From Theory to Behaviour: Towards a General Model of Engagement
This work addresses the challenge of making engagement measurable for applications in data-driven methods and industry, though it appears incremental by building on previous theory-inspired approaches.
The authors tackled the problem of operationalizing the fuzzy concept of engagement by linking it to human behavior, proposing the Melchoir Model as a new modeling technique to better model engagement processes. They illustrated how machine-learned models can be linked to theoretical frameworks through model comparison and inspection.
Engagement is a fuzzy concept. In the present work we operationalize engagement mechanistically by linking it directly to human behaviour and show that the construct of engagement can be used for shaping and interpreting data-driven methods. First we outline a formal framework for engagement modelling. Second we expanded on our previous work on theory-inspired data-driven approaches to better model the engagement process by proposing a new modelling technique, the Melchoir Model. Third, we illustrate how, through model comparison and inspection, we can link machine-learned models and underlying theoretical frameworks. Finally we discuss our results in light of a theory-driven hypothesis and highlight potential application of our work in industry.