Interdisciplinary Studies

Place identity: a generative AI's perspective

K. M. Jang, J. Chen, et al.

This study delves into the exciting realm of generative AI (GenAI) and its ability to express the unique identity of cities through textual and visual means. Researchers, including Kee Moon Jang and Junda Chen, reveal how models like ChatGPT and DALL-E2 can echo real-world urban characteristics, while also revealing some intriguing limitations regarding trustworthiness and bias.

00:00

Playback language: English

Index

Abstract

This study explores the potential of generative AI (GenAI) in capturing the place identity of cities using ChatGPT and DALL-E2. The researchers investigated whether GenAI models could generate textual and visual representations of place identity consistent with real-world data from Wikipedia and Google Images. Results showed GenAI models could capture salient city characteristics, though limitations in trustworthiness and potential biases were noted. The study contributes to urban design and geography by highlighting both the potential and limitations of GenAI in simulating the built environment and its associated meanings.

Publisher

Humanities and Social Sciences Communications

Published On

Sep 07, 2024

Authors

Kee Moon Jang, Junda Chen, Yuhao Kang, Junghwan Kim, Jinhyung Lee, Fabio Duarte, Carlo Ratti

Related Publications

Explore these studies to deepen your understanding of the subject.

Linguistics and Languages

A study on identification of youth identity through a gender lens in network buzzwords: A critical discourse analysis

H. Tan and Y. Yu

Urban Studies

Infrastructure and the evolution of settlement space: a study from a spatial anthropological perspective on the Pearl River Delta

J. Yin and J. Feng

Interdisciplinary Studies

Gender and feminist considerations in artificial intelligence from a developing-world perspective, with India as a case study

S. Kumar and S. Choudhury

Chemistry

A generative artificial intelligence framework based on a molecular diffusion model for the design of metal-organic frameworks for carbon capture

H. Park, X. Yan, et al.

Listen, Learn & Level Up

Over 10,000 hours of research content in 25+ fields, available in 12+ languages.

No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.

listen to research audio papers with researchbunny