An official website of the United States government
Knowledge tracing is a method to model students’ knowledge and enable personalized education in many STEM disciplines such as mathematics and physics, but has so far still been a challenging task in computing disciplines. One key obstacle to successful knowledge tracing in computing education lies in the accurate extraction of knowledge components (KCs), since multiple intertwined KCs are practiced at the same time for programming problems. In this paper, we address the limitations of current methods and explore a hybrid approach for KC extraction, which combines automated code parsing with an expert-built ontology. We use an introductory (CS1) Java benchmark dataset to compare its KC extraction performance with the traditional extraction methods using a state-of-the-art evaluation approach based on learning curves. Our preliminary results show considerable improvement over traditional methods of student modeling. The results indicate the opportunity to improve automated KC extraction in CS education by incorporating expert knowledge into the process.
more »
« less
Evaluating Multi-Knowledge Component Interpretability of Deep Knowledge Tracing Models in Programming
Evaluates DKT models’ ability to track individual knowledge components (KCs) in programming tasks. Proposes two enhancements—adding an explicit KC layer and code features—and shows that the KC layer yields modest improvements in KC-level interpretability, especially when tracking incorrect submissions.
more »
« less
- Award ID(s):
- 2013502
- PAR ID:
- 10609433
- Publisher / Repository:
- Proceedings of the 17th International Conference on Educational Data Mining / International Educational Data Mining Society
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null; null; null; null; null (Ed.)Educational content labeled with proper knowledge components (KCs) are particularly useful to teachers or content organizers. However, manually labeling educational content is labor intensive and error-prone. To address this challenge, prior research proposed machine learning based solutions to auto-label educational content with limited success. In this work, we significantly improve prior research by (1) expanding the input types to include KC descriptions, instructional video titles, and problem descriptions (i.e., three types of prediction task), (2) doubling the granularity of the prediction from 198 to 385 KC labels (i.e., more practical setting but much harder multinomial classification problem), (3) improving the prediction accuracies by 0.5–2.3% using Task-adaptive Pre-trained BERT, outperforming six baselines, and (4) proposing a simple evaluation measure by which we can recover 56–73% of mispredicted KC labels. All codes and data sets in the experiments are available at: https://github.com/tbs17/TAPT-BERTmore » « less
-
Educational content labeled with proper knowledge components (KCs) are particularly useful to teachers or content organizers. However, manually labeling educational content is labor intensive and error-prone. To address this challenge, prior research proposed machine learning based solutions to auto-label educational content with limited success. In this work, we significantly improve prior research by (1) expanding the input types to include KC descriptions, instructional video titles, and problem descriptions (i.e., three types of prediction task), (2) doubling the granularity of the prediction from 198 to 385 KC labels (i.e., more practical setting but much harder multinomial classification problem), (3) improving the prediction accuracies by 0.5–2.3% using Task-adaptive Pre-trained BERT, outperforming six baselines, and (4) proposing a simple evaluation measure by which we can recover 56–73% of mispredicted KC labels. All codes and data sets in the experiments are available at: https://github.com/tbs17/TAPT-BERT Keywordsmore » « less
-
Knowledge components (KCs) have many applications. In computing education, knowing the demonstration of specific KCs has been challenging. This paper introduces an entirely data-driven approach for (i) discovering KCs and (ii) demonstrating KCs, using students’ actual code submissions. Our system is based on two expected properties of KCs: (i) generate learning curves following the power law of practice, and (ii) are predictive of response correctness. We train a neural architecture (named KC-Finder) that classifies the correctness of student code submissions and captures problem-KC relationships. Our evaluation on data from 351 students in an introductory Java course shows that the learned KCs can generate reasonable learning curves and predict code submission correctness. At the same time, some KCs can be interpreted to identify programming skills. We compare the learning curves described by our model to four baselines, showing that (i) identifying KCs with naive methods is a difficult task and (ii) our learning curves exhibit a substantially better curve fit. Our work represents a first step in solving the data-driven KC discovery problem in computing education.more » « less
-
In the coastal ocean, interactions of waves and currents with large roughness elements, similar in size to wave orbital excursions, generate drag and dissipate energy. These boundary layer dynamics differ significantly from well-studied small-scale roughness. To address this problem, we derived spatially and phase-averaged momentum equations for combined wave–current flows over rough bottoms, including the canopy layer containing obstacles. These equations were decomposed into steady and oscillatory parts to investigate the effects of waves on currents, and currents on waves. We applied this framework to analyse large-eddy simulations of combined oscillatory and steady flows over hemisphere arrays (diameter $$D$$ ), in which current ( $$U_c$$ ), wave velocity ( $$U_w$$ ) and period ( $$T$$ ) were varied. In the steady momentum budget, waves increase drag on the current, and this is balanced by the total stress at the canopy top. Dispersive stresses from oscillatory flow around obstacles are increasingly important as $$U_w/U_c$$ increases. In the oscillatory momentum budget, acceleration in the canopy is balanced by pressure gradient, added-mass and form drag forces; stress gradients are small compared to other terms. Form drag is increasingly important as the Keulegan–Carpenter number $$KC=U_wT/D$$ and $$U_c/U_w$$ increase. Decomposing the drag term illustrates that a quadratic relationship predicts the observed dependences of steady and oscillatory drag on $$U_c/U_w$$ and $KC$ . For large roughness elements, bottom friction is well represented by a friction factor ( $$f_w$$ ) defined using combined wave and current velocities in the canopy layer, which is proportional to drag coefficient and frontal area per unit plan area, and increases with $KC$ and $$U_c/U_w$$ .more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Proceeding:
- The DOI is not currently available.
