Logo image
Enhancing Urban Data Analysis through Large Language Models: A Case Study with NYC 311 Service Requests
Conference paper   Open access

Enhancing Urban Data Analysis through Large Language Models: A Case Study with NYC 311 Service Requests

Hedaya Walter, Emily Portalatin-Mendez, Matthew Grimalovsky, Brian Smith, Jennifer Laird and Jorge Ortiz
Rutgers University
ACM/IEEE HRI 2024, 19th Annual ACM/IEEE International Conference on Human-Robot Interaction (Denver, Colorado, USA, 03/10/2024–03/14/2026)
DOI:
https://doi.org/10.7282/00000596

Abstract

This paper demonstrates using large language models (LLMs) to extract insights from extensive urban data sets, demonstrated through a case study analyzing New York City's 35.4 million 311 service requests. While ChatGPT 4.0 generated multi-modal narratives from small data samples, limitations emerged in recognizing long-term patterns across the larger data set due to constrained context windows. Overcoming these LLM limitations on complex real-world data remains an open challenge to create effective interactive community engagement agents. ACM Reference Format:
pdf
Human___Large_Language_Model_Interaction__HRI_Workshop_paper__311 (10)455.33 kBDownloadView
Open Access
url
Report an accessibility issueView
Please complete a content remediation request to report an accessibility issue with a library electronic resource, website, or service.

Metrics

3 File downloads
8 Record Views

Details

Logo image