Item Response Ranking for Cognitive Diagnosis

Authors: Shiwei Tong, Qi Liu, Runlong Yu, Wei Huang, Zhenya Huang, Zachary A. Pardos, Weijie Jiang

IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on two real-world datasets show that CDMs with IRR not only significantly outperforms the baselines, but also effectively provides interpretable insights for understanding the cognitive diagnostic results of students.
Researcher Affiliation Academia 1Anhui Province Key Laboratory of Big Data Analysis and Application, School of Computer Science and Technology & School of Data Science, University of Science and Technology of China 2University of California, Berkeley
Pseudocode No The paper describes methods in paragraph form and does not include any explicitly labeled 'Pseudocode' or 'Algorithm' blocks.
Open Source Code Yes Our code is available at https://github.com/bigdataustc/EduCDM.
Open Datasets Yes ASSISTments (ASSISTments 20092010 skill builder ) is an open dataset collected by the ASSISTments online tutoring systems [Feng et al., 2009]. Collected from a widely-used online learning system, MATH contains mathematical test items and logs of high school examinations.
Dataset Splits Yes For each dataset, we divide the students on each test item into training: test = 8:2. We use 90% of the training data to train model and apply grid search to adjust the hyper-parameters on the remaining 10% of the data (i.e., the validation dataset).
Hardware Specification Yes all experiments are run on a Linux server with two Intel(R) Xeon(R) E5-2699 v4 CPUs and a Tesla P100 PCIe GPU.
Software Dependencies No All models are implemented by MXNet using Python. (No version numbers provided for MXNet or Python).
Experiment Setup Yes All hyper-parameters are tuned in the validation datasets. λ is selected from [0.1, 0.01, 0.001, 0.0001]. N O and N U are selected from [1, 5, 10, 30]. Based on the performance on the validation datasets, we set λ = 0.0001 and N O = N U = 10. We initialize parameters in all networks with Xavier initialization [Glorot and Bengio, 2010] and we use the Adam algorithm [Kingma and Ba, 2014] for optimization.