Identification of personal traits in adaptive learning environment: Systematic literature review

• Main Authors: Afini Normadhi, Nur Baiti, Shuib, Liyana, Md Nasir, Mohd Hairul Nizam, Bimba, Andrew, Idris, Norisma, Balakrishnan, Vimala
• Format: Article
• Published: Elsevier 2019
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://eprints.um.edu.my/20143/; https://doi.org/10.1016/j.compedu.2018.11.005

An adaptive learning environment provides personalised information to the learner through self-directed study. An adaptive learning environment model can be subdivided into a learner model, domain model, instructional model and adaptive engine. Personal traits comprise part of the components in a learner model and can be identified either explicitly or implicitly in an adaptive learning environment. In such an environment, the e-learning system should adapt to a learner's needs. However, even though academic research on adaptive learning environments has increased, the field lacks a comprehensive literature analysis of learners’ personal traits in these environments. This study conducts a systematic literature review to identify the most commonly used personal traits in modelling the learner and the existing techniques suitable for identifying personal traits in an adaptive learning environment. A total of 140 articles spanning the years 2010–2017 are initially reviewed, from which 78 are selected based on the inclusion and exclusion criteria relevant to this study. This study provides an overview of learners’ personal traits and the techniques used to identify them to provide a basis for improving adaptive learning environments. The findings indicate that most of the previous works used a learning style from the cognition learning domain category to model individual personal traits, while the computer-based detection technique was commonly applied to identify a learner's personal traits in adaptive learning environments. This study reveals the common learner characteristics used to develop learner models and the techniques for implementing such models. The findings of this paper can guide other researchers to recognise various personal traits and the identification technique for further studies, as well as assist developers in the development of the adaptive learning system.