Advancing Knowledge Tracing by Exploring Follow-up Performance Trends

TL;DR

This paper introduces FINER, a novel knowledge tracing method that integrates follow-up performance trends with historical data, significantly improving student performance prediction accuracy in intelligent tutoring systems.

Contribution

The paper proposes a new approach called FINER that effectively combines follow-up performance trends with historical learning sequences for enhanced knowledge tracing.

Findings

FINER outperforms ten state-of-the-art KT methods.

Accuracy improvements range from 8.74% to 84.85%.

FPTs can be retrieved in linear time.

Abstract

Intelligent Tutoring Systems (ITS), such as Massive Open Online Courses, offer new opportunities for human learning. At the core of such systems, knowledge tracing (KT) predicts students' future performance by analyzing their historical learning activities, enabling an accurate evaluation of students' knowledge states over time. We show that existing KT methods often encounter correlation conflicts when analyzing the relationships between historical learning sequences and future performance. To address such conflicts, we propose to extract so-called Follow-up Performance Trends (FPTs) from historical ITS data and to incorporate them into KT. We propose a method called Forward-Looking Knowledge Tracing (FINER) that combines historical learning sequences with FPTs to enhance student performance prediction accuracy. FINER constructs learning patterns that facilitate the retrieval of FPTs from historical ITS data in linear time; FINER includes a novel similarity-aware attention mechanism that aggregates FPTs based on both frequency and contextual similarity; and FINER offers means of combining FPTs and historical learning sequences to enable more accurate prediction of student future performance. Experiments on six real-world datasets show that FINER can outperform ten state-of-the-art KT methods, increasing accuracy by 8.74% to 84.85%.