Botanic garden visitors’ preference analysis - A case study of Chicago botanic garden

Huang, Hexiang

Permalink

https://hdl.handle.net/2142/124592 Copy

Description

Title

Botanic garden visitors’ preference analysis - A case study of Chicago botanic garden

Author(s)

Huang, Hexiang

Issue Date

2024-05-03

Director of Research (if dissertation) or Advisor (if thesis)

Deal, Brian

Committee Member(s)

• Sullivan, William C.
• Lemon, Kelley
• Fang, Fang

Department of Study

Landscape Architecture

Discipline

Landscape Architecture

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.L.A.

Degree Level

Thesis

Keyword(s)

• Landscape Spatial Analysis
• Visitor Preferences
• User-generated Content

Language

eng

Abstract

User-generated content (UGC) offers an extensive and readily accessible data source for understanding visitor preferences and experiences in natural landscapes. However, there is a lack of large-scale spatial analysis of UGC images depicting landscapes. This study introduces a novel framework that systematically manages and analyzes landscape UGC data to investigate visitor preferences at the Chicago Botanic Garden. The methodology involves web scraping Google Maps reviews and photos, employing generative AI models for computer vision-based image analysis, and applying natural language processing techniques for text analysis. Landscape spatial structure types, elements, components, and plant species are systematically categorized and quantified from the images, while sentiment analysis extracts visitors' feedback and experiences from the text reviews. The results provide insights into the most favored landscape spaces, elements, and specific components that enhance visitor experiences. The efficacy of integrating UGC data analysis with GenAI models is demonstrated, bridging existing research gaps concerning spatial assessment and quantification of visitors' landscape preferences. This study contributes methodological advances in utilizing UGC for landscape research and offers practical implications to empower landscape managers and designers in creating visitor-centric spaces aligned with user preferences. The systematic management of landscape UGC data presents a viable complementary approach to conventional visitor survey methods for landscape design and management.

Graduation Semester

2024-05

Type of Resource

Text

Handle URL

https://hdl.handle.net/2142/124592

Copyright and License Information

Copyright 2024 Hexiang Huang

Owning Collections