Data‐driven Q‐matrix learning based on Boolean matrix factorization in cognitive diagnostic assessment

Xiong, Jian; Luo, Zhaosheng; Luo, Guanzhong; Yu, Xiaofeng

doi:10.1111/bmsp.12271

Cited by 5 publications

(3 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Expert-based [88,102]; Statistic-based [29,31,108,139,170]; Deep Learning: CNN [79], RNN [75,90,122], NLP [119,172].…”

Section: Question Bank Construction Sectionmentioning

confidence: 99%

“…An alternate recursive algorithm with a Heaviside step function is used to address the NP-hard nature of BMF and the non-invertibility of Boolean operations. Further enhancements to this method include additional judgment and processing steps to ensure convergence and robustness, as well as refinement procedures to avoid local optima in Q-matrix estimation [170].…”

Section: Statistic-based Characteristics Annotationmentioning

confidence: 99%

See 1 more Smart Citation

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks (GNNs) have emerged as a powerful tool for graph representation learning, in an end-to-end supervised setting, their performance heavily relies on a large amount of task-specific supervision. To reduce labeling requirement, the "pre-train, fine-tune" and "pre-train, prompt" paradigms have become increasingly common. In particular, prompting is a popular alternative to fine-tuning in natural language processing, which is designed to narrow the gap between pre-training and downstream objectives in a task-specific manner. However, existing study of prompting on graphs is still limited, lacking a universal treatment to appeal to different downstream tasks. In this paper, we propose GraphPrompt, a novel pre-training and prompting framework on graphs. GraphPrompt not only unifies pre-training and downstream tasks into a common task template, but also employs a learnable prompt to assist a downstream task in locating the most relevant knowledge from the pre-trained model in a task-specific manner. Finally, we conduct extensive experiments on five public datasets to evaluate and analyze GraphPrompt. CCS CONCEPTS• Computing methodologies → Learning latent representations; • Information systems → Data mining.

show abstract

“…Expert-based [88,102]; Statistic-based [29,31,108,139,170]; Deep Learning: CNN [79], RNN [75,90,122], NLP [119,172].…”

Section: Question Bank Construction Sectionmentioning

confidence: 99%

Section: Statistic-based Characteristics Annotationmentioning

confidence: 99%

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

show abstract

“…In recent years, with the development of artificial intelligence and big data technologies, cognitive diagnosis, and personalized learning can be performed more accurately with the support of artificial intelligence and big data technologies to further improve students' learning outcomes [12][13]. The literature [14] proposed a data-driven Q-matrix learning method based on Boolean matrix decomposition for cognitive diagnostic assessment. The Q-matrix is a matrix that represents the relationship between students' abilities and topic requirements and plays an important role in cognitive diagnostic assessment.…”

Section: Introductionmentioning

confidence: 99%

A resource sharing platform based on the construction of cognitive mapping to promote the development of macro education in universities

Cao

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

In this paper, firstly, the complementary grouping method is realized through the complementary grouping of cooperative shared learning supported by cognitive diagnosis, the knowledge relationship dependency graph construction, expected response pattern construction, and dynamic stratification process, and then the complementary grouping method is realized. Then, a cognitive mapping embedded resource sharing platform based on memory network and graph attention is proposed, including test factors based on graph attention and student factors based on memory network. The results show that in the FrcSub dataset DINA model deviates from the other two models in the 1st, 3rd, 8th, 12th, and 14th question prediction effects, and the overall question prediction performance is stable with a deviation of ±0.05. The cognitive mapping embedded resource sharing platform is efficient and feasible and also provides a new way of thinking for the development of macro education in universities.

show abstract

Combining regularization and logistic regression model to validate the Q‐matrix for cognitive diagnosis model

Sun,

Zhang,

Nie

et al. 2024

Brit J Math & Statis

View full text Add to dashboard Cite

Q‐matrix is an important component of most cognitive diagnosis models (CDMs); however, it mainly relies on subject matter experts' judgements in empirical studies, which introduces the possibility of misspecified q‐entries. To address this, statistical Q‐matrix validation methods have been proposed to aid experts' judgement. A few of these methods, including the multiple logistic regression‐based (MLR‐B) method and the Hull method, can be applied to general CDMs, but they are either time‐consuming or lack accuracy under certain conditions. In this study, we combine the L1 regularization and MLR model to validate the Q‐matrix. Specifically, an L1 penalty term is imposed on the log‐likelihood of the MLR model to select the necessary attributes for each item. A simulation study with various factors was conducted to examine the performance of the new method against the two existing methods. The results show that the regularized MLR‐B method (a) produces the highest Q‐matrix recovery rate (QRR) and true positive rate (TPR) for most conditions, especially with a small sample size; (b) yields a slightly higher true negative rate (TNR) than either the MLR‐B or the Hull method for most conditions; and (c) requires less computation time than the MLR‐B method and similar computation time as the Hull method. A real data set is analysed for illustration purposes.

show abstract

Data‐driven Q‐matrix learning based on Boolean matrix factorization in cognitive diagnostic assessment

Cited by 5 publications

References 62 publications

Geography of Technology Transfer in China

Geography of Technology Transfer in China

A resource sharing platform based on the construction of cognitive mapping to promote the development of macro education in universities

Combining regularization and logistic regression model to validate the Q‐matrix for cognitive diagnosis model

Contact Info

Product

Resources

About