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

Abstract

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.

A Literature Review of Knowledge Tracing for Student Modeling : Research Trends, Models, Datasets, and Challenges

“…The last study by Klingler et al [13] proposed Dynamic 4, DKT is the most widely proposed model. DKT utilizes a Recurrent Neural Network (RNN) to trace students' knowledge states by finding the hidden structure of each exercise's correlation and analyzing student answers [3], [24]. DKT also captures complex high-dimensional features of items and students [26].…”

“…The AUC score obtained was 87.86%. Whereas Liu et al [24] proposed the multiple features fusion attention mechanism enhanced deep knowledge tracing (MFA-DKT) model. This model has an AUC score of 96%.…”

Student Performance Prediction via Attention-Based Multi-Layer Long-Short Term Memory

“…We hope to obtain real-time information on the learning status of students so that teachers can intervene in the learning status of students in time and help students better master the content of this course [11]. In order to achieve this goal, we consider establishing a student performance prediction system to evaluate student performance [12].…”

Prediction of learning outcomes via clickstream data using machine learning

“…However, unlike the single matrix in MANN, DKVMN uses two matrices a key matrix for latent concepts and value matrix for student mastery level. More recently, transformers have also been applied to train DKTs [225][226][227]. Since they employ a self-attention mechanism, information encoded by transformers may also be interpreted.…”

“…Random forests [174,197,199], k-nearest neighbours [204], Neural networks [177,200,[208][209][210]219], Bayesian networks [197,210,214], Regression models [174,177,178,188,198,205,206,213,216,217], Nave Bayes [174,214], Rule-based systems [197,207,209,221], Decision trees [174, 183, 196-198, 210, 214], Correlational analysis [220], Support vector machines [198,214], Matrix factorization & collaborative filtering [200-203, 211, 212], Cox proportional hazard model [215] Deep knowledge tracing -Deep knowledge tracing [31,222,223], Memory-augmented neural networks [224], Transformers [225][226][227] Chapter 6…”