Recommendation system based on rule-space model of two-phase blue-red tree and optimized learning path with multimedia learning and cognitive assessment evaluation

Among the various indicators used by the Ministry of Education to assess the learning performance and competencies in Taiwan, a highly emphasized one for students in the vocational education system is the numbers of professional certification they have, which is also an important factor for vocational students to gain suitable job opportunities and to enhance their working competitiveness. As a result, the importance of obtaining professional certifications can never be over emphasized. Specifically, the numbers of certifications they obtained is highly related with the numbers of job opportunities they can expect. In this research, we propose a RS (Recommendation System) based solution. The proposed solution combines two-phase Blue-Red trees of Rule-Space Model and the optimized learning path, and is focused on remedying and analyzing the learning status of MTA courses with the goal of enhancing students’ pass rate of MTA certifications. In phase one, we then identify three SGs (Skill Groups) based on course information from the Certiport of Microsoft certification center, and the three SGs can be utilized for producing both concept maps and Blue-Red trees. In phase two, we classified ten chapters of MTA course into three SGs identified in phase one based on the similarities observed in the ten chapters and the three SGs. The three SGs will then be used for generating the needed concept maps and groups of Blue-Red trees. In this research, we generated three of each. The analysis is based on Rule-Space Mode for all learning objects in each skill group of phase two. For each pair of learning objects, we define the RW (Relation Weight) of them. From all learning paths, we calculate the Confidence Level values of each adjacent pairs of learning objects. Finally, we obtain the optimized learning path through the adoption of the inferred optimized learning path derivation algorithm from the combination of RW (Relation Weight) and CL (Confidence Level). It can be used in OCMLS (Online Course Multimedia Learning System) that recommended the optimized learning path of learning objects for learners to online self-learning, or to RS (Recommendation System) that provides the basis of self-learning remedies for RFRC (Recommended Form of Remedial Course). By adopting this recommendation system for giving guidance for students in preparing for the MTA (Microsoft Technology Associate) certification, we have observed good results in learning performance and pass rate.