Recommender systems are used to predict what a user might like in the future. In the cultural field using those systems raises the question of diversity, novelty, and discovery. The human being is fond of stability, but he is not against breaking his routine and explore things out of his comfort zone. In this context we created a method, based on dissimilarity measure between cultural items, which expands the cultural knowledge of users. We have been able to delimit an intermediate zone between “too similar” and “too different”. We have developed an application which allows us to test andvalidate this method. We explain the concept of “intermediate zone”, wepresent the mobile application, its functionalities, and some tests we carried out.