Prerequisite Relation Learning for Concepts in MOOCs

Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 1447–1456 Vancouver, Canada, July 30 - August 4, 2017. c⃝2017 Association for Computational Linguistics https://doi.org/10.18653/v1/P17-1133 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 1447–1456 Vancouver, Canada, July 30 - August 4, 2017. c⃝2017 Association for Computational Linguistics https://doi.org/10.18653/v1/P17-1133 Prerequisite Relation Learning for Concepts in MOOCs Liangming Pan, Chengjiang Li, Juanzi Li∗ and Jie Tang Knowledge Engineering Laboratory Department of Computer Science and Technology Tsinghua University, Beijing 100084, China (∗ corresponding author) {panlm14@mails,licj17@mails,lijuanzi,tangjie}tsinghua.edu.cn Abstract What prerequisite knowledge should stu- dents achieve a level of mastery be- fore moving forward to learn subsequent coursewares? We study the extent to which the prerequisite relation between knowledge concepts in Massive Open On- line Courses (MOOCs) can be inferred automatically. In particular, what kinds of information can be leveraged to uncover the potential prerequisite relation between knowledge concepts. We first propose a representation learning-based method for learning latent representations of course concepts, and then investigate how differ- ent features capture the prerequisite rela- tions between concepts. Our experiments on three datasets form Coursera show that the proposed method achieves significant improvements (+5.9-48.0% by F1-score) comparing with existing methods. 1 Introduction Mastery learning was first formally proposed by Benjamin Bloom in 1968 (Bloom, 1981), suggest- ing that students must achieve a level of mastery (e.g., 90% on a knowledge test) in prerequisite knowledge before moving forward to learn sub- sequent knowledge concepts. From then on, pre- requisite relations between knowledge concepts become a cornerstone for designing curriculum in schools and universities. Prerequisite relations essentially can be considered as the dependency among knowledge concepts. It is crucial for peo- ple to learn, organize, apply, and generate knowl- edge (Laurence and Margolis, 1999). Figure 1 shows a real example from Coursera. The student wants to learn “Conditional Random Field” (in video18 of CS229). The prerequisite knowledge might be “Hidden Markov Model” (in video25 of Figure 1: An example of prerequisite relations in MOOCs CS224), whose prerequisite knowledge is “Maxi- mum Likelihood” (in video12 of Math112). Organizing the knowledge structure with pre- requisite relations in education improves tasks such as curriculum planning (Yang et al., 2015), automatic reading list generation (Jardine, 2014), and improving education quality (Rouly et al., 2015). For example, as shown in Figure 1, with explicit prerequisite relations among concepts (in red), a coherent and reasonable learning sequence can be recommended to the student (in blue). Before, the prerequisite relationships were pro- vided by teachers or teaching assistants (Novak, 1990); however in the era of MOOCs, it is becoming infeasible as the teachers would find that they are facing with hundreds of thousands of students with various background. Meanwhile, the rapid growth of Massive Open Online Courses has offered thousands of courses, and students are free to choose any course from the thousands of candidates. Therefore, there is a clear need for methods to automatically dig out the prerequisite relationships among knowledge concepts from the large course space, …

Content truncated to 500 words