Adaptive learning module for a conversational agent to support MOOC learners

Abstract

Massive open online courses (MOOCs) pose a challenge for instructors when trying to provide personalised support to learners, due to large numbers of registered participants. Conversational agents can be of help to support learners when working with MOOCs. This article presents an adaptive learning module for JavaPAL, a conversational agent that complements a MOOC on Java programming, helping learners review the key concepts of the MOOC. This adaptive learning module adapts the difficulty of the questions provided to learners considering their level of knowledge using item response theory (IRT) and also provides recommendations of video fragments extracted from the MOOC for when learners fail questions. The adaptive learning module for JavaPAL has been evaluated showing good usability and learnability through the system usability scale (SUS), reasonably suitable video fragments recommendations for learners, and useful visualisations generated as part of the IRT-based adaptation of questions for instructors to better understand what is happening in the course, to design exams, and to redesign the course content. Implications for practice or policy: • A conversational agent that adapts the questions provided to learners using Item Response Theory (IRT) can be helpful for learners to review the concepts of a MOOC. • A conversational agent that provides video fragments recommendations can be helpful for learners to improve their performance when answering questions from a MOOC. • IRT-based visualisations of item characteristic curves and item information curves can be helpful to redesign the contents of a MOOC.