A Hybrid Tourism Recommendation System with Modified Similarity and Weighted Popularity Scores

Obtaining valuable and accurate tourism information can become an overwhelming and time-consuming task to tackle given the vast pool of options available to the consumer. Having a plethora of options with no clear guidelines on how to manage and narrow down choices presents a challenge that can be unwanted for many looking to plan trips and activities in the future. Tourists often spend hours researching different destinations and may still not find the perfect match. Creating a streamlined option to eliminate these issues is, therefore, a worthwhile endeavor. A tourism recommendation system provides a solution by providing tourists with personalized recommendations that are tailored to their specific needs. Recommendation systems, or recommender systems, are a class of artificial intelligence and big data designed to suggest items to users based on prior opinions and preferences, product engagement, and interactions. This can save tourists time and money, and it can help them to have a more enjoyable and memorable travel experience. In this work, we develop a recommender system for Ghanaian tourism websites to provide personalized recommendations to users based on their travel preferences, behavior, and tastes. A combination of collaborative filtering and content-based filtering algorithms have been utilized for this work. This hybrid approach combines the advantages of both methods to create an improved recommendation system. The results obtained ascertain the efficiency of our proposed method.