User experiences in fishing tourism

This study aims to address the limited academic exploration of fishing tourism by means of Pine and Gilmore’s established experiential marketing model by analysing online reviews of fishing tourism activities on TripAdvisor. To do so, we use machine learning techniques combining supervised and unsupervised analysis and with graphic value, which favours decision-making for tourism operators. Our results highlight a clear emphasis on user satisfaction in the overall model, with a significant connection to the escapist sense of the experience. Unsupervised association analysis suggests that user enjoyment across experiential components positively influences satisfaction. It also allows to visualise the Fishing Tourism user's behaviour according to two types of activity: Charter Fishing Tourism, with an active presence of the escapist component, and Combined Fishing Tourism, characterised by a more passive integration – entertainment and aesthetic – of the user in the activity. The study concludes that improvements in one experiential realm can impact others. Methodologically, the use of AI for sentence-level analysis enhances the understanding of relationships between expressions and variables. The expanded model, incorporating new variables like tourism satisfaction and loyalty, reflects the complexity of the contemporary tourism industry.