Jin Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jin Wu has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Chanjin Zheng
East China Normal University
4 shared publications - Haoran Shi
East China Normal University
1 shared publication - Jiarui Yu
School of Computer Science and Technology, Faculty of Information, East China Normal University, Shanghai 200062, China
1 shared publication - Shaoyang Guo
School of Education and Intelligent Education Research Center, Yangzhou University, Yangzhou 225009, China
1 shared publication - Wei Xia
Department of Educational Psychology, Faculty of Education, East China Normal University, Shanghai 200062, China
1 shared publication Xiaoyu Li
Yangzhou University
1 shared publication
Latest Publications
- Open Access
- 7 July 2026
- Published by MDPI AG in Behavioral Sciences
- Vol. 16 (7) , 1140
A Deep Learning-Based Latent Trait Model for Forced-Choice Personality Assessment
In the era of intelligent assessment, psychometric tests are becoming increasingly important for personnel selection, career development, and mental health assessment. Forced-choice tests are common in personality assessments because they require participants to select from closely related options, lowering the risk of response distortion. However, traditional latent trait models for forced-choice tests suffer from severe computational bottlenecks in high-dimensional settings. Furthermore, existing deep learning-based cognitive diagnosis models are primarily designed for independent items in educational scenarios (predicated on absolute scoring), making them structurally maladapted to the ipsative data (relative preference comparisons) generated by forced-choice tests. To address these challenges, this study presents a deep learning-based Forced-Choice Neural Latent Trait (FCNLT) Model that overcomes the limitations of traditional models and is applicable to the three most common item block types found in forced-choice tests. To account for the unidimensionality of items, participants’ latent trait levels and item characteristics are represented as interpretable latent embeddings. FCNLT mines these features through nonlinear mapping and introduces a weighted BPR-based ranking loss to natively align with the relative-scoring nature of forced-choice data. Additionally, the monotonicity assumption is utilized to improve the interpretability of the trait estimates. The FCNLT’s effectiveness is validated by experiments on real-world and simulated datasets that show its accuracy, interpretability, and robustness.
- 7 July 2026
- Published by MDPI AG in Behavioral Sciences
- Vol. 16 (7) , 1140
Open AccessA Deep Learning-Based Latent Trait Model for Forced-Choice Personality Assessment
In the era of intelligent assessment, psychometric tests are becoming increasingly important for personnel selection, career development, and mental health assessment. Forced-choice tests are common in personality assessments because they require participants to select from closely related options, lowering the risk of response distortion. However, traditional latent trait models for forced-choice tests suffer from severe computational bottlenecks in high-dimensional settings. Furthermore, existing deep learning-based cognitive diagnosis models are primarily designed for independent items in educational scenarios (predicated on absolute scoring), making them structurally maladapted to the ipsative data (relative preference comparisons) generated by forced-choice tests. To address these challenges, this study presents a deep learning-based Forced-Choice Neural Latent Trait (FCNLT) Model that overcomes the limitations of traditional models and is applicable to the three most common item block types found in forced-choice tests. To account for the unidimensionality of items, participants’ latent trait levels and item characteristics are represented as interpretable latent embeddings. FCNLT mines these features through nonlinear mapping and introduces a weighted BPR-based ranking loss to natively align with the relative-scoring nature of forced-choice data. Additionally, the monotonicity assumption is utilized to improve the interpretability of the trait estimates. The FCNLT’s effectiveness is validated by experiments on real-world and simulated datasets that show its accuracy, interpretability, and robustness.
- 12 May 2026
- Published by Springer Nature
- p. 103-119
FCRD: Forced-Choice Relation-Based Diagnosis for Noncognitive Assessment
- 12 May 2026
- Published by Springer Nature
- p. 103-119
FCRD: Forced-Choice Relation-Based Diagnosis for Noncognitive Assessment
- Open Access
- 6 April 2026
- Published by MDPI AG in Behavioral Sciences
- Vol. 16 (4) , 542
The Best of Two Worlds: IRT-Enhanced Automated Essay Interpretable Scoring
The Automated Essay Scoring (AES) systems confront two fundamental challenges: opaque “black-box” decision-making that limits educator trust, and insufficient validation across linguistically diverse educational contexts. This study proposes IRT-AESF, an innovative framework that bridges educational measurement theory and artificial intelligence by integrating item response theory (IRT) with deep learning. The framework generates three theoretically grounded psychometric parameters: student ability, item difficulty, and item discrimination, which provide transparent and interpretable explanations for scoring decisions. We rigorously evaluated IRT-AESF through 5-fold cross-validation on three large-scale datasets comprising 41,328 authentic essays from English and Chinese educational settings, including both classroom assessments and high-stakes examinations. Results demonstrate statistically significant improvements over competitive baseline models, achieving an 8.4% relative increase in quadratic weighted kappa while maintaining robust cross-lingual performance. This research advances the development of transparent, trustworthy automated assessment systems that deliver not only scores but meaningful diagnostic insights for educational practice.
- 6 April 2026
- Published by MDPI AG in Behavioral Sciences
- Vol. 16 (4) , 542
Open AccessThe Best of Two Worlds: IRT-Enhanced Automated Essay Interpretable Scoring
The Automated Essay Scoring (AES) systems confront two fundamental challenges: opaque “black-box” decision-making that limits educator trust, and insufficient validation across linguistically diverse educational contexts. This study proposes IRT-AESF, an innovative framework that bridges educational measurement theory and artificial intelligence by integrating item response theory (IRT) with deep learning. The framework generates three theoretically grounded psychometric parameters: student ability, item difficulty, and item discrimination, which provide transparent and interpretable explanations for scoring decisions. We rigorously evaluated IRT-AESF through 5-fold cross-validation on three large-scale datasets comprising 41,328 authentic essays from English and Chinese educational settings, including both classroom assessments and high-stakes examinations. Results demonstrate statistically significant improvements over competitive baseline models, achieving an 8.4% relative increase in quadratic weighted kappa while maintaining robust cross-lingual performance. This research advances the development of transparent, trustworthy automated assessment systems that deliver not only scores but meaningful diagnostic insights for educational practice.
- Open Access
MetaCD: A Meta Learning Framework for Cognitive Diagnosis based on Continual Learning
Cognitive diagnosis is an essential research topic in intelligent education, aimed at assessing the level of mastery of different skills by students. So far, many research works have used deep learning models to explore the complex interactions between students, questions, and skills. However, the performance of existing method is frequently limited by the long-tailed distribution and dynamic changes in the data. To address these challenges, we propose a meta-learning framework for cognitive diagnosis based on continual learning (MetaCD). This framework can alleviate the long-tailed problem by utilizing meta-learning to learn the optimal initialization state, enabling the model to achieve good accuracy on new tasks with only a small amount of data. In addition, we utilize a continual learning method named parameter protection mechanism to give MetaCD the ability to adapt to new skills or new tasks, in order to adapt to dynamic changes in data. MetaCD can not only improve the plasticity of our model on a single task, but also ensure the stability and generalization of the model on sequential tasks. Comprehensive experiments on five real-world datasets show that MetaCD outperforms other baselines in both accuracy and generalization.
Open AccessMetaCD: A Meta Learning Framework for Cognitive Diagnosis based on Continual Learning
Cognitive diagnosis is an essential research topic in intelligent education, aimed at assessing the level of mastery of different skills by students. So far, many research works have used deep learning models to explore the complex interactions between students, questions, and skills. However, the performance of existing method is frequently limited by the long-tailed distribution and dynamic changes in the data. To address these challenges, we propose a meta-learning framework for cognitive diagnosis based on continual learning (MetaCD). This framework can alleviate the long-tailed problem by utilizing meta-learning to learn the optimal initialization state, enabling the model to achieve good accuracy on new tasks with only a small amount of data. In addition, we utilize a continual learning method named parameter protection mechanism to give MetaCD the ability to adapt to new skills or new tasks, in order to adapt to dynamic changes in data. MetaCD can not only improve the plasticity of our model on a single task, but also ensure the stability and generalization of the model on sequential tasks. Comprehensive experiments on five real-world datasets show that MetaCD outperforms other baselines in both accuracy and generalization.