Lyme disease is a zoonotic disease that poses a new public health problem in urbanized areas where increasingly large numbers of people attend urban forests and park settings. Understanding spatial patterns of human risk of exposure to Lyme disease is critical to target prevention, control, and surveillance actions. To this end, we adopt a geographic approach where the extent of the exposure is related to the type, frequency, and duration of a person's activities in a tick-infested environment. To extract visitors’ typical behavior patterns, we used questionnaires and web mapping tools to collect data about visitors’ activities in Forollect data about visitorsdopt a geographic approach where the extent of the, we propose a formal approach to model activity patterns and present a method to automatically extract them from collected data. Our pattern extraction tool can be used to assess at-risk behaviors of certain categories of visitors, which can help public health authorities implement preventive actions.