Supporting students through notifications about importance in academic lectures

Abstract

Identifying and extracting important information from monologic interaction is a difficult task for humans and modelling this for an intelligent system is a big challenge. In our work, we have previously used models that are grounded in semiotic, linguistic and psychological theories of multi-modal interaction. Here, we concentrate on academic lectures as a specific form of monologic interaction. Our goal is to support students through a system alerting them to important aspects of a lecture. In this paper, we outline the requirements that went into an early implementation of the system. We discuss a rich contextual model and what this entails for modelling requirements and system implementation. We provide an overview of the system and discuss our notion and role of context within the application domain.