• Xiao HU, The University of Arizona, United States [Chair Coordinator]
• Dirk IFENTHALER, Unversity of Mannheim and Curtin University, Germany
• Jelena M. JOVANOVIĆ, University of Belgrade, Serbia
• Elizabeth KOH, Nanyang Technological University, Singapore
• Bernardo PEREIRA NUNES, Australian National University, Australia
• Demetrios SAMPSON, University of Piraeus, Greece

Track description and topics of interest

The analysis and discovery of patterns that characterize human learning—and the contextual factors shaping these patterns—remain critical challenges across disciplines such as Education, Psychology, Sociology, Information Systems, and Computing. These patterns often relate to learners’ achievements, engagement, and the effectiveness of learning environments. Whether analyzing assessment in classrooms or identifying best practices in experiential learning, researchers strive to answer the fundamental question: how can we optimize learning efficiency, effectiveness, and overall learning experience and education quality? Today, this challenge is amplified by the continuously increasing complexity of digital ecosystems and the demand for personalized, equitable education.

Recent advances in artificial intelligence (AI), particularly Generative AI, have introduced transformative possibilities for education. Beyond traditional analytics, AI now enables automated content generation, personalized feedback, and adaptive learning pathways at scale. Combined with multimodal data sources—such as text, video, interaction logs, and biometric signals—these technologies offer unprecedented opportunities to study and enhance learning processes. At the same time, they raise critical questions about ethics, privacy, and fairness in educational AI. The Big Data in Education and Learning Analytics (BDELA) track invites contributions that explore opportunities and challenges at the intersection of big data, learning analytics, and AI-enhanced education, including innovative methods, applications, and theoretical frameworks.

Topics of interest include but are not limited to:

• Foundations and Infrastructure
  • Big data theory, science, and technology for education and learning
  • Scalable machine learning and data mining algorithms for educational big data
  • Big data infrastructure for academic institutions and EdTech platforms (cloud, edge, stream, mobile, high-performance computing)
  • Scalability and uncertainty handling in educational data analytics
• AI and Advanced Analytics
  • Generative AI for personalized learning, automated feedback, and learning content creation
  • AI-empowered learning analytics for student success
  • Multimodal learning analytics (text, video, interaction logs, biometric data)
  • Computer vision and natural language processing in education
  • Human-centered analytics and human-in-the-loop approaches in educational AI
• Ethics, Privacy, and Governance
  • Security, privacy, inclusivity, fairness, and ethics in AI-powered education
  • Bias detection and mitigation in educational algorithms
  • Data governance and responsible AI practices in learning analytics
• Applications and Emerging Trends
  • Data-informed instructional design and curriculum development
  • AI-enhanced assessment and credentialing
  • Educational data literacy
  • human-AI collaboration in teaching and learning
  • Sentiment, emotion and affective state detection and analysis
  • Collaborative and/or adaptive learning platforms
  • Analytics for academic administration and strategic planning
  • Institutional effectiveness and productivity analysis
• Research Methods and Standards
  • Emerging standards and interoperability in learning analytics
  • AI-based techniques for analyzing unstructured and semi-structured educational data
  • Research methods for big data and learning analytics

Track Program Committee