Deep Knowledge Tracing

Abstract

Knowledge tracing---where a machine models the knowledge of a student as they interact with coursework---is a well established problem in computer supported education. Though effectively modeling student knowledge would have high educational impact, the task has many inherent challenges. In this paper we explore the utility of using Recurrent Neural Networks (RNNs) to model student learning. The RNN family of models have important advantages over previous methods in that they do not require the explicit encoding of human domain knowledge, and can capture more complex representations of student knowledge. Using neural networks results in substantial improvements in prediction performance on a range of knowledge tracing datasets. Moreover the learned model can be used for intelligent curriculum design and allows straightforward interpretation and discovery of structure in student tasks. These results suggest a promising new line of research for knowledge tracing and an exemplary application task for RNNs.

Cited by in corpus (76)

• Exponential expressivity in deep neural networks through transient chaos
• A Self-Attentive model for Knowledge Tracing
• SAINT+: Integrating Temporal Features for EdNet Correctness Prediction
• Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing
• How deep is knowledge tracing?
• Biologically inspired protection of deep networks from adversarial attacks
• Knowledge Query Network: How Knowledge Interacts with Skills
• Deep-IRT: Make Deep Learning Based Knowledge Tracing Explainable Using Item Response Theory
• On the Expressive Power of Deep Neural Networks
• Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice
• EKT: Exercise-aware Knowledge Tracing for Student Performance Prediction
• SINKT: A Structure-Aware Inductive Knowledge Tracing Model with Large Language Model
• DAS3H: Modeling Student Learning and Forgetting for Optimally Scheduling Distributed Practice of Skills
• Teaching Categories to Human Learners with Visual Explanations
• GIKT: A Graph-based Interaction Model for Knowledge Tracing
• pyBKT: An Accessible Python Library of Bayesian Knowledge Tracing Models
• Knowledge Tracing Machines: Factorization Machines for Knowledge Tracing
• EdNet: A Large-Scale Hierarchical Dataset in Education
• Deep Learning Methods for Vessel Trajectory Prediction based on Recurrent Neural Networks
• Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves
• HGKT: Introducing Hierarchical Exercise Graph for Knowledge Tracing
• AI-Driven Interface Design for Intelligent Tutoring System Improves Student Engagement
• Application of Deep Self-Attention in Knowledge Tracing
• Assessment Modeling: Fundamental Pre-training Tasks for Interactive Educational Systems
• R2DE: a NLP approach to estimating IRT parameters of newly generated questions
• Generative Grading: Near Human-level Accuracy for Automated Feedback on Richly Structured Problems
• VLEngagement: A Dataset of Scientific Video Lectures for Evaluating Population-based Engagement
• Enhancing Knowledge Tracing with Concept Map and Response Disentanglement
• On the Interpretability of Deep Learning Based Models for Knowledge Tracing
• Modeling Knowledge Acquisition from Multiple Learning Resource Types
• ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback
• Dynamic Knowledge embedding and tracing
• Student Performance Prediction Using Dynamic Neural Models
• qDKT: Question-centric Deep Knowledge Tracing
• Deep Graph Memory Networks for Forgetting-Robust Knowledge Tracing
• Enhancing Knowledge Tracing via Adversarial Training
• GRAM: Fast Fine-tuning of Pre-trained Language Models for Content-based Collaborative Filtering
• Deep inference of latent dynamics with spatio-temporal super-resolution using selective backpropagation through time
• Deep Trustworthy Knowledge Tracing
• VarFA: A Variational Factor Analysis Framework For Efficient Bayesian Learning Analytics
• Recommendation in Personalised Peer-Learning Environments
• On the verification of Embeddings using Hybrid Markov Logic
• Play to Grade: Testing Coding Games as Classifying Markov Decision Process
• BKT-LSTM: Efficient Student Modeling for knowledge tracing and student performance prediction
• Towards Interpretable Deep Learning Models for Knowledge Tracing
• Extending Deep Knowledge Tracing: Inferring Interpretable Knowledge and Predicting Post-System Performance
• Predicting Student Performance in Interactive Online Question Pools Using Mouse Interaction Features
• Reliable Deep Grade Prediction with Uncertainty Estimation
• PEEK: A Large Dataset of Learner Engagement with Educational Videos
• An Exploratory Analysis of the Latent Structure of Process Data via Action Sequence Autoencoder
• SCOUT: Self-aware Discriminant Counterfactual Explanations
• Learning Data Teaching Strategies Via Knowledge Tracing
• Last Query Transformer RNN for knowledge tracing
• LSTM-SAKT: LSTM-Encoded SAKT-like Transformer for Knowledge Tracing
• Model Elicitation through Direct Questioning
• Design and Evaluation of a Tutor Platform for Personalized Vocabulary Learning
• Consistency and Monotonicity Regularization for Neural Knowledge Tracing
• Deep learning approaches for neural decoding: from CNNs to LSTMs and spikes to fMRI
• Dynamic Key-Value Memory Networks for Knowledge Tracing
• Domain Adaption for Knowledge Tracing
• Deep Knowledge Tracing and Dynamic Student Classification for Knowledge Tracing
• Quality meets Diversity: A Model-Agnostic Framework for Computerized Adaptive Testing
• Evolvable Psychology Informed Neural Network for Memory Behavior Modeling
• Deep Knowledge Tracing with Side Information
• Addressing Two Problems in Deep Knowledge Tracing via Prediction-Consistent Regularization
• Personalized Stopping Rules in Bayesian Adaptive Mastery Assessment
• Metric-Free Individual Fairness with Cooperative Contextual Bandits
• In Proximity of ReLU DNN, PWA Function, and Explicit MPC
• Graph-based Exercise- and Knowledge-Aware Learning Network for Student Performance Prediction
• Deep Knowledge Tracing with Learning Curves
• Context-Aware Attentive Knowledge Tracing
• Unsupervised Representations Predict Popularity of Peer-Shared Artifacts in an Online Learning Environment
• Exploring Common and Individual Characteristics of Students via Matrix Recovering
• Domain Adaptation for Real-Time Student Performance Prediction
• What's happened in MOOC Posts Analysis, Knowledge Tracing and Peer Feedbacks? A Review
• Interpreting Deep Knowledge Tracing Model on EdNet Dataset