This paper introduces a methodological and computational framework that integrates temporal network analysis, cognitive load (CL) theory, and metacognitive (MC) research to model how humans learn and adapt during artificial intelligence (AI) mediated conversations. The proposed approach defines a unified architecture and a functional platform capable of estimating CL and MC awareness directly from conversation transcripts, without the need for specialized sensors or intrusive measurements. Rather than focusing on empirical validation, the work establishes the conceptual foundations, data processing pipeline, and visual analytics components required to investigate cognitive–metacognitive dynamics in dialog-based learning. The framework opens new perspectives for designing adaptive educational chatbots, cognitively aware conversational systems, and analytical tools to study learning and collaboration in human–AI interactions.