Measuring Inclusion in Interaction: Inclusion Analytics for Human-AI Collaborative Learning
This work addresses the need for process-oriented measurement of inclusion in collaborative problem-solving for AI and education researchers, but it is incremental as a proof-of-concept step.
The paper tackles the problem of measuring inclusion in human-AI collaborative learning by introducing inclusion analytics, a discourse-based framework that conceptualizes inclusion along three dimensions and demonstrates its application using simulated and empirical data to reveal patterns invisible to traditional methods.
Inclusion, equity, and access are widely valued in AI and education, yet are often assessed through coarse sample descriptors or post-hoc self-reports that miss how inclusion is shaped moment by moment in collaborative problem solving (CPS). In this proof-of-concept paper, we introduce inclusion analytics, a discourse-based framework for examining inclusion as a dynamic, interactional process in CPS. We conceptualize inclusion along three complementary dimensions -- participation equity, affective climate, and epistemic equity -- and demonstrate how these constructs can be made analytically visible using scalable, interaction-level measures. Using both simulated conversations and empirical data from human-AI teaming experiments, we illustrate how inclusion analytics can surface patterns of participation, relational dynamics, and idea uptake that remain invisible to aggregate or post-hoc evaluations. This work represents an initial step toward process-oriented approaches to measuring inclusion in human-AI collaborative learning environments.