Contextual Based E-Tourism Application: A Personalized Attraction Recommendation System for Destination Branding and Cultivating Tourism Experiences

Abstract

This research introduces an innovative automated application designed to offer users personalized attraction recommendations tailored to their interests and current situations. Utilizing a contextual model and advanced machine learning techniques, the system constructs a comprehensive user profile by considering factors like historical behavior, current context, and demographic data. This approach addresses limitations observed in conventional personalized recommendation systems, including challenges in suggesting attractions for new users, providing comparable recommendations, and incorporating appropriate weighting. By integrating multi-dimensional user models based on context, the system enhances the platform's personalization and adaptability, ultimately contributing to the augmentation of Destination Branding and the cultivation of enriched Tourism. The research yields practical solutions for optimizing tourism services' personalization and introduces improvements in e-tourism recommender systems, carrying significant implications for both industry practitioners and academic researchers.