Educational innovation is a field that has been greatly enriched by using technology in its processes, resulting in a leaing model where information comes from numerous sources and collaboration takes place among multiple students. One attractive challenge within educational innovation is the design of collaborative leaing activities from the social computing point of view, where collaboration is not limited to student-to-student relationships, but includes student-to-machine interactions. At the same time, there is a great lack of tools that give support to the whole leaing process and are not restricted to specific aspects of the educational task. In this paper, we present and evaluate context-aware framework for collaborative leaing applications (CAFCLA) as a solution to these problems. CAFCLA is a flexible framework that covers the entire process of developing collaborative leaing activities, taking advantage of contextual information and social interactions. Its application in the experimental case study of a collaborative WebQuest within a museum has shown that, among other benefits, the use of social computing improves the leaing process, fosters collaboration, enhances relationships, and increases engagement.