It is difficult for e-learners to make decisions on how to learn when they are facing with a large amount of learning resources, especially when they have to balance available limited learning time and multiple learning objectives in various learning scenarios. This research presented in this paper addresses this challenge by proposing a new multi-constraint learning path recommendation algorithm based on knowledge map. The main contributions of the paper are as follows. Firstly, two hypotheses on e-learners’ different learning path preferences for four different learning scenarios (initial learning, usual review, pre-exam learning and pre-exam review) are verified through questionnaire-based statistical analysis. Secondly, according to learning behavior characteristics of four types of the learning scenarios, a multi-constraint learning path recommendation model is proposed, in which the variables and their weighted coefficients considers different learning path preferences of the learners in different learning scenarios as well as learning resource organization and fragmented time. Thirdly, based on the proposed model and knowledge map, the design and implementation of a multi-constraint learning path recommendation algorithm is described. Finally, it is shown that the questionnaire results from over 110 e-learners verify the effectiveness of the proposed algorithm and show the similarity between the learners’ self-organized learning paths and the recommended learning paths.
The main contributions of this paper are as follow.
(1)Based on the collected questionnaires, we have obtained learners’ self-organized learning paths in four basic learning scenarios (initial learning, usual review, pre-exam learning and pre-exam review) and their ratings on the recommended learning paths. The analysis of the results based on these collected questionnaires proves following two hypotheses:
•Hypothesis I: A learner has different learning path requirements in different learning scenarios.
•Hypothesis II: Different learners have similar learning path requirements in a same learning scenario.
E-learners’ different learning path preferences for four different learning scenarios are verified via the proof of the two hypotheses.
(2)A multi-constraint learning path recommendation model based on a linear weighted formula is proposed to meet the learners’ different learning path preferences in different learning scenarios and fragmented learning time with eight kinds of learning paths (complemented learning path, shortest learning path, shortest duration learning path, critical learning path, easy learning path, complete learning path, more-hotspot learning path and quick learning path) and their constraint factors for the proposed model. This model solves the problem of how to recommend a suitable path for an e-learner when he/she is learning in a specific scenario.
(3)We propose a multi-constraint learning path recommendation algorithm based on the proposed model and knowledge map , as well as other key information including the features of learners’ behaviors, such as learning duration, learning frequency, learning interval, attention degree and learning centrality of knowledge unit (KU). The feature of learning centrality of KU is based on our team’s previous research, in which the inheritance and development of knowledge is seen as a stochastic dynamic migration process of the semantic information in knowledge map.