Generative Artificial Intelligence is increasingly used to enable personalization in digital learning environments, yet its role within game-based learning remains insufficiently mapped and conceptually fragmented. Existing research primarily focuses on personalization at the individual level, neglecting group level support, adaptive collaboration, and role-based guidance in shared learning environments. To clarify the structure of this emerging field, this study uses a science-mapping analysis to examine the intersection of generative AI, personalization, and game-based learning. Using a structured Scopus search and established science-mapping techniques, the analysis identified dominant conceptual themes and thematic developments. The results reveal significant gaps related to adaptive support, explainable feedback, and collaborative personalization mechanisms. Guided by these insights, the paper proposes an ontology-based framework that extends personalization to collaborative, game-based settings through role prompts, micro-scenarios, and adaptive explanation mechanisms. The framework is accompanied by an implementation that demonstrates its key components and illustrates its applicability within a game-based learning environment. This study provides a structured map of the field and lays the groundwork for future system design.

This paper presents a comprehensive review of the integration of Multi-Intelligent Agents (MIA) and Generative AI (GenAI) in learner assessment. Through a systematic bibliometric analysis of literature from 2019 to 2024, we identify key research trends, methodologies, and applications in educational contexts. Our findings reveal that MIA excels in orchestrating adaptive and collaborative assessments (34.6% of research), while GenAI demonstrates significant potential in higher education (50% of research) for content generation and personalized feedback. The combined approach remains underexplored (14.6% of studies) but shows promise for developing more effective assessment frameworks. This study contributes to the field by mapping the evolution of MIA and GenAI in assessment, identifying current gaps in empirical validation, and proposing a hybrid model that enhances both automation and personalization. It offers a critical perspective on practical challenges and ethical concerns, setting a structured research agenda for future explorations.

This paper examines assessment indicators for evaluating learning outcomes in higher education and proposes a structured framework that categorizes them into seven key areas: Content Quality, Engagement Metrics, Study Time, Assessment Indicators, Difficulty and Efficiency, Participation Metrics, and Motivation and Tracking Indicators. This framework helps educators better understand student performance and engagement. Building on this, an ontological model is introduced to standardize and organize these indicators, enhancing interoperability and supporting automated reasoning for educational decision-making. It is compatible with Learning Management Systems and includes mechanisms for generating automated feedback for timely and personalized interventions. An empirical evaluation shows the model’s effectiveness in identifying at-risk students and providing tailored feedback. The paper concludes by discussing the framework’s implications for improving assessment practices and future directions involving advanced analytics and artificial intelligence in learning outcome assessments.

The use of artificial intelligence (AI) in medicine and healthcare has expanded significantly, particularly in classification and prediction tasks. Machine learning algorithms analyze medical data, identify patterns, and generate predictions that assist in clinical decision-making. However, challenges such as data quality, redundancy, and sensitivity hinder the development of optimal predictive models. This study focuses on improving impairment level prediction by leveraging high-quality datasets and advanced machine learning techniques. Using medical records from cerebral palsy patients, we evaluate six machine learning algorithms: Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest (RF), Logistic Regression (LR), Naïve Bayes (NB), and XGBoost. Our objective is to determine the most effective model for predicting Gross Motor Function Classification System (GMFCS) levels, a key indicator in cerebral palsy assessment. Additionally, we introduce MEDX-Ensemble, a novel interpretable ensemble model that integrates multiple classifiers to enhance prediction accuracy while maintaining clinical explainability. Performance evaluation, including Weighted Kappa scores, reveals that advanced models like XGBoost and MEDX-Ensemble achieve the highest accuracy and robustness, demonstrating substantial agreement with physician classifications. These results demonstrate the potential of AI-driven models to enhance patient assessment and clinical decision-making. Through rigorous validation of diverse machine learning techniques, this study identifies optimal methodologies for GMFCS level prediction, contributing to reliable and interpretable healthcare predictive models.

Game-based learning environments are capturing increasing attention for their ability to engage learners and promote knowledge acquisition. Artificial intelligence holds immense potential to personalize learning experiences and deliver intelligent assessment. Collaborative learning approaches, when integrated seamlessly with game settings, can further enhance the learning process. This study explores the domain of intelligent collaborative assessment in game-based learning environments through bibliometric analysis. Using data from Scopus, we uncover important research themes, global impact trends, influential sources, and the evolution of research over time. Our analysis of findings reveals a gap in research concerning the integration of AI assessment within collaborative game-based learning environments. To address this gap, we propose a novel framework that utilizes continuous assessment, personalized learning, and dynamic adaptation to optimize the learning experience for all participants. This study provides valuable insights to guide future research and educational improvements in intelligent collaborative assessment for game-based learning.

In today’s collaborative learning environments, effective assessment plays an important role in assessing knowledge acquisition and fostering skill development. The integration of serious games adds an interactive and engaging dimension to these environments, offering opportunities for immersive learning experiences. This combination not only evaluates learners’ progress but also enhances their engagement and motivation, contributing to more effective educational outcomes. This research proposes an innovative ontological model specifically designed for intelligent assessment scenarios with serious games in collaborative environments. Our research aims to enhance learning experiences and skill development by integrating artificial intelligence, education, and serious games. The suggested ontological model incorporates stealthy assessment methods, personalization, and adaptivity to accurately represent the dynamics of collaborative serious gaming. Our approach fills in the gaps in the research by integrating personalized instruction, stealth assessment, and adaptive gameplay in a collaborative environment. We validate the model to make sure it is accurate and consistent and to make sure there are no logical conflicts. This work creates paths for future research, focusing on intelligent assessment and collaborative learning within the context of educational serious games.

As the demand for more effective and efficient eLearning assessment systems continues to rise, there is a growing need for innovative approaches. This paper introduces the Intelligent Collaborative Assessment Framework (ICAF), which is a novel ontology-based framework that integrates Artificial Intelligence (AI) and collaborative tools to enhance assessment activities in cyberspace eLearning environments. Our research approach involved developing a specific ontology to capture essential concepts related to collaborative eLearning assessment, guiding the creation of the ICAF. The architecture of the ICAF consists of interconnected components that work in synergy to support assessment activities in cyberspace eLearning environments. One of its key features is the integration of collaborative learning techniques, which fosters a more engaging and effective learning experience. Additionally, the framework incorporates learning analytics and machine learning algorithms to analyze group learning patterns and deliver precise and valuable feedback. By presenting the viability and potential benefits of the ICAF, we demonstrate how the ICAF has the potential to significantly enhance assessment practices and facilitate collaborative learning in cyberspace eLearning environments.

Open Educational Resources (OERs) have emerged as indispensable components of educational innovation, encompassing freely accessible teaching, learning and research materials. The increasing variety and quantity of OERs present a challenge in terms of assessing their quality. A structured recommendation framework is needed to organize and categorize information and knowledge related to OERs and then systematically evaluate the quality of these resources and most importantly enable informed decision-making in educational settings. This research paper focuses on the proposal of a recommender system supporting open educational practices, with a particular emphasis on the quality of OERs. In this context, this research work proposes the development of an ontology called Open Learning Object Metadata (OLOM) specifically designed for OERs. Indeed, OLOM was built upon an existing Learning Object Metadata (LOM) ontology, incorporating additional classes and attributes as necessary. By improving resource discovery and organization, OLOM assists educators in enhancing the efficiency and effectiveness of OERs. Our ontology-based proposed framework will contribute to the assessment and organization of OERs, facilitating informed decision-making and optimizing their reuse and interoperability in educational settings.

Assessment is a critical component of any teaching-learning process. It is the only way to gain a better understanding of the knowledge and abilities of the learners, especially in a collaborative learning environment. The learner must pay special attention to interactions and real-world context when selecting collaborative situations and activities. As a result, it is critical to ensure that assessment methods and techniques are adapted so that the learning process is better suited to each group of learners, with their unique learning style, background, needs, previous experiences, and most importantly, context. This paper addressed two major issues in the development of a personalized formative assessment system that will be used to assess the knowledge, skills, and competencies of individual and group learners in an online collaborative learning environment. One approach is to design an adaptive assessment path that helps learners achieve specific learning goals based on previous learner performance, level, and context. The other is to make a personalized recommendation using a Context-Aware Recommender System (CARS), which monitors group formation while performing collaborative assessment activities. To formalize and well define our proposed system, we suggest a semantic web approach using ontologies and eLearning standards, CMI5 to describe the proposed assessment path, and IEEE PAPI for the learner model, all of which allow data reusability and interoperability.

Currently, there is a daily evolution of the world and our current digital society faces challenges for changing the environment. Currently, learning environments are undergoing an evolution due the increasing development of mobile technologies. Designing and implementing Smart Learning Environments (SLEs) has emerged to enhance the learning process and the creation of content. In this paper, we are interested on SLE. Our objective is to propose a new pedagogical approach to provide adaptive and personalized open learning based on Computational Thinking (CT). This contribution describes the main theoretical relationships between SLE, Open Learner Model, Open Education Resource, Open Practice and Open Pedagogy when developing SLE to promote the learning process. New pedagogical approaches, based on openness, need to be implemented. The goal is to orchestrate between different features of SLE in order to propose a Smart Open Learning Environment (SOLE). We focus in particular on the pedagogical scenario that will be deployed in a Smart Open Learning Environment (SOLE). The proposed scenario is promoted by Smart Open Pedagogy to enhance CT. We aim to deliver open assessment adapted to specific learner context profile, progress and CT’s Level in the learning.

Higher education still follows a traditional one-size-fits-all, centralized, controlled, and static learning/teaching approach. Moreover, there is a mismatch between the competencies acquired by the student and the industry needs. Addressing the problem should include effective cooperation with industry, better integration with innovative research, and internationalization. We require a move away toward a more personalized, networked, agile, and industry-oriented model for learning. In this research work, we propose a Scenario for using learning analytics to recommend personalized micro-credentials based on a competences score as a solution for reducing the gap between the industry needs and the actual students’ skill set.

Project-based learning allows the learner to be involved in the analysis of a given project and the search for possible solutions. Proposed projects usually have problems related to practical facts about the content of the proposed course. An online course could be based on this learning concept; Thus, providing learners with collaborative and contextualized learning. In such an environment, the online tutor plays an important role. In fact, we distinguish two types of tutors: academic and professional. The tutorial functions are related to the selection as well as contextualization of the proposed projects and also the monitoring and evaluation of the learners. In order to improve the efficiency and responsiveness of e-learning and to better manage project-based learning processes, we are also interested in the notions of peer tutoring in a learning environment by project online.The goal of this research is to create the tutoring process in project-based learning environments using semantic web technologies

In the learning analytics field, it is highly significant to track and collect the big educational data to improve the learning experience. In fact, one of the e-learning standards for data interoperability which had attracted a remarkable amount of attention in the last years is the Experience API (xAPI). In this paper, we explore the use of xAPI in the learning analytics field. Therefore assessment data represents an important proportion of the educational data generated. When we focus on assessment, we can launch a new source of data that can be analyzed and hence contribute to the improvement of the field of learning analytics. In fact, we discuss the suitability of xAPI standard to track the assessment data and try to enhance its data model to support effectively the assessment analytics. An ontological model is proposed supporting assessment analytics purpose based on the weaknesses of the xAPI data model from assessment point of view. Since our proposed pattern is an ontological model, this gives us the chance to reason about the assessment data by performing some logic rules edited with SWRL(Semantic Web Rule Language) for supporting inference mechanisms related to the leaner level according to its assessment performance.

Mobile assessment is a new delivery mode of assessment that offers ubiquitous access to testing material anytime and anyplace. Due to its mobile features, it has the potential to complement and to improve other assessment delivery modes (paper-and-pencil based or computer-based). Moreover, semantic Web technologies have been applied in recent years with different purposes in education. But, their applications for generating useful personalized mobile assessment resources have not been researched enough so far. In this paper, we propose an assessment system built on semantic Web technologies and Web services to support personalized self-assessment in mobile environments. In particular, we present the MobiSWAP system that presents an assessment tool based on the use of ontologies and the REST architecture. With MobiSWAP learner can generate and answer to questions and tests using mobile devices. We provide the system architecture and the implementation. We have carried out also an experiment with computer science students to determine the degree of their satisfaction to use the MobiSWAP system and to adopt mobile assessment.

Learning analytics has attracted a remarkable attention in the last years due to its potential to support and improve the learning experience. The first step of the learning analytics process is the educational data collection, therefore it is highly significant to track and collect the big educational data generated (learning data, assessment data, communication data etc). Assessment data represent an important proportion of the educational data generated. When we focus on assessment, we can launch a new source of data that can be analyzed and hence contribute to the improvement of the field of learning analytics. In this paper, we will focus on assessment data by proposing an assessment analytics architecture. This architecture uses the semantic web technologies and focus essentially on analyzing the set of assessment activities, the assessment result and the assessment context. These assessment data are conceived and annotated via an ontological model, inspired from the xAPI data model, which enable performing logic rules for supporting inference mechanisms related to assessment analytics and especially concerning the concrete level of the assessment actor and the level of difficulty of the assessment object.

Closely linked to the demand of labor market for the skills and competences required on the workplace, designing new approaches enhancing actual assessment systems is becoming a necessity. These systems have to carry out specific requirements, such as recognition and reflect of the learner's real acquired competences. Nevertheless, most of the research work focuses on the competence-based approaches disregarding the assessment process. Following some previous works where we discussed our competence-based assessment model, we present in this paper an overview of the overall approach and we provide a generic scenario model to depict the performing of the competence-based assessment process.

Providing personalized and context-aware assessment contents to learners in mobile environment require to consider and to represent the term context in such environments. Context-awareness means being able to collect environment and assessment resources information from the learner and surrounding equipment to provide learners with the context-related assessment activities and content. In this paper, we aim to provide learners with personalized assessment content. To serve this purpose, we first define the concept of MAO (Mobile Assessment Object) and we consider various parameters allowing mobile assessment personalization. Similarly, we detail models used to implement the semantics of our framework. Models are described through ontologies. Ontologies are one of the most functional means for representing data and allow a semantic information representation and interchange between different tools. Finally, we introduce a formal description for assessment personalization in a mobile learning environment.

Assessment plays an essential role in the educational activity, not only to verify the knowledge acquisition of learners, but also as a motivation factor. In this paper we consider the IMS/QTI specification. We first propose a formalization of the question structure in his specification based on ontology, representing its information model. Then we enhance this specification by adding new types of questions/interactions and apply them to an Object Oriented Programming (OOP) course. In this context, we specify a new type of interaction that we called "composite Text Interaction" and which can define questions of type "identify the errors in a program and correct them". The new type of question has been integrated into an editor for question construction supporting the IMS/QTI specification.

This paper describes the design, development and qualitative evaluation of a Web-based personalized assessment service of an object-oriented programming course at the University of Sousse. The assessment service was integrated in the personal reader software, of the University of Hannover and was designed to select specific questions based on the progress and performance in the course of each learner individually. This paper identifies benefits to learners brought about with the use of a personalized assessment service. It describes and discusses a first experiment of this tool. The evaluation was completed with the assistance of a group of ten students with different levels of prior programming knowledge. The students are enrolled in a computer science degree program at the Informatics College (ISITC) of the University of Sousse. The personalized assessment framework is introduced, with a description of its architecture and functionalities. An analysis of learner's feedback following this experiment is also provided