A intelligent Gamifying learning recommender system integrated with learning styles and Kelly repertory grid technology

摘要

As RS (recommendation system) presents the advantage of adaptive recommendation, it is gradually applied to e-learning systems to recommend learners for the next learning content. Problems exist in current learning recommender system available to student in that they are often of a general learning content not offering a personalized service. To overcome this, An adaptive learning path recommendation system (ALPRS) is proposed comprising: (a) Fuzzy Delphi Method (FDM) is applied to acquire the key factors in learning content; (b) Fuzzy Interpretive Structural Model (ISM) is further utilized for establishing the adaptive learning path hierarchical structure; and (c) repertory grid technology (RGT) is further used for acquiring the effects of the recommender element attributes of the adaptive learning path. The result show that the learning outcome with ALPRS is better than it with general learning course guided recommendation mechanism, and the scores of system satisfaction with ALPRS and personal service are higher than 90; recall (95%), precision (68%), F1 index (45%), and MAE (8%) in ALPRS outperform other approaches. Finally, three contributions are organized in this study. (1) The novel hybrid ALPRS is proposed and tested the practicability. (2) A prototype gamification geometry teaching material module is developed for the promotion in MSTE (Mathematics, Science, and Technology Education) areas. (3) The adaptive geometry learning path diagram generated with ISM based on learning styles could offer reference for successive studies.