Prerequisite-Driven Deep Knowledge Tracing

Chen, Penghe; Lu, Yu; Zheng, Vincent W.; Pian, Yang

doi:10.1109/icdm.2018.00019

Cited by 113 publications

(56 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Models such as [9,17] have shown the importance of explicitly incorporating the relations between KCs as input to the KT model. In particular, [17] uses Dynamic Bayesian Network to model the pre-requisite relations between KCs while [9] incorporate the same in DKT model. However, they assume that the relation between KCs is known apriori.…”

Section: Introductionmentioning

confidence: 99%

RKT: Relation-Aware Self-Attention for Knowledge Tracing

Pandey

Srivastava

2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

105

View full text Add to dashboard Cite

The world has transitioned into a new phase of online learning in response to the recent Covid19 pandemic. Now more than ever, it has become paramount to push the limits of online learning in every manner to keep flourishing the education system. One crucial component of online learning is Knowledge Tracing (KT). The aim of KT is to model student's knowledge level based on their answers to a sequence of exercises referred as interactions. Students acquire their skills while solving exercises and each such interaction has a distinct impact on student ability to solve a future exercise. This impact is characterized by 1) the relation between exercises involved in the interactions and 2) student forget behavior. Traditional studies on knowledge tracing do not explicitly model both the components jointly to estimate the impact of these interactions. In this paper, we propose a novel Relation-aware self-attention model for Knowledge Tracing (RKT). We introduce a relation-aware self-attention layer that incorporates the contextual information. This contextual information integrates both the exercise relation information through their textual content as well as student performance data and the forget behavior information through modeling an exponentially decaying kernel function. Extensive experiments on three real-world datasets, among which two new collections are released to the public, show that our model outperforms state-ofthe-art knowledge tracing methods. Furthermore, the interpretable attention weights help visualize the relation between interactions and temporal patterns in the human learning process.

show abstract

Section: Introductionmentioning

confidence: 99%

RKT: Relation-Aware Self-Attention for Knowledge Tracing

Pandey

Srivastava

2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

105

View full text Add to dashboard Cite

show abstract

“…DKVMN designs two memory matrixes, including a static key matrix (which stores the knowledge concepts) and a dynamic value matrix (which updates students' knowledge mastery level) based on memory-augmented neural networks [16]. Prerequisitedriven deep knowledge tracing (PDKT-C) incorporates the knowledge structure information and uses another type of recurrent neural network called gated recurrent unit (GRU) [17]. At the same time, it also solves the issue of sparse data [1].…”

Section: ) Combine Knowledge Tracing With Deep Learningmentioning

confidence: 99%

Multiple Features Fusion Attention Mechanism Enhanced Deep Knowledge Tracing for Student Performance Prediction

Dong

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Student performance prediction is a fundamental task in online learning systems, which aims to provide students with access to active learning. Generally, student performance prediction is achieved by tracing the evolution of each student's knowledge states via a series of learning activities. Every learning activity record has two types of feature data: student behavior and exercise features. However, most methods use features that are related to exercises, such as correctness and concepts, while other student behavior features are usually ignored. The few studies that have focused on student behavior features through subjective manual selection argue that different student behavior features can be used in an equivalent manner to predict student performance. In this paper, we assume that the integration of student behavior features and exercise features is crucial to improve the precision of prediction, and each feature has a different impact on student performance. Therefore, this paper proposes a novel framework for student performance prediction by making full use of both student behavior features and exercise features and combining the attention mechanism with the knowledge tracing model. Specifically, we first exploit machine learning to capture feature representation automatically. Then, a fusion attention mechanism based on recurrent neural network architecture is used for student performance prediction. Extensive experiments on a real-world dataset show the effectiveness and practicability of our approach. The accuracy of our method is up to 98%, which is superior to previous methods.

show abstract

“…Recent literature claims that Deep Knowledge Tracing (DKT) -which was first introduced by Piech et al in [19] and consists in performing KT by means of neural networks -outperforms logistic models in predicting the results of future exams [1,6,32,33], but this advantage is not agreed across the community [7,18,28,31]. Also, DKT does not estimate explicitly the skill level of students nor the latent traits of questions, which makes the interpretation of such models a strenuous task.…”

Section: Knowledge Tracingmentioning

confidence: 99%

R2de

Benedetto

Cappelli²,

Turrin³

et al. 2020

Proceedings of the Tenth International Conference on Learning Analytics &Amp; Knowledge

View full text Add to dashboard Cite

The main objective of exams consists in performing an assessment of students' expertise on a specific subject. Such expertise, also referred to as skill or knowledge level, can then be leveraged in different ways (e.g., to assign a grade to the students, to understand whether a student might need some support, etc.). Similarly, the questions appearing in the exams have to be assessed in some way before being used to evaluate students. Standard approaches to questions' assessment are either subjective (e.g., assessment by human experts) or introduce a long delay in the process of question generation (e.g., pretesting with real students). In this work we introduce R2DE (which is a Regressor for Difficulty and Discrimination Estimation), a model capable of assessing newly generated multiple-choice questions by looking at the text of the question and the text of the possible choices. In particular, it can estimate the difficulty and the discrimination of each question, as they are defined in Item Response Theory. We also present the results of extensive experiments we carried out on a real world large scale dataset coming from an e-learning platform, showing that our model can be used to perform an initial assessment of newly created questions and ease some of the problems that arise in question generation.

show abstract

Prerequisite-Driven Deep Knowledge Tracing

Cited by 113 publications

References 16 publications

RKT: Relation-Aware Self-Attention for Knowledge Tracing

RKT: Relation-Aware Self-Attention for Knowledge Tracing

Multiple Features Fusion Attention Mechanism Enhanced Deep Knowledge Tracing for Student Performance Prediction

R2de

Contact Info

Product

Resources

About