Cultural Landscapes and Sustainable Tourism Planning in Jiangnan Water Towns: Multimodal Evidence from User-Generated Content

Sustainable heritage tourism requires understanding shared visitor experiences alongside local cultural distinctiveness. This study develops a comparative framework linking independently derived textual and visual profiles across 12 Jiangnan water towns. Using 33,383 reviews and 74,763 tourist photographs, latent Dirichlet allocation and RoBERTa identify textual themes and sentiment, while Qwen3-VL-8B-Instruct and keyword networks characterize photographic representations. Multiple factor analysis integrates five textual themes and seven visual dimensions to examine their shared and source-specific patterns. Positive reviews accounted for 75.81% of the corpus. Nighttime Tourism Experience attracted the greatest discussion, whereas Water-town Landscape Imagery received the most favorable evaluations. These principal patterns persisted across pandemic-related subperiods. Joint analysis revealed that similar textual profiles could accompany distinct photographic representations, while similar photographed features could coexist with different visitor concerns. The study contributes an interpretable method for identifying convergence and divergence between the two forms of evidence and extends the understanding of local distinctiveness within a shared regional cultural landscape. These findings support town-specific priorities for nighttime activity management, heritage interpretation, visitor services, and local business practices, linking visitor perception analysis with sustainable heritage tourism planning.

Authors

Institutions

Publication Details

Journal
Sustainability
Published
2026-11-19
DOI
https://doi.org/10.3390/su182211772
Primary Topic
Diverse Aspects of Tourism Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Cultural Landscapes and Sustainable Tourism Planning in Jiangnan Water Towns: Multimodal Evidence from User-Generated Content

Wenting Fang, 宋曜廷 Yao-Ting Sun
Sustainability
Diverse Aspects of Tourism Research
article

Cultural Landscapes and Sustainable Tourism Planning in Jiangnan Water Towns: Multimodal Evidence from User-Generated Content

Wenting Fang, 宋曜廷 Yao-Ting Sun
article en

Abstract

Sustainable heritage tourism requires understanding shared visitor experiences alongside local cultural distinctiveness. This study develops a comparative framework linking independently derived textual and visual profiles across 12 Jiangnan water towns. Using 33,383 reviews and 74,763 tourist photographs, latent Dirichlet allocation and RoBERTa identify textual themes and sentiment, while Qwen3-VL-8B-Instruct and keyword networks characterize photographic representations. Multiple factor analysis integrates five textual themes and seven visual dimensions to examine their shared and source-specific patterns. Positive reviews accounted for 75.81% of the corpus. Nighttime Tourism Experience attracted the greatest discussion, whereas Water-town Landscape Imagery received the most favorable evaluations. These principal patterns persisted across pandemic-related subperiods. Joint analysis revealed that similar textual profiles could accompany distinct photographic representations, while similar photographed features could coexist with different visitor concerns. The study contributes an interpretable method for identifying convergence and divergence between the two forms of evidence and extends the understanding of local distinctiveness within a shared regional cultural landscape. These findings support town-specific priorities for nighttime activity management, heritage interpretation, visitor services, and local business practices, linking visitor perception analysis with sustainable heritage tourism planning.

SustainabilityVol. 18(22)
Shanghai Dianji University (CN)
Diverse Aspects of Tourism Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon