Fuzzy context adaptation through conceptual situation spaces

Context-adaptive information systems (IS) are highly desired across several application domains and usually rely on matching a particular real-world situation to a finite set of predefined situation parameters. To represent context parameters, semantic and non-semantic representation standards are widely used. However, describing the complex and diverse notion of specific situations is costly and may never reach semantic completeness. Whereas not any situation parameter completely equals another, the number of (predefined) representations of situation parameters is finite. Moreover, following symbolic representation approaches leads to ambiguity issues and does not entail semantic meaningfulness. Consequently, the challenge is to enable fuzzy matchmaking methodologies to match real-world situation characteristics to a finite set of predefined situation descriptions. In this paper, we propose conceptual situation spaces (CSS) which enable the description of situation characteristics as members in geometrical vector spaces following the idea of conceptual spaces. Consequently, fuzzy matchmaking is supported by calculating the semantic similarity between the current situation and prototypical situation descriptions in terms of their Euclidean distance within a CSS. Aligning CSS to existing symbolic representation standards, enables the automatic matchmaking between real-world situation characteristics and symbolic parameter representations. To prove the feasibility, we apply our approach to the domain of e-learning.