Human-Centered and Explainable AI for Personalized Adaptive Systems

Dear Colleagues,

As artificial intelligence is increasingly embedded in interactive systems that mediate learning, work, healthcare, and everyday decision-making, two research questions have moved to the center of machine learning and knowledge extraction [1]: how to build models that adapt effectively to individual users, and how to make the reasoning behind those adaptations transparent and accountable. The convergence of human-centered artificial intelligence (HCAI) and explainable AI (XAI) offers a principled response to both, connecting user modelling and personalization with interpretability, controllability, and human oversight.

This Special Issue, organized in the framework of the 6th International Conference on Novel & Intelligent Digital Systems (NiDS 2026) (https://nids2026.uniwa.gr/), invites original research articles and focused review papers on human-centered and explainable AI for personalized adaptive systems. We seek contributions that treat personalization and explainability as coupled design objectives rather than parallel tracks, and that report methodologically rigorous work involving real users, real tasks, and real data.

The first thematic pillar concerns explainable and interpretable models for user modelling, personalization, and adaptation. Topics of interest include, but are not limited to, interpretable user models, neuro-symbolic and hybrid representations of user knowledge and preferences, explainable recommender and tutoring systems, transparent affective and cognitive state modelling, uncertainty communication in personalized predictions, and explanation interfaces that convey model confidence and rationale to end users. We particularly welcome work that couples large language models or deep learning with post-hoc or intrinsic interpretability mechanisms, and studies that empirically examine how such explanations affect user understanding, trust, and behaviour.

The second thematic pillar concerns human oversight, controllability, and accountability in personalized adaptive systems. Contributions in this area include human-in-the-loop and human–AI collaboration frameworks for adaptive systems, mechanisms that let users inspect, contest, or steer personalized behaviour, fairness and non-discrimination auditing for user-facing AI, safeguards against manipulation and over-personalization, and evaluation methodologies that jointly assess personalization quality, explanation quality, and user agency. Application domains of particular interest include adaptive learning, clinical decision support, accessibility, and knowledge work.

We are particularly interested in contributions that report reproducible evaluations involving human participants and that critically reflect on the trade-offs between personalization performance, interpretability, and user autonomy.

In addition to this open call, selected papers presented at NiDS 2026 will be invited to submit substantially extended versions to this Special Issue. In such cases, the conference paper should be cited and mentioned on the first page of the submitted manuscript; authors are asked to disclose that the paper is based on NiDS 2026 in their cover letter, and to include a statement explaining what has been changed in comparison to the original conference version. Each submission should contain at least 50 % new material, e.g. technical extensions, more in-depth evaluations or additional use cases.

Importantly, this Special Issue is open to anyone who wants to submit a relevant research manuscript. We also welcome submissions from researchers and practitioners not involved in NiDS 2026. They will be subjected to the same peer-review process.

All submitted papers will be reviewed according to the standard peer-review procedure of Machine Learning and Knowledge Extraction. Accepted papers will be published in open access format and collected in the website of this Special Issue.

We look forward to your contributions.

[1] Holzinger, A.; Longo, L.; Cangelosi, A.; Ser, J.D. Research Frontiers in Machine Learning & Knowledge Extraction. Mach. Learn. Knowl. Extr. 2026, 8, 6. https://doi.org/10.3390/make8010006.

Prof. Dr. Yasushi Kambayashi
Dr. Filippo Sciarrone
Prof. Dr. Jaime Caro
Dr. Christos Troussas
Dr. Akrivi Krouska
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. Machine Learning and Knowledge Extraction 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 1800 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.