Inferring Concept Prerequisite Relations from Online Educational Resources

Abstract

The Internet has rich and rapidly increasing sources of high quality educational content. Inferring prerequisite relations between educational concepts is required for modern large-scale online educational technology applications such as personalized recommendations and automatic curriculum creation. We present PREREQ, a new supervised learning method for inferring concept prerequisite relations. PRE-REQ is designed using latent representations of concepts obtained from the Pairwise Latent Dirichlet Allocation model, and a neural network based on the Siamese network architecture. PREREQ can learn unknown concept prerequisites from course prerequisites and labeled concept prerequisite data. It outperforms state-of-the-art approaches on benchmark datasets and can effectively learn from very less training data. PREREQ can also use unlabeled video playlists, a steadily growing source of training data, to learn concept prerequisites, thus obviating the need for manual annotation of course prerequisites.

Undergraduate Grade Prediction in Chinese Higher Education Using Convolutional Neural Networks

“…These mapping-based methods could be support vector machine (SVM) [1], artificial neural networks (ANN) [2], graph convolutional networks (GCN) [8]. However, there are two observations from our dataset: (1) The k courses are usually organized in prerequisite relationships [14]. (2) The k courses are usually distributed into multiple terms rather than a rigorous time-based sequence.…”

MOOCCube: A Large-scale Data Repository for NLP Applications in MOOCs

“…Prerequisite relation has received much attention in recent years (Pan et al, 2017a;Fabbri et al, 2018; and has a direct help for teaching applications. To build prerequisite chains, we first reduce the amount of candidate concept pairs by utilizing taxonomy information (Liang et al, 2015) and video dependency (Roy et al, 2019), and then lead manual annotation. The annotation results are then employed to train different models to build a much larger distant supervised prerequisite dataset.…”

“…• PREREQ employs a network to detect such relationships from course and video dependency (Roy et al, 2019). Here we present an improved version PREREQ-S by introducing students' video watch order to enhance the video dependency network, i.e., we sort the watched videos of each student by time and utilize these sequences for replacing the video sequences in the original paper.…”

“…Since MOOC is committed to helping students learn implicit knowledge concepts from diverse courses, many efforts from NLP and AI raise topics to build novel applications for assistance. From extracting course concepts and their prerequisite relations (Pan et al, 2017b;Roy et al, 2019; to analyzing student behaviors (Zhang et al, 2019;Feng et al, 2019), MOOC-related topics, tasks, and methods snowball in recent years.…”

Linguistically-Driven Strategy for Concept Prerequisites Learning on Italian

“…Gasparetti et al (2018) proposed a ML methods based on Multilayer Perceptron exploiting LOs, Wikipedia pages of concepts mentioned in the LOs and Wikipedia hierarchical category structure. Roy et al (2018) presented a supervised learning method using a Siamese Network to predict prerequisite relations between University and MOOC courses.…”