Concept Analytics aims to understand human thinking by analysing conceptual layering in texts. We develop and apply innovative tools and techniques that combine both the distant reading of texts and corpus linguistic techniques to objectively identify suitable targets for analysis and subsequently analyse them. Our ideas embrace Digital Humanities thinking in that big data exploration works best when there is dialogue between different views and layers of data.
The things we write about and the words we use to do so hold the key to our conceptualisation of the world and everything in it. We attach primary importance to concepts as units of knowledge cognitively categorised on the basis of their importance in every-day life. We consider concepts embedded in language as units that provide a window into the human mind and thinking processes. The Concept Analytics Lab seeks to develop tools and apply corpus and socio-linguistic analysis techniques to reveal and visualise these very concepts.
Accessing conceptual information in big textual data requires expertise in both computational models of language as well as understanding of linguistic nuances. In this respect we position our intellectual efforts in making connections between the macro and micro of knowledge. This approach is highly valuable both on an academic but also industry [real world] level, as these state-of-the-art approaches to conceptualisation provides information to solve real world problems. Partnerships between academia and industry are key to ensure that our research has real impact – providing insight to inform business models and public policy. As has been seen in previous editions to our projects, industry involvement is essential and provides fertile ground for skills and knowledge sharing.
Identifying conceptual patterns and change in human thought through a combination of distant text reading and corpus linguistics techniques.
