A Content-Based Recommendation System for Leisure Activities

People’s selection of leisure activities is a complex choice because of implicit human factors and explicit environmental factors. Satisfactory participation in leisure activities is an important task since keeping a regular active lifestyle can help to maintain and improve the wellbeing of people. Technology could help in selecting the most appropriate activities by designing and implementing activities, collecting people profiles and their preferences relations. In fact, recommendation systems, have been successfully used in the last years in similar tasks with different types of recommendation systems. This thesis aims at the design, implementation, and evaluation of recommendation systems that could help us to better understand the complex choice of selecting leisure activities. In this work, we first define an evaluation framework for different recommendations systems. Then we compare their performances using different evaluation metrics. Thus, we explore and try to better understand the user’s preferences over leisure activities. After, having a comprehensive analysis of modelling recommended items and leisure activities, we also design and implement a content-based leisure activity recommendation system to make use of a taxonomy of activities. Moreover, in the course of our research, we have collected and evaluated two datasets obtained one from the Meetup social network and the other from crowd-workers and made them available as open data sources for further evaluation in the recommendation system research community.