A Literature Review on Learner Models for MOOC to Support Lifelong Learning Sergio Iván Ramírez Luelmo a , Nour El Mawas b and Jean Heutte c CIREL - Centre Interuniversitaire de Recherche en Éducation de Lille, Université de Lille, Campus Cité Scientifique, Bâtiments B5 – B6, Villeneuve d’Ascq, France Keywords: Learning Analytics, Knowledge Representation, Technology Enhanced Learning, Lifelong Learning, Learner Model, Learning Environment, Literature Review, MOOC. Abstract: Nowadays, Learning Analytics is an emerging topic in the Technology Enhanced Learning and the Lifelong Learning fields. Learner Models also have an essential role on the use and exploitation of learner-generated data in a variety of Learning Environments. Many research studies focus on the added value of Learner Models and their importance to facilitate the learner’s follow-up, the course content personalization and the trainers/teachers’ practices in different Learning Environments. Among these environments, we choose Massive Open Online Courses because they represent a reliable and considerable amount of data generated by Lifelong Learners. In this paper we focus on Learner Modelling in Massive Open Online Courses in an Lifelong Learning context. To our knowledge, currently there is no research work that addresses the literature review of existing Learner Models for Massive Open Online Courses in this context in the last five years. This study will allow us to compare and highlight features in existing Learner Models for a Massive Open Online Course from a Lifelong Learning perspective. This work is dedicated to MOOC designers/providers, pedagogical engineers and researchers who meet difficulties to model and evaluate MOOCs’ learners based on Learning Analytics. 1 INTRODUCTION Massive Online Open Courses (MOOC) have proliferated in the last decade all around the world. Their global reach and popularity steams from their original concept to offer free and open access courses for a massive number of learners from anywhere all over the world (Yousef et al., 2014). However, despite their global reach, popularity and often low- to-none costs, they have very low completion rates (Yuan & Powell, 2013; Jordan, 2014) with research metrics agreeing at median of about 6.5%. As this percentage increases and tops to about 60%, a ten- fold difference, for fee-based certificates, studies of both cases show that engagement, intention and motivation (Jung & Lee, 2018; Wang & Baker, 2018; Watted & Barak, 2018) are among the top factors to a https://orcid.org/0000-0002-7885-0123 b https://orcid.org/0000-0002-0214-9840 c https://orcid.org/0000-0002-2646-3658 1 e.g. course-shopping, dabbling topic courses, auditing knowledge on the material and on its difficulty level, etc. affect performance in MOOCs. DeBoer, Ho, Stump, & Breslow (2014) confirm the multifactor complexity of this phenomena by concluding that MOOC participants have reasons to enrol other than course completion 1 . We extend this affirmation by attributing a part of this phenomena to the obvious heterogenous nature of these new global learners and their heterogenous learning needs; a situation also highlighted by M. L. Sein-Echaluce et al. (2016). Thus, improving academic success in MOOCs by increasing the learning outcome and the average completion rate of learners creates the need to personalize content and learning paths by modelling the learner (El Mawas et al., 2019). Research studies (Bodily et al., 2018; Corbet & Anderson, 1995) focus on the added value of Learner Models (LM) and their importance to facilitate the learner’s follow-up, the Luelmo, S., El Mawas, N. and Heutte, J. A Literature Review on Learner Models for MOOC to Support Lifelong Learning. DOI: 10.5220/0009782005270539 In Proceedings of the 12th International Conference on Computer Supported Education (CSEDU 2020) - Volume 1, pages 527-539 ISBN: 978-989-758-417-6 Copyright c  2020 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved 527