Constraint-Based Validation of Adaptive e-Learning Courseware

Abstract

Personalized e-learning allows the course creator to create courseware that dynamically adapts to the needs of individual learners or learner groupings. This dynamic nature of adaptive courseware makes it difficult to evaluate what the delivery time courseware will be for the learner. The course creator may attempt to validate adaptive courseware through dummy runs, but cannot eliminate the risk of pedagogical problems due to adaptive courseware's inherent variability. Courseware validation checks whether adaptive courseware conforms to a set of pedagogical and nonpedagogical requirements. The validation of adaptive courseware limits the risk of pedagogical problems at delivery time. In this paper, we present our approach to adaptive courseware validation using the Courseware Authoring Validation Information Architecture (CAVIAr). We outline how CAVIAr captures adaptive courseware authoring concerns and validates courseware using a constraint-based approach. We also describe how CAVIAr can be integrated with the state of the art in adaptive e-learning and evaluate our validation approach.

Learning SQL with Artificial Intelligent Aided Approach

“…The most acclaimed ITS systems evolved through the history are cognitive tutors [11], [12] followed by approaches, based on constraint-based modelling [3], [13], [14] or the principle of constructing student models with machine learning techniques [6], [15].…”

“…SQL-Tutor [3] is an important representative of CBM system. A significant amount of time is needed to define rules and constraints for cognitive tutors and CBM systems to become useful [14], [21], [22]. To some extent, AI methods can be used to automatically generate set of rules and constraints, if there is enough data about specific domain to learn from [13], [22].…”

Recommender system for learning SQL using hints

“…The most acclaimed ones are cognitive tutors (Anderson et al, 1995;Kunmar, 2002). Later approaches are based on either constraint-based modelling (CBM) (Melia and Pahl, 2009;Mitrovic et al, 2013), a philosophy which helps students to learn from their errors, or they construct student models using machine learning techniques (Smith-Atakan and Blandford, 2003;Stein et al, 2013) to automate the rule generation in the construction of ITS.…”

Learning Path Construction Based on Association Link Network

“…However, the method in addition performs a query rewriting based on student profiles, which describe student learning preferences and learning performance (which indicate student knowledge level), such that students only need to focus on what they want to learn and the system will take care of the suitability of every LR, which matches the student searching criteria. [9] proposes a more comprehensive modeling of LRs, where each of them is designed to associate with a concept, a knowledge type (verbal information or intellectual skills), and a knowledge level. LRs are connected based on concept relationships, where teachers manually define prerequisite among concepts.…”

“…Identifying relevant LRs is essential to learning path [11] generation. Existing work determine such a relevancy by matching student specific requirements, including topics to learn, learning preferences or constraints [4,3] against the characteristics of LRs, which can be maintained by a list of attributes, such as related topic and difficulty level, or additionally by a structure that defines how LRs are related among each other [9]. Learning path generation methods aim at arranging selected LRs into a proper sequence for delivering to students, such that they can learn effectively in terms of minimizing the cognitive workload.…”