Visitor-Discourse-Informed Narrative Planning for Heritage Regeneration: A Single-Site Demonstration in Lijiang

Heritage regeneration requires a defensible translation of visitor discourse into site-specific planning choices. This study presents a single-site planning demonstration at Lion Hill in Lijiang Old Town, informed by 3849 destination-level Ctrip texts published between June and December 2025. The workflow integrates latent Dirichlet allocation, narrative interpretation, semantic–behavior–function mapping, functional salience assessment, a researcher-led site and heritage audit, and generative-AI visualization. Nine topic interpretations were mapped to six candidate-function categories. Functional salience was assessed by combining topic prevalence with within-topic component weights calculated through frequency normalization following researcher-reviewed semantic mapping. T6 was interpreted as visual and affective experience, with photographic activity representing a limited component of its retained vocabulary. The site audit assigned photography a supporting role within the cultural program. The broader sensitivity analyses showed that the cultural category’s baseline lead persisted under ±10% relative weight perturbations but could change under wider perturbations or conservative treatment of T7’s historical and cultural references. All 48 generated candidates underwent five-criterion assessment and three-stage screening, with six selected outputs and twelve non-selected examples examined in detail. Expert rating profiles and image-level comparison identified differences in spatial readability, functional expression, cultural representation, and correspondence with the scenario briefs. The study offers a structured workflow that distinguishes discursive salience from planning priority and links semantic interpretation, site and heritage review, and AI-generated scenario analysis. This integration makes the assumptions underlying candidate uses explicit and offers potential for transfer to other heritage-regeneration settings through adaptation to local discourse, building conditions, and conservation requirements.

Authors

Institutions

Publication Details

Journal
Buildings
Published
2026-11-16
DOI
https://doi.org/10.3390/buildings16224555
Primary Topic
Cultural Heritage Management and Preservation
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Visitor-Discourse-Informed Narrative Planning for Heritage Regeneration: A Single-Site Demonstration in Lijiang

Haozun Sun, Nan Zhang, Yifan Wang
3 links
Buildings
Cultural Heritage Management and Preservation
article

Visitor-Discourse-Informed Narrative Planning for Heritage Regeneration: A Single-Site Demonstration in Lijiang

Haozun Sun, Nan Zhang, Yifan Wang
article en

Abstract

Heritage regeneration requires a defensible translation of visitor discourse into site-specific planning choices. This study presents a single-site planning demonstration at Lion Hill in Lijiang Old Town, informed by 3849 destination-level Ctrip texts published between June and December 2025. The workflow integrates latent Dirichlet allocation, narrative interpretation, semantic–behavior–function mapping, functional salience assessment, a researcher-led site and heritage audit, and generative-AI visualization. Nine topic interpretations were mapped to six candidate-function categories. Functional salience was assessed by combining topic prevalence with within-topic component weights calculated through frequency normalization following researcher-reviewed semantic mapping. T6 was interpreted as visual and affective experience, with photographic activity representing a limited component of its retained vocabulary. The site audit assigned photography a supporting role within the cultural program. The broader sensitivity analyses showed that the cultural category’s baseline lead persisted under ±10% relative weight perturbations but could change under wider perturbations or conservative treatment of T7’s historical and cultural references. All 48 generated candidates underwent five-criterion assessment and three-stage screening, with six selected outputs and twelve non-selected examples examined in detail. Expert rating profiles and image-level comparison identified differences in spatial readability, functional expression, cultural representation, and correspondence with the scenario briefs. The study offers a structured workflow that distinguishes discursive salience from planning priority and links semantic interpretation, site and heritage review, and AI-generated scenario analysis. This integration makes the assumptions underlying candidate uses explicit and offers potential for transfer to other heritage-regeneration settings through adaptation to local discourse, building conditions, and conservation requirements.

BuildingsVol. 16(22)
Central South University (CN)
National Natural Science Foundation of China
Sustainable cities and communities
Cultural Heritage Management and Preservation
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