个性化学习路径推荐综述

近年来,伴随着现代信息技术的迅猛发展,以人工智能为代表的新兴技术在教育领域得到了广泛应用,引发了学习理念和方式的深刻变革.在这种大背景下,在线学习超越了时空的限制,为学习者“随时随地”学习提供了更多的可能性,从而得到了蓬勃发展.然而,在线学习中师生时间、空间分离的特征,导致教师无法及时掌握学生的学习状态,一定程度上制约了在线学习中教学质量的提升.面对多元化的学习需求及海量学习资源,如何迅速完成学习目标、降低学习成本、合理分配学习资源等问题成为限制个人和时代发展的重大问题.然而,传统的“一刀切”的教育模式已经不能满足人们获取知识的需求了,需要一个更高效、更科学的个性化教育模式,以帮助学习者以最小的学习成本最大限度地完成学习目标.基于以上背景,如何自动高效识别学习者特征,高效地组织和分配学习资源,为每一位学习者规划个性化路径,成为面向个体的精准化教育资源匹配机制研究中亟待解决的问题.系统地综述并分析了当前个性化学习路径推荐的研究现状,并从多学科领域的角度分析了对于同一问题的不同研究思路,同时也归纳总结了当前研究中最为主流的核心推荐算法.最后,强调当前研究存在的主要不足之处.

State-of-the-art Survey on Personalized Learning Path Recommendation

Recently, with the rapid development of information technology, emerging technologies represented by artificial intelligence are widely applied in education, triggering profound changes in the concept and mode of learning. In addition, online learning transcends the limitations of time and space, providing more possibilities for learners to learn "anytime and anywhere". Nevertheless, the separation of time and space of teachers and students in online learning makes teachers could not handle students'' learning process, limits the quality of teaching and learning. Diversified learning targets and massive learning resources generate some new problems, such as how to quickly accomplish learning targets, reduce learning costs, and reasonably allocate learning resources. These problems have become the limitations of the development of individuals and the society. However, traditional "one size fits all" educational model can no longer fit human''s needs, thus, one more efficient and scientific personalized education model is needed to help learners maximize their learning targets with minimal learning costs. Based on these considerations, new adaptive learning system is needed which could automatically and efficiently identify learner''s personalized characteristics, efficiently organize and allocate learning resources, and plan a global personalized learning path. This study systematically reviews and analyzes the current researches on personalized learning path recommendation and the different research vision from multidisciplinary perspective. Then, the most applied algorithm in current research is summarized. Finally, the main shortcomings of the current research, which should be paid more attention to, are highlighted.