Mood2Trip

In the current era of digital personalization, the tourism industry is increasingly shifting toward user-specific and emotionally intelligent solutions. Most traditional travel recommendation systems rely heavily on generalized indicators such as ratings and reviews. However, these approaches often overlook the traveler's current emotional state, which plays a critical role in influencing preferences and decision-making during travel planning. To address this limitation, the proposed model integrates sentiment analysis, spatial intelligence, and real-time data to deliver personalized and emotionally adaptive travel experiences. The system begins with emotional profiling using natural language processing techniques to identify the user's current mood. Based on the detected emotional state, destinations are recommended through a mood-to-destination mapping framework. Subsequently, a clustering algorithm organizes tourist attractions into day-wise clusters according to the optimal trip duration and the maximum travel distance permitted per day. Hotel recommendations are then retrieved and ranked using skyline computation based on proximity and cost, with additional personalization available through user-specified amenities.