Decoding tourist satisfaction for sustainable economic development: a multi-method configuration framework using online reviews
利用在线评论，结合文本挖掘、情感分布计算和模糊集定性比较分析，构建了一个多方法框架，识别出驱动高游客满意度的属性组合模式，为旅游目的地和企业提供长期经济效益的指导。
Online reviews are crucial to understanding tourist satisfaction (TSA) in the digital tourism era. This study deconstructs the factors leading to high TSA performance in reviews, offering guidance for long-term economic benefits for destinations and businesses. Building on the three-factor theory, we create a framework utilizing text mining, affective distribution computing, and fuzzy-set qualitative comparative analysis (fsQCA) to identify patterns driving high TSA. We employ topic modeling to extract destination attributes from reviews, quantifying their performance through affective distribution computing. An enhanced Kano model classifies tourist needs based on emotional expressions in reviews. We investigate how basic, performance and excitement attributes interact and influence TSA. Additionally, we apply the coupling coordination degree model (CCDM) to analyze attribute interconnections within configurations. Our results show that no single attribute leads to specific outcomes; relatively, high TSA results from a combination of attributes. This study identifies three normative causal recipes and is the first to clarify the complex interactions in satisfaction management within the three-factor theory framework, addressing a significant knowledge gap. Ultimately, our operational guidelines aim to sustain the economic vitality of the tourism industry. First published online 14 July 2025