytics and City Science.
30. Zhu, Y., Brenken, M., Biljecki, F., & Zhang, Y. (2025b). Unveiling the meaning in the image of the city: A novel approach using place reviews and large language models. Environment and Planning B: Urban Analytics and City Science, 0(0), 23998083251369143. https://doi.org/10.1177/23998083251369143