ON EVALUATION OF QUALITY AND SUITABILITY OF LEARNING PATHS TO STUDENTS’ PERSONAL NEEDS
1 Vilnius University / Vilnius Gediminas Technical University (LITHUANIA)
2 Vilnius University (LITHUANIA)
About this paper:
Conference name: 8th International Conference on Education and New Learning Technologies
Dates: 4-6 July, 2016
Location: Barcelona, Spain
Abstract:The main aim of the paper is to analyse and propose a novel probabilistic model to evaluate the quality of personalised learning paths (scenarios), i.e. their suitability to particular students according to their learning styles. In the paper, the authors: first, perform systematic literature review on scientific methods and techniques on evaluating the quality of personalised learning paths (scenarios) and other learning components, and second – present an original research methodology and some examples of evaluating the quality and suitability of learning paths to particular students’ needs. Expert evaluation method based on multiple criteria decision making approach is applied in the research. Students’ learning styles are analysed according to Felder-Silverman learning styles model. Students’ learning styles are necessary to create learning paths that should be optimal for particular learners. These learning paths should consist of suitable learning components (learning objects, learning methods and activities, virtual learning environments: learning tools, apps etc.) optimal to particular students according to their learning styles. Original probabilistic model is presented and applied to establish not only students’ learning styles but also probabilistic suitability of inquiry-based learning activities to students’ learning styles. An example of personalised learning path based on original intelligent software agent is presented in more detail. Examples of the expert evaluation of the quality of learning paths and suitability to students’ learning styles are also presented in the paper.
Keywords: Evaluation of student learning, personalised learning, learning styles, probabilistic model, learning paths.