I. Introduction
The analysis and discovery of relations between human learning and contextual factors that influence these relations have been one of the contemporary and critical global challenges facing researchers in a number of areas, particularly in Education, Psychology, Sociology, Information Systems, and Computing. Traditionally, these relations concern learner performance and the effectiveness of the learning context from summative and formative points of view. Be it the assessment marks distribution in a classroom context or the mined pattern of best practices in an apprenticeship context, analysis and discovery have always addressed the elusive causal question about the need to best serve learners' learning efficiency. Learning efficiency encompasses any and all aspects that concern “learning” of individual learners or groups of learners. Examples of learning efficiency aspects include learning style, metacognitive scaffolds, peer interactions, self-regulation, co-regulation, social networking, and other learning-oriented activities and characteristics associated with learners. With the advent of new technologies such as eye-tracking, activities monitoring, video analysis, content analysis, sentiment analysis and interaction analysis, one could potentially collect “continuous data”, in addition to formative and summative data. Continuous data is different from the other two in terms of its incessant arrival from direct observations of a learning activity and other activities related to that learning activity. For example, assessment of a submitted essay by a student offers summative data. Observing the development of the essay that assists the learner (or the teacher) in making targeted decisions about the quality of the essay being written offers formative data. This data can be obtained at real time and can be used to classify each student's progress in a learning task and to develop a model of growth of competency, say in writing essays. The volume and arrival rate of continuous data leads to big data learning analytics.