Ontological analysis for dynamic data model exploration

Increasing access to data and computational resources allows use to use more expressive approaches to data analysis. We propose using established statistical metrics to assist the automatic analysis of free text transcripts. The meaningful concepts from a domain and their axiomatic relationships can be captured in an ontology. This provides an aggregate model which describes the domain. However, the fine detail from individual elements and their characteristics are subsumed by the whole. Keeping multiple 'micro models' of the data, along with meta information allows a range of different view points. This can be applied to free text documents that within a domain where significant information is carried by one or a few instances such as in the analysis of interview transcripts. This paper presents a framework that utilises ontological tools to create domain models in a way that it allows for a distributed and parallel implementation necessary for big data analysis.