In recent years, recommender systems have achieved a great success. Popular sites like Amazon.com and CDNow give thousands of recommendations every day. However, although many activities are carried out in groups, like going to the theater with friends, these systems are focused on recommending items for individual users. This brings out the need of systems capable of performing recommendations for groups of people, a domain that has received little attention in the literature. In this article we introduce an investigation of automatic group recommendations, making connections with problems considered in social choice and psychology. Then we suggest a novel method of making recommendations for groups, based on existing techniques of collaborative filtering and classification of alternatives using fuzzy majority. Finally we experimentally evaluate the proposed method to see its behavior under groups of different sizes and degrees of homogeneity.