Comparative analysis of personalisation approaches and tools to improve learning used in different learning systems

Abstract

The aim of the paper is to present learning system based on open authoring (Graasp) and sharing (Golabz) platforms developed in Next-Lab project and compare its personalisation approach and tools to improve learning with personalisation approach and tools developed by Lithuanian multi-agent learning system created in Vilnius Gediminas Technical University. The Next-Lab project (Next Generation Stakeholders and Next Level Ecosystem for Collaborative Science Education with Online Labs) is a European research project funded by Horizon 2020 focusing on introduction of Inquiry-Based Science Education in schools. The philosophy and technology of Next-Lab base on its previous project Go-Lab, and will continue its mission of promoting innovative and interactive methods of teaching science in primary and secondary schools across Europe. In Next-Lab, personalisation of Inquiry Learning Spaces (ILSs) is supported in Go-Lab Repository (GoLabz) by enabling teachers to share, reuse and modify ILSs created by colleagues. Typically, the learning content can be personalised by customising phases as well as the instructions and items they contain (e.g. images, files, links, apps). In particular, it’s detailed how apps contained in the ILSs can be personalised through their configurations to fit particular learning scenarios. A basic recommender system for labs and apps is also provided to support this process. Personalisation of labs and apps, especially at the level of internationalisation and terminology is supported by the App composer. Individual or collaborative personalisation of apps (in context and content) by teachers (co-)creating an ILS for their own students and supported in the Platform (Graasp) and in the apps themselves. Lithuanian multiagent learning system in terms of its personalisation approach and tools will be also presented in the paper. The paper is organised as follows: (1) systematic review on research topic, (2) analysis of personalisation approaches, features and tools used in Next-Lab learning system and Lithuanian multi-agent learning system, (3) comparative analysis of personalisation possibilities provided by both systems to improve learning, and (4) discussion and conclusion. The work presented in this paper is partially supported by the European Commission under Horizon 2020 research and innovation programme – as part of the Next-Lab project (Grant Agreement Number No 731685).