Vectors, Planes and Context

Information Retrieval (IR) models based on vector spaces have been investigated for a long time. Nevertheless, they have recently attracted further research interest beyond the classical statistical view of vectors and matrices. Moreover, “context” has been recognized as a crucial component of IR systems. As the way context affects IR systems is very complex, a principled approach to modeling and ranking can be useful for designing innovative context-aware systems. This paper presents an approach to modeling and ranking information objects in context using vector spaces thereby introducing a new perspective of context-aware IR.