Sentiment analysis of visitor perceptions on architectural heritage: a case study of Phoenix Ancient Town for sustainable conservation and development

With the growth of tourism and social media, understanding visitor perceptions of destinations has become essential for tourism management and planning. Built heritage, as a cultural asset and tourist attraction, plays a significant role in sustainable urban development, but there is a research gap...

Full description

Saved in:
Bibliographic Details
Main Authors: Hao Yuan, Rui Ke, Xubin Xie
Format: Article
Language:English
Published: Taylor & Francis Group 2025-08-01
Series:Journal of Asian Architecture and Building Engineering
Subjects:
Online Access:http://dx.doi.org/10.1080/13467581.2025.2540079
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the growth of tourism and social media, understanding visitor perceptions of destinations has become essential for tourism management and planning. Built heritage, as a cultural asset and tourist attraction, plays a significant role in sustainable urban development, but there is a research gap in exploring visitor perceptions of historic districts, particularly through fine-grained sentiment analysis using social media data. Fine-grained sentiment analysis, which examines both sentiment polarity and intensity, allows for a deeper understanding of visitor experiences by capturing the nuanced emotional responses of visitors to specific aspects of the destination. Conventional survey-based approaches often fail to capture the complexity and real-time nuances of visitor sentiments, necessitating advanced AI-driven methodologies. This study introduces a cascaded deep learning framework that first identifies key aspects of visitor experiences and then classifies their sentiment polarity and intensity. The results demonstrate the model’s effectiveness in providing detailed insights into visitors’ perceptions and satisfaction, offering data-driven recommendations for the conservation and optimization of historic districts. The innovation of this study lies in its integration of multi-task learning for fine-grained sentiment analysis, contributing valuable insights for heritage tourism management.
ISSN:1347-2852