New Advances of Intelligence Measurement in the AI Era: Theory, Methods and Applications

A special issue of Journal of Intelligence (ISSN 2079-3200). This special issue belongs to the section "Contributions to the Measurement of Intelligence".

Deadline for manuscript submissions: 31 December 2026 | Viewed by 1821

Editors


E-Mail Website
Guest Editor
Department of Educational Psychology, East China Normal University, 3663 North Zhongshan Road Shanghai, 200062, China
Interests: psychometrics; principled item design and test development; AI-augmented automatic item generation and automated scoring; computeriszed adpative testing; validity theory; performance-based competence assessment

E-Mail Website
Guest Editor
College of Education, The University of Alabama, Tuscaloosa, AL 35404, USA
Interests: statistics and measurement; technology-enhanced digital assessments; test security; item response theory; item response times

Special Issue Information

Dear Colleagues,

Vast advances in the general artificial intelligence (gen-AI) have significantly impacted the field of measurement in general, and intelligence assessment in particular. These technological developments not only highlight the importance of measuring more complex cognitive constructs that are crucial in our-AI transformed society—such as executive functioning, critical thinking, collaborative ability—but also offer unprecedented opportunities to develop innovative AI-augmented approaches for assessing human intellectual capabilities. Therefore, it is essential to disseminate advances in research that leverage AI technologies to better understand and measure human intelligence, while ensuring that such developments are grounded in sound measurement theory and principles.

The focus of this Special Issue is new developments in psychological and educational measurement methodology and practices that integrate AI technology with rigorous measurement principles, specifically targeting the assessment of human intelligence and cognitive abilities. We encourage submissions that present theoretical work and/or empirical research related to innovative approaches to design, administer, analyze, interpret, and report assessments of cognitive function and intellectual capabilities, especially those involving complex cognitive constructs.

The topics that this Special Issue is soliciting submissions on include, but are not limited to, the following:

  • Innovative AI-enhanced approaches to measure cognitive abilities and intelligence factors (e.g., fluid intelligence, working memory, processing speed, executive functions);
  • Computer-supported, game-based, and scenario-based assessments of human intellectual capabilities;
  • Principled item design and test development for cognitive ability measurement;
  • AI-augmented automatic item generation for intelligence and cognitive assessments;
  • Multi-modal process data analysis and modeling in cognitive assessment contexts;
  • AI-assisted automated scoring of complex cognitive tasks and reasoning assessments;
  • AI-assisted data visualization and automated feedback for cognitive ability profiles;
  • AI-based personalized assessment of individual cognitive strengths and weaknesses;
  • Novel psychometric models for AI-enhanced cognitive assessment;
  • Validation studies of AI-augmented intelligence measures against established cognitive benchmarks.

Dr. Xiangdong Yang
Dr. Kaiwen Man
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a double-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Intelligence is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • cognitive ability assessment and intelligence measurement
  • complex construct modeling
  • principled item design and automatic item generation
  • AI-enhanced psychometric modeling for intelligence tests
  • automated scoring for complex cognitive constructs
  • process data modeling and multimodal data integration in cognitive assessment
  • data visualization
  • data harmonization across platforms (e.g., learning management and assessment systems) personalized and adaptive assessment
  • computer-supported, scenario-based or game-based assessment
  • new measurement models for innovative cognitive items
  • validity concerns in measuring intelligence using generative AI tools like ChatGPT

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

30 pages, 5699 KB  
Article
Evaluating Neural Networks Architectures for Competency Prediction from Process Data Using PISA Computer-Based Mathematics Assessment
by Huan Kuang
J. Intell. 2026, 14(4), 70; https://doi.org/10.3390/jintelligence14040070 - 20 Apr 2026
Viewed by 609
Abstract
Computer-based assessments generate rich process data that captures examinees’ interactions with test items. Using process data from the U.S. PISA 2012 computer-based mathematics assessment sample, this study applied recurrent neural networks to predict item-level correctness and assessment-level latent proficiency. The analysis also examines [...] Read more.
Computer-based assessments generate rich process data that captures examinees’ interactions with test items. Using process data from the U.S. PISA 2012 computer-based mathematics assessment sample, this study applied recurrent neural networks to predict item-level correctness and assessment-level latent proficiency. The analysis also examines the impact of expert-engineered features, levels of architectural complexity, action variability, and score variability on model performance. At the item level, most models achieved AUC values around 0.80, indicating good predictive performance. Moderate correlations were observed between latent proficiency from 30 items and predictions based on process data from a subset of items (n = 10). For item-level models, adding expert-engineered features reduces training time and may improve predictive performance with low action variability. For the assessment-level models, adding expert-engineered features improved performance. Model complexity, including model type (i.e., standard RNN, GRU, and LSTM), number of nodes, and number of layers, had little effect on accuracy and efficiency. Moreover, items with greater action variability were associated with better model performance. The findings suggest that simple neural network architectures are sufficient for modeling process data with limited action variability and that combining action sequences with expert-engineered features improves accuracy, efficiency, and interpretability. Full article
Show Figures

Figure 1

Back to TopTop