Presentation of content is an important aspect of today’s virtual reality applications, especially in domains such as virtual museums. The large amount and variety of exhibits in such applications raise a need for adaptation and personalization of the environment. This paper presents a content personalization platform for Virtual Museums, which is based on a semantic description of content and on information implicitly collected about the users through their interactions with the museum. The proposed platform uses stereotypes to initialize user models, adapts user profiles dynamically and clusters users into similar interest groups. A science fiction museum has been set up as a case study for this platform and an evaluation has been carried out.