Purpose – This paper aims at describing the role of a developed Recommender System in a Virtual Collective Intelligence Environment. The analysis of different types of data, such as social network data or users’ behaviours, are very useful to delineate people customs and interests. Such information are necessary for the Recommender System, which is based on similarity and on a system that associates resources to users in a personalized way. Therefore, the analysis and processing of these data become tools to power the Recommender System, to suggest items closely related to users and to create social communities of people with similar interests. Design/methodology/approach – This paper is based on the study of literature and the analysis of possible scenarios applicable in the context of a Virtual Collective Intelligence Environment. Such virtual environment is based on the principle of Enterprise Social Software, which supports a series of actions and operations related to the management of information and knowledge. The approach based on Collective Intelligence and on social software aims specifically at the integration of explicit knowledge with the implicit one and the simultaneous extraction, derivation and determination of new knowledge, through techniques of mining, search, clustering, Recommender Systems, and so on. Originality/value – In VINCENTE Environment, the proposed Recommender System uses and analyses both social network data and people behaviours with the aim of suggesting items that are closely related to users and of creating social communities based on similar interests. The Recommender System adopts a similarity function, specifically designed to calculate both network and profile similarity between users by using social network data, taking into account all the connections between users. This approach brings many benefits, as the cold start problem prevention for new users. Moreover, by employing a fuzzy graph to establish a connection between different items, it is possible to recommend different resources, also favouring serendipitous discovery. Practical implications – This work can have different implications, such as: Applications of the Recommender System in scenarios in which services such as those ones related to the search of users in the community, to the logic of collaborative working or to the business are implemented. Applications of the Recommender System to virtual platforms with different purposes. Applications of the Recommender System to mobile app, aiming at advising users on relevant resources and information by predicting their interests and preferences on a specific item.