In open environments like the Web, and open Multiagent and Peer2Peer systems, consent among the autonomous, self-interested knowledge sources and users very often cannot be established, and the estimation of trustability and truthfulness of knowledge sources may not be possible. Moreover, competing viewpoints and their communicative contexts even provide valuable meta-knowledge about the intentions of the participants and their social relationships. As a foundational approach to semantically heterogeneous knowledge perspectives, we introduce a formal framework for the computational representation and integration of multi-source knowledge, which makes explicit heterogeneous viewpoints, and conflicting opinions and their social contexts, and allows for the rating, generalization and optional fusion of knowledge by social choice.