AI-Based Assessment and Learning Analytics: Psychological Constructs, Validity and the Human-in-the-Loop in AI-Enabled Education

Dear Colleagues,

The rapid integration of Artificial Intelligence (AI) into institutional educational settings is reshaping learning and fundamentally transforming paradigms of assessment, monitoring, and pedagogical support. Two developments are particularly transformative: the synergy of AI-enabled adaptive assessment (e.g., computer-adaptive testing, automated feedback, and AI-supported scoring) and learning analytics (e.g., process data, dashboarding, prediction, and early-warning systems). By combining these approaches, educational systems can now provide personalized learning pathways and support more timely instructional decisions across schools, universities, and professional training environments. At the same time, their growing adoption raises questions, from an educational psychological perspective, regarding construct representation, measurement validity, and responsible use.

This Special Issue focuses on the intersection of AI-based educational systems and the psychological constructs that underpin learning and instruction. As AI systems increasingly infer attributes such as competence, engagement, self-regulation, motivation, or collaboration from behavioral traces, construct clarity and measurement validity, as well as the alignment between computational models and psychometric theory, become paramount. We invite submissions that scrutinize construct representation, model-to-construct alignment, and fairness across diverse learner groups and contexts. Central questions include the following: What evidence supports the validity of AI-derived indicators? Under which conditions do adaptive assessments improve learning outcomes, and when might they introduce bias? How can learning analytics be translated into actionable insights without oversimplifying complex cognitive and affective processes?

A distinctive emphasis of this Special Issue is the “human-in-the-loop” approach in AI-based institutional education. Effective and responsible implementation of AI-based assessments and analytics depends on educators’ readiness to employ AI (e.g., attitudes, self-efficacy, trust, and adoption intentions) and their AI-related competencies (e.g., assessment literacy, data literacy, the ability to interpret outputs, and ethical judgment). We, therefore, explicitly welcome research on educators’ AI readiness, professional development interventions, and organizational conditions that enable or hinder the meaningful use of AI in instruction.

We welcome (a) systematic reviews and meta-reviews that consolidate the state of the art and identify open problems; (b) empirical studies, including field studies, experiments, quasi-experiments, and intervention studies; and (c) conceptual frameworks or position papers that advance the theoretical integration of educational psychology with AI-based measurement. By integrating perspectives from educational psychology, measurement theory, and applied AI research, this Special Issue will clarify what AI-based systems in institutional education can validly claim, how their outputs should be interpreted, and which human competencies are essential for their responsible and effective use.

Prof. Dr. Holger Horz
Dr. Maria Zirenko
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 single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Behavioral Sciences 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 2400 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.

• artificial intelligence in education (AIEd)
• adaptive assessment
• learning analytics
• educational measurement
• construct validity
• human-in-the-loop
• educator AI-related competencies
• educator‘ AI readiness
• algorithmic fairness and bias