How Does ChatGPT Measure City Similarities?
Year: 2025
Type: conference-paper
Abstract: This paper quantifies GPT’s perceptions of cities by converting the descriptive texts, which are responses from GPT using prompts of different word lengths, into numeric embeddings using the BERT model. Our findings reveal that as the prompted length of the response increases, the stability and reliability of GPT’s textual descriptions of cities increases. Additionally, when comparing our results with previous studies that utilised Street View images to quantify city similarity, we find that the GPT model effectively links cities with similar characteristics, such as geographical proximity and cultural similarity.
Authors: Cheng, Qingya, Zhu, Rui, Harris, Richard
Institution: University of Bristol
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6967956237
FWCI:
Cites:
Cited by:
Related to: