A GRAPH-BASED CLUSTERING AND LARGE LANGUAGE MODEL-ENHANCED ASPECT-BASED SENTIMENT ANALYSIS FRAMEWORK FOR MODELING PASSENGER SATISFACTION IN EUROPEAN CRUISE ITINERARIES
This study highlights the effectiveness of the GPT-4o mini large language model in extracting nuanced sentiment from informal online reviews and identifies the most and least satisfying cruise regions in Europe based on customer feedback, while providing an aspect×region knowledge map for decision support.