Neural cognitive diagnosis modeling incorporating response times
Clinical Snapshot
PICO Framework
| P — Population | Students taking computerized assessments in educational settings (PISA2012, 2MFC, and ASSIST09 datasets) |
| I — Intervention | JRT-NCD (joint response times neural cognitive diagnosis) model incorporating response time data |
| C — Comparator | Traditional statistical cognitive diagnosis models and NCD models without response time |
| O — Outcomes | Diagnostic accuracy of student knowledge concept mastery, model interpretability, reduction of overspeed behavior effects |
Bottom Line
This methodological study presents a novel neural network approach (JRT-NCD) that incorporates response time data to improve cognitive diagnosis in educational assessments. The model demonstrated superior performance compared to traditional statistical models and neural networks without response time across three educational datasets. Key advantages include better handling of complex nonlinear relationships, improved diagnostic accuracy, and reduced impact of overspeed behavior while maintaining interpretability. The approach shows promise for enhancing computerized educational assessments, though the abstract lacks specific statistical measures. The methodology appears applicable to Australian educational contexts, particularly for online testing platforms and adaptive learning systems. However, further validation studies with detailed statistical reporting would strengthen the evidence base for widespread implementation.
Key Findings
P Value: Not reported
Effect Size: Not specified in abstract
Primary Outcome: Enhanced diagnostic accuracy of student knowledge concept mastery
Nnt Or Sensitivity: Improved diagnostic accuracy compared to traditional models and NCD without response time
Confidence Interval: Not reported
Clinical Application
High feasibility for implementation in computerized testing platforms with response time data collection capabilities Relevant to Australian educational technology initiatives, NAPLAN online testing, and university computerized assessments. Could inform development of adaptive learning platforms in Australian schools and universities Students in computerized educational assessment environments, particularly relevant for adaptive learning systems
Abstract
Cognitive diagnosis is a fundamental issue in the field of intelligent education, aiming to identify students' mastery of specific knowledge concepts. With computerized testing, response time (RT) is a process data that can be collected. Incorporating RT in cognitive diagnosis assessment can enhance diagnostic accuracy. However, RT is only considered in traditional statistical cognitive diagnosis models. Compared with traditional statistical diagnostic models, cognitive diagnosis models based on neural networks have advantages such as high precision and strong generalization ability. Therefore, this paper proposes a JRT-NCD (joint response times neural cognitive diagnosis) model that uses neural networks to model the complex nonlinear interactions between exercises and students and incorporates RT as a new feature to refine diagnostic results on student abilities. Research findings on three datasets of PISA2012, 2MFC, and ASSIST09 indicate that: (1) In comparison with traditional statistical models, neural networks have better fitting capabilities for real complex nonlinear data; (2) compared to the NCD model that disregards RT, JRT-NCD achieves higher diagnostic accuracy while maintaining its interpretability, and reduces the misleading effects of "overspeed behavior" on the diagnostic results.
References
- 1.Xiong, J., Li, M., Luo, F., & Wang, W. (2026). Neural cognitive diagnosis modeling incorporating response times. Behavior Research Methods. https://doi.org/10.3389/fpsyg.2018.00997
Related Research
Journal of affective disorders
Interventions to reduce loneliness in children and adolescents (4-18 years): A systematic review and meta-analysis with narrative synthesis of study-level characteristics
16 June 2026
PloS one
A systematic review and meta-analysis on achievement emotions, working memory and student-teacher relationship during second language learning in primary school
28 May 2026
PloS one
Investigating ChatGPT-mediated mind mapping to facilitate EFL learners' reading comprehension
21 May 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service