Learning Analytics - Science topic

Collaborative problem-solving is a critical 21st-century skill, yet how scaffolding strategies (idea-oriented cognitive stimulation or task-oriented procedural support) shape student engagement across diverse online collaborative environments is insufficiently understood. This lack of understanding makes it challenging to design productive strategi...

Background A key skill for self‐regulated learners is the ability to critically interpret and act on feedback—key components of feedback literacy. Yet, the connection between feedback literacy and self‐regulated learning (SRL) remains underexplored, particularly in terms of how different levels of feedback literacy influence SRL processes in authen...

Obhective: The main objective is to map the evolution of current literature on Learning Analytics and identify the most influential sources of knowledge, in order to understand the development trends in the field and provide a foundation for future research. To this end, a bibliometric analysis was conducted in the Scopus database using Vosviewer s...

The ethical integration of the data generated by learners into educational practices is of great importance now that data-rich technologies are prevalent in education. Despite the common agreement that learners should have agency in deciding what to do with their data, existing ethical discussions focus on policies or algorithms, with limited atten...

This thesis investigates the complex interplay between self-regulated learning, student engagement, and learning analytics in online educational environments. Through three related studies, the research examines how learning analytics can support self-regulated learning, how students' selfefficacy beliefs influence their learning behaviors, and how...

O artigo apresenta o processo de recomendação de Estratégias Pedagógicas baseadas em Cenários Socioafetivos em um Ambiente Virtual de Aprendizagem (AVA). Os Cenários Socioafetivos (CSA) utilizando Learning Analytics são o cruzamento dos estados de ânimo (animado, desanimado, satisfeito, insatisfeito e indefinido afetivo) e indicadores sociais (ausê...

Learning analytics have gained relevance in online higher education over the last decade, focusing on supporting teaching and learning processes while enhancing students' academic performance. These methods leverage students' academic data to inform decision-making and interventions aimed at improving educational outcomes. However, recent research...

This study aims to create a model using machine learning algorithms to determine teacher candidates’ misconceptions about electricity, to determine the algorithm with the highest success rate, and to realize students’ conceptual changes about electricity with activities prepared based on differentiated teaching in a laboratory environment. A design...

Learning analytics (LA) can improve student outcomes and support institutional decision-making in higher education. However, its adoption remains limited in developing countries due to concerns about trust, privacy, and institutional readiness. This study addresses this gap by examining the factors that influence LA adoption from a multi-stakeholde...

This article analyzes educational research approaches in the context of educational data science. Based on traditional research paradigms, it examines the extent to which educational data science implies a potential paradigm shift in educational science. The increasing digitalization and the resulting availability of large amounts of data open up n...

Project-based learning plays a crucial role in computing education. However, its open-ended nature makes tracking project development and assessing success challenging. We investigate how dialogue and system interaction logs predict project quality during collaborative, project-based AI learning of 94 middle school students working in pairs. We use...

This review traces the rapid convergence of liquid biopsy science and machine learning analytics in breast oncology. After systematically screening publications from 2020 through 2025, it synthesizes forty five studies that examine routine complete blood count indices, circulating tumor DNA, circulating microRNAs, circulating tumor cells, and extra...

The introductory programming course (CS1) at the university level is often perceived as particularly challenging, contributing to high dropout rates among Computer Science students. Identifying when and how students encounter difficulties in this course is critical for providing targeted support. This study explores the behavioral patterns of CS1 s...

The recent surge in the use of learning analytics in education has led to the development of more adaptive and personalized learning environments (APLE). A key feature of APLE is its capability to support learning tailored to various student needs and goals. Although educational studies emphasize goal setting as essential for effective student lear...

In this article, we present a novel multimodal feedback framework called MOSAIC-F, an acronym for a data-driven Framework that integrates Multimodal Learning Analytics (MMLA), Observations, Sensors, Artificial Intelligence (AI), and Collaborative assessments for generating personalized feedback on student learning activities. This framework consist...

This study presents the design, implementation, and validation of the Smart Teaching Factory (STF) framework, which integrates Extended Reality (XR), Artificial Intelligence (AI), and animated simulation technologies to enhance vocational education. Targeting 62 electronics engineering students and 6 vocational instructors across three Indonesian p...

Simulators have become central in professional training, in this case maritime education, where they support the development and assessment of skills and competencies required of competent seafarers. This study aims to inform the design of a learning analytics dashboard utilizing multimodal learning analytics to deliver automated, adaptive feedback...

Background Learning analytics dashboards (LAD) have been developed as feedback tools to help students self‐regulate their learning (SRL) by using the large amounts of data generated by online learning platforms. Despite extensive research on LAD design, there remains a gap in understanding how learners make sense of information visualised on LADs a...

In CSCL research, audiovisual data plays a central role in understanding collaborative learning processes and fostering methodological advancements, such as the Mondrian transcription charts and multimodal learning analytics. DOTEbase is a powerful tool designed to support the systematic analysis of rich audiovisual datasets, empowering researchers...

Predicting mental health-related challenges, such as programming anxiety, is essential for delivering timely support and improving academic outcomes among students in computer-related disciplines. This study examined the use of Automated Machine Learning (AutoML) to predict programming anxiety levels using a dataset composed of demographic, academi...

Understanding the dynamics of transitions plays a central role in educational research, informing studies of learning processes, motivation shifts, and social interactions. Transition network analysis (TNA) is a unified framework of probabilistic modeling and network analysis for capturing the temporal and relational aspects of transitions between...

The rise of generative artificial intelligence (GAI), especially with multimodal large language models like GPT‐4o, sparked transformative potential and challenges for learning and teaching. With potential as a cognitive offloading tool, GAI can enable learners to focus on higher‐order thinking and creativity. Yet, this also raises questions about...

To improve the online learning experience, adaptive learning technologies are being used to personalise learning content to suit individual learning needs, with learning analytics being integrated to collect data about the student usage behaviour on the platform. Research indicates that the adaptive learning platforms promote a supportive learning...

While behavioral, contextual, and physiological data streams have long been used to investigate self-regulated learning (SRL), a systematic understanding of the current state how different data streams and modalities contribute to measuring regulation processes across diverse learning contexts remains limited. This systematic literature review prov...

This study presents the development and validation of a Learning Analytics Rubric for Self-Regulated Learning (SRL) in higher education. The rubric aims to measure students' SRL processes within learning management systems (LMS) in a scalable, consistent, and explainable manner. The research follows a design-based approach, mapping validated SRL sc...

This study conducts a detailed bibliometric analysis of the Learning Analytics (LA) and Educational Data Mining (EDM) research from 2014 to 2023 as well as content analyses based on the abstracts of the selected papers. It explores the evolution of the LA & EDM fields, their diverse applications, and the data sources employed in the research. 356 p...

Introduction Middle-aged and older adults are highly susceptible to depression. For this reason, early identification and intervention can substantially reduce its prevalence. This study innovatively proposed a visual risk prediction system for depressive symptoms and depression in middle-aged and older adults, rooted in machine learning and visual...

Personalized learning in higher education aims to enhance student motivation, engagement, and academic outcomes. Learner personas as representations of students offer a promising approach to personalizing learning in technology-enhanced environments, particularly in combination with learning analytics (LA). This study explores how LA can be used to...

To better understand and optimize learning and the environments in which it takes place, learning analytics involves gathering, measuring, analyzing, and reporting data about learners. It supports well-informed academic decision-making by giving institutions useful information about students' behavior, performance, and engagement. The Open Universi...

This article investigates the state of AI regulations from diverse geopolitical contexts including the European Union, the United States, China, and several African nations, and their implications for learning analytics (LA) and AI research. We used a comparative analysis approach of 11 AI regulatory documents and applied the OECD framework to cla...

A major issue in distant learning is student dropout, particularly at open universities where variable learning styles could result in uneven participation. Early detection of student dropout can facilitate prompt interventions and enhance academic results. This study compares several machine learning models for predicting student dropout using the...

Engaging students in collaborative knowledge building (CKB) is important. However, previous studies that aimed to promote CKB used question prompts to instruct students on how to proceed their discussions. While these studies provided valuable insights into how to foster CKB, they failed to support students in constructing strategic knowledge of CK...

Deploying autonomous robots in safety-critical applications requires safety guarantees. Provably safe reinforcement learning is an active field of research which aims to provide such guarantees using safeguards. These safeguards should be integrated during training to prevent a large sim-to-real gap. While there are several approaches for safeguard...

Blended learning, a pedagogical approach that combines face-to-face and online activities, is widely adopted in higher education due to its flexible nature. This flexibility encourages personalisation however there is variation in the way educators apply online technologies, including the use of artificial intelligence (AI). The deliberate use of t...

Quality feedback is essential for supporting student learning in higher education, yet personalized feedback at scale remains costly. Advances in learning analytics and artificial intelligence now enable the automated delivery of personalized feedback to many students simultaneously. At the same time, recent feedback research increas-ingly emphasiz...

This paper presents a novel graph neural network (GNN)-based model for personalized learning with advanced graph neural networks, incorporating both graph convolutional networks (GCN) and graph attention Networks (GAT). Our model leverages GCN, which consists of multiple layers embedding deep learning models, to aggregate data from neighboring node...

Integrating artificial intelligence (AI) into water treatment processes offers transformative potential for enhancing chemical operations' sustainability and energy efficiency. This paper explores the development of AI-powered optimization frameworks to address the dual challenges of resource conservation and environmental protection in water treat...

Amid the growing need to keep learners abreast of rapid technological advancements brought about by the Fourth Industrial Revolution, this study explores perceived needs of students in virtual learning environments supported by emerging technologies. A survey was conducted across five leading open universities in Southeast Asia. The study aimed to...

Learning Analytics (LA) concerns the analysis of educational data to enhance learning processes and conditions. Its growing use in higher education has inspired synthesis studies on its applications and effectiveness in studying academic performance, with have had heterogeneous approaches and results. Previous meta-reviews have not provided compreh...

Learning analytics and educational data mining are rapidly evolving fields that leverage data-driven methods to enhance teaching, learning, and institutional decision-making. This review provides a comprehensive overview of the key analytical techniques and tools employed in learning analytics and educational data mining, including classification,...

With the development of mobile Internet and digital technologies, online education platforms transcend time and space constraints to provide ubiquitous learning environments. However, high dropout rates and low pass rates pose a great challenge. Predicting student performance enables early identification of academic failure tendencies, facilitating...

This study critically analyzes the development of artificial intelligence (AI) research in education using a bibliometric approach, leveraging data from 191 Scopus-indexed documents during the 2015-2024 period. Employing Biblioshiny software, the study identifies an annual publication growth rate of 44.22% and an average of 11.88 citations per docu...

Assessment is part of teaching and learning at all levels of education and when it's taken into consideration it impacts students' academic performance. At different levels of education, assessment takes different trajectories. From summative, formative, diagnostic and learning analytics, assessment for learning plays a major role in assisting inst...

As large language models (LLMs) become integral to educational technology, concerns about their effectiveness, ethical deployment, and personalization grow. This paper introduces a human-centered framework for integrating LLMs into educational environments via open-source user interfaces. We propose a novel approach that enables participatory evalu...

The complex processes of collaborative knowledge construction require a multimodal approach to capture the interplay between learners, tools, and the environment. While existing studies have recognized the importance of considering multiple modalities, there remains a need for a comprehensive framework that explicitly models the dynamics of knowled...

Graz University of Technology originally launched a study progress dashboard in 2020 to help students monitor their academic progress and better understand their degree structures. In response to systematic changes in the university's academic data modeling and the phasing out of legacy curricula between 2022 and 2024, the dashboard underwent a com...

Inquiry-based learning (IBL) is a practice-oriented approach where students pose questions, conduct investigations, and interpret data to develop scientific knowledge and exploratory skills. Learning analytics (LA) holds great potential to capture these dynamic processes, which provides valuable insights to understand student inquiry behaviours and...

Background Methodology Contribution Findings Research indicates that many students’ learning time is wasted due to cyber- loafing, which involves non-course-related activities on their digital devices. Smartphones present a more significant potential for distracting learners than other technological instruments because of their availability, ease o...

Researchers and practitioners from different disciplines (e.g., educational science, computer science, statistics) continuously enter the rapidly developing research field of learning analytics (LA) and bring along different perspectives and experiences in research design and methodology. Scientific communities share common problems, concepts, theo...

This study investigates the impact of using the Pebasco app, a mobile microlearning tool, to train peer feedback skills within a mandatory university English as a Foreign Language (EFL) course employing a communicative language teaching (CLT) approach. Building on previous research, this study aims to assess how the app influences students' ability...

This paper presents the refactoring and evaluation of IDeRBlog, an educational blog platform designed to support German language acquisition in primary schools. Originally developed as part of an EU Erasmus project, IDeRBlog aims to improve students' spelling skills through a combination of intelligent feedback and blogging features. The recent red...

Automated classification of learner-generated text to identify behavior, emotion, and cognition indicators, collectively known as Learning Engagement Classification (LEC), has received considerable attention in fields such as NLP, Learning Analytics, and Educational Data Mining. Recently, Large Language Models (LLMs), such as ChatGPT, which are con...

The development of information and communication technologies has created limitless prospects for using augmented reality (AR) in various fields. Unfortunately, the multitasking nature of AR systems prevents learners from successfully reflecting and retaining knowledge. This study developed and designed a learning analytics dashboard (LAD) with thr...

Sustainable education systems based on developments in educational design for design variables specific to educational technology still occupy a large space in research priorities in many classified scientific journals, and among these variables augmented reality. In addition, educational data mining, intelligence applications in education, learnin...

Sustainable education systems based on developments in educational design for design variables specific to educational technology still occupy a large space in research priorities in many classified scientific journals, and among these variables augmented reality. In addition, educational data mining, intelligence applications in education, learnin...

Background: The increasing prevalence of online education has raised concerns about student engagement and success. Learning analytics (LA) offers potential for early detection and support of at-risk students.

Multimodal learning analytics (MMLA) has become a prominent approach for capturing the complexity of learning by integrating diverse data sources such as video, audio, physiological signals, and digital interactions. This comprehensive review synthesises findings from 177 peer-reviewed studies to examine the foundations, methodologies, tools, and a...

The prediction of student academic performance through data analysis and machine learning has become increasingly significant for improving educational systems and student outcomes. This study explores three publicly available datasets-Open University Learning Analytics Dataset (OULAD), xAPI-Edu-Data, and the UCI Student Performance dataset-to iden...

This study contributes to the understanding of the impact of self-efficacy in a high-fidelity simulator training by unpacking the association between general self-efficacy, task-specific self-efficacy, and performance. Miscalibration of self-efficacy among the trainees was studied, analyzing differences in overestimating, accurate, and underestimat...

Generative AI offers potential for educational support, but often lacks pedagogical grounding and awareness of the student's learning context. Furthermore, researching student interactions with these tools within authentic learning environments remains challenging. To address this, we present JELAI, an open-source platform architecture designed to...

Recent advancements in Natural Language Processing (NLP) have facilitated the analysis of student-generated language products in learning analytics (LA), particularly through the use of NLP embedding models. Yet when it comes to science-related language, symbolic expressions such as equations and formulas introduce challenges that current embedding...

In a world changed by the COVID-19 pandemic, in 2020 universities had to completely rethink and immediately transform their teaching to a fully online setting. As a result, students had to learn from home and organize their learning by themselves. In a natural experiment, data about learning processes indicate that students learned more engaged and...

Effectiveness of Artificial Intelligence-Based Learning Analytics Tool in Supporting Personalized Learning in Higher Education. Objective: The use of Artificial Intelligence (AI) in higher education has become one of the significant innovations to improve the quality of learning, especially through personalization. However, the effectiveness of AI-...

The focus of this paper is to address an educational research question – the correlation between a student’s practice duration and performance in problems. This intends to offer rule-of-thumb advice for students in formulating a particular study plan. Throughout the paper, we investigate such a topic by using data from roboTutor tablets, which prov...

Introduction Sparse education on sexual health promotion for health and welfare professionals can lead to unequal sexual health care provision, with related needs and rights being insufficiently met. To improve knowledge for health and welfare professionals, co-production and shared learning are essential, as students’ learning, and professional de...

Inadequate consideration of course workload in undergraduate students’ course selections has contributed to adverse academic outcomes. At the same time, credit hours, the default institutional metric to convey time-based course workload to students, has been shown to capture students’ experienced workload insufficiently. Recent research documents t...

The role of resources and capabilities in shaping and implementing a firm’s strategy is paramount. The COVID-19 pandemic underscored the necessity for managers to possess a decision-making model that facilitates the selection of resources and capabilities in a real-time, dynamic, adaptive, and iterative manner. However, the dynamic capabilities fra...

This systematic review examines the application of learning analytics to enhance user experience within Learning Management Systems in higher education institutions. Addressing a salient knowledge gap regarding the optimal integration of learning analytics for diverse learner populations, this study identifies analytical approaches and delineates i...

Laboratory instruction is crucial for promoting experiential learning, analytical reasoning, and scientific investigation, which are fundamental for academic achievement in fields such as General Chemistry. Anchored on SDG 5 (Quality Education) and SDG 9 (Industry, Innovation, and Infrastructure), this study sought to determine the principal determ...

This systematic review comprehensively examines the application and impacts of Educational Data Mining (EDM) over the past decade. It explores the use of various data mining tools and techniques, statistics, and machine learning algorithms in education. The review discusses how EDM helps understand and improve the learning experience, educational s...

Teachers who are aware of their students’ strengths and weakness can tailor their teaching methodologies to meet the challenging students efficiently for better results. This helps them to identify any potential learning challenges at an early stage leading to improved academic performance and success ratio. This also fosters a learning environment...

Learning Analytics Dashboards (LADs) often fall short of their potential to empower learners, frequently prioritizing data visualization over the cognitive processes crucial for translating data into actionable learning strategies. This represents a significant gap in the field: while much research has focused on data collection and presentation, t...

Classroom orchestration tools allow teachers to identify student needs and provide timely support. These tools provide real-time learning analytics, but teachers must decide how to respond under time constraints and competing demands. This study examines the relationship between indicators of student states (e.g., idle, struggle, system misuse) and...

Artificial intelligence continues to reshape contemporary educational systems, offering both transformative opportunities and inherent challenges. The integration of AI technologies has facilitated unprecedented personalization of learning experiences, enabling adaptive content delivery that responds to individual student needs while simultaneously...

The digital revolution has transformed various aspects of education, including assessment practices. This article explores the pedagogical implications and challenges of rethinking assessment in the digital age. Grounded in current literature, the article presents a conceptual framework for digital assessment and discusses the key aspects of assess...

Advancements in computing and information technologies have significantly transformed educational practices. This transformation can be understood through three paradigms. The first paradigm (Artificial Intelligence Guided Learning) involves systems that model knowledge and guide cognitive processes, positioning learners as passive recipients. The...

Teamwork is an essential part of professional life and cooperation skills are necessary for students for successful employment. The main task of higher education is to increase the competitiveness of graduates in the job market by creating educational programs aimed at teamwork skills development. A reliable measurement method is needed to observe...

У статті досліджено сучасні підходи до розробки та впровадження інформаційно-аналітичних систем (ІАС) в управлінні освітнім процесом закладів вищої освіти (ЗВО) України в умовах цифрової трансформації. Визначено, що ІАС є не лише засобом автоматизації адміністративних функцій, а й стратегічним інструментом, що забезпечує аналітичну підтримку прийня...

This paper explores the integration and innovative application of educational technology in contemporary learning environments. It discusses how digital tools, platforms, and systems are reshaping pedagogical practices and enhancing educational access and effectiveness. By examining technologies such as artificial intelligence, augmented and virtua...

Researchers have extensively explored learning analytics in online courses, primarily focusing on linear course structures where students progress sequentially through lessons and assessments. However, non-linear courses, which allow students to complete tasks in any order, present unique challenges for learning analytics due to the variability in...

Healthcare systems based on intelligence evolve medical practices through the combination of Internet of Things electronics with machine learning algorithms for predictive diagnosis and customized medical care. Medical decisions can become potentially unsafe when the training data contains biased or tampered information so it remains crucial to mai...

This study investigates the transformative role of Artificial Intelligence (AI) in enhancing instructional leadership and fostering academic excellence within the framework of smart school management. It is anchored in the emerging Integrating AI into Instructional Leadership Theory, which synthesizes principles from Transformational Leadership The...

Amotivation, as a construct of the Self-Determination Theory (SDT), represents a critical barrier to student engagement and success in engineering education. While a lot of study has concentrated on intrinsic and extrinsic motivators, there has been little focus on diagnosing and addressing amotivators within this context. This study explores the p...

Simulation and gamification offer valuable pedagogical approaches, providing safe environments for dental students to practice complex professional skills. Developing clinical reasoning is crucial as students perform irreversible procedures early in their training. Traditional methods may offer limited opportunities to experience decision consequen...

This research explores the application of multimodal data, including eye-tracking, heart rate variability, and emotion recognition, to deliver real-time adaptive feedback in learning environments. Specifically , the study investigates how this feedback influences learner engagement, task performance, and persistence during English language conversa...

The ability to accurately predict and analyze student performance in online education, both at the outset and throughout the semester, is vital. Most of the published studies focus on binary classification (Fail or Pass) but there is still a significant research shortcoming in predicting performance of students across multiple categories. This stud...

Despite the growing use of large language models (LLMs) in educational contexts, there is no evidence on how these can be operationalized by students to generate custom datasets suitable for teaching and learning. Moreover, in the context of network science, little is known about whether LLMs can replicate real-life network properties. This study a...

IT Project and Change Management (ISYS90050) is a core subject in the Master of Information Systems course, designed to be practice oriented. It helps students develop technical and interpersonal skills essential for becoming effective IT project managers. Managing real-world projects requires more than conceptual understanding—it requires abilitie...

When students enter higher education, self-regulated learning (SRL) involving goal setting, planning, monitoring, and reflection is crucial for academic success. This study systematically reviews SRL strategies, supporting technologies, and their impacts, especially with the shift to online learning due to the COVID-19 pandemic. Following Kitchenha...

Student-facing learning analytics has been gaining attention in educational research as it offers a promising approach to providing personalised feedback on students' online learning activities. However, there is limited understanding of the competencies required by students to effectively utilise this feedback and designs that can cultivate such c...

Free play is a fundamental aspect of early childhood education, supporting children's cognitive, social, emotional, and motor development. However, assessing children's development during free play poses significant challenges due to the unstructured and spontaneous nature of the activity. Traditional assessment methods often rely on direct observa...