Learning is the subjective process of acquiring knowledge and skills. Defining an optimal learning pathway that would fit everybody is not possible nor would be effective, since it is generally recognized that different learning styles and tools fit the needs, backgrounds, competencies and personalities of different persons. Tailoring the learning process so as to meet the needs of each learner is a significant concept that can improve education and enhance social skills. However, personalization of learning using conventional ways, e.g. book-based learning, has been the exclusive privilege of merely a tiny subset of people who could afford the accompanying cost of such a service. Even in this case though, the personalized service is far from being optimal and individualized due to inherent constraints of traditional face-to-face tutoring, e.g. limited available time, lack of devotion, etc.
Recent advances in ICT have enabled the widespread use of personalized learning. In this context, a number of virtual labs, emulating real lab environments, where users can accomplish a number of learning tasks and conduct various experiments with no cost or risk, have been recently developed. Online virtual labs have the potential to revolutionize the educational landscape by providing students with distance courses and curricula that otherwise would be difficult, if not infeasible, to be offered. The main challenge with such tools is to find effective and innovative ways to boost the learning experience and motivate the students to engage with the learning system, preventing them from churning out.
To this end, ENVISAGE aims to develop an authoring environment for virtual lab design and development, which, equipped with data analytics methods and visualization tools that have been developed and reached maturity in the gaming industry, is suitable for iteratively evolving the design of virtual labs and for dynamically adapting the learning content to users. In reaching this goal, ENVISAGE migrates knowledge from the digital games domain, with the intention to track learners behavioral data and model the students’ current behavior, predict their future behavior, and recognize the weaknesses and strengths of the learning path. Learning analytics are used to facilitate decision-making during the design of a lab by an educator and also support content adaptation to the personal needs and requirements of students
