Study-GNN: A Novel Pipeline for Student Performance Prediction Based on Multi-Topology Graph Neural Networks

Abstract

Student performance prediction has attracted increasing attention in the field of educational data mining, or more broadly, intelligent education or “AI + education”. Accurate performance prediction plays a significant role in solving the problem of a student dropping out, promoting personalized learning and improving teaching efficiency, etc. Traditional student performance prediction methods usually ignore the potential (underlying) relationship among students. In this paper, we use graph structure to reflect the students’ relationships and propose a novel pipeline for student performance prediction based on newly-developed multi-topology graph neural networks (termed MTGNN). In particular, we propose various ways for graph construction based on similarity learning using different distance metrics. Based on the multiple graphs of different topologies, we design an MTGNN module, as a key module in the pipeline, to deal with the semi-supervised node classification problem where each node represents a student (and the node label is the student’s performance, e.g., Pass/Fail/Withdrawal). An attention-based method is developed to produce the unified graph representation in MTGNN. The effectiveness of the proposed pipeline is verified in a case study, where a real-world educational dataset and several existing approaches are used for performance comparison. The experiment results show that, compared with some traditional machine learning methods and the vanilla graph convolutional network with only a single graph topology, our proposed pipeline works effectively and favorably in student performance prediction.

Predicting Student Performance in Online Learning: A Multidimensional Time-Series Data Analysis Approach

“…Chen et al [28] proposed a performance prediction model based on the differences in patterns of student behavioral features for students with significant performance changes, which uses a multi-head attention mechanism to automatically select more important higher-order behavioral combinations of features, maintain higher temporal accuracy, and can predict student performance more accurately. Li et al [29] considered the potential relationships between students and used multiple graphs with different topologies to reflect the relationships between students and proposed a student performance prediction model based on a multi-topological graph neural network (MTGNN). Yang et al [30] utilized clickstream data and assessment scores as input data to train a time series neural network to capture the unique features of each student's learning pattern.…”

Parking recommendation with meta-heuristic algorithms

“…IoT technology is used in this paper [3] to model the main parking lots and roads around target stations to find a more effective, convenient, and accurate parking space prediction effect. Adaptive genetic algorithms are used to simulate and induce real drivers.…”

“…This paper [3] proposes a wavelet neural network model and trains and predicts the model using parking lot B data. As a result of the gradient descent method, the neural net-work's parameters are trained to increase prediction accuracy.…”

“…A further improvement in accuracy was observed as well as a reduction in the error between the predicted and actual values. This paper [3] proposes a parking lot selection method based on the Logit model that considers vehicle running time, parking rate, walking time, and effective parking space as characteristic parameters of the utility function. Using the Logit model for parking lot induction, the experimental results demonstrate the capacity of the method for selecting the best parking lot.…”

A Systematic Literature Review of Student Performance Prediction Techniques in Virtual Learning Environment

“…Ming Li et al [19] introduced a multi-topology graph neural network (MTGNN) for student performance prediction. Initially, the system used the OULAD dataset for data collection, and then preprocessing was done on the collected data to improve the prediction quality of the classifier.…”