Track 7. Big Data in Education and Learning Analytics (BDELA@ICALT2016)

Track Chairs

Ching Sing Chai, National Institute of Education, Singapore
Hsin-Yi Chang, National Taiwan University of Science and Technology, Taiwan
Jovanovic Jelena Jovanovic, University of Belgrade, Serbia
Kumar Vive Kumar, Athabasca University, Canada [Coordinator -]
Mazza Riccardo Mazza, University of Lugano, Switzerland
Pardo Abelardo Pardo, University of Sydney, Australia

Track Program Committee

  • Alejandra Martínez, University of Valladolid, Spain
  • Alfred Essa, McGraw-Hill Education, USA
  • Amal Zouaq, Royal Military College of Canada, Canada
  • Anastasios Economides, University of Macedonia, Greece
  • Ben Daniel, University of Otago, New Zealand
  • Christos Doulkeridis, University of Piraeus, Greece
  • Dragan Gasevic, University of Edinburgh, UK
  • James Willis, Indiana University, USA
  • Lanqin Zheng, Beijing Normal University, China
  • Michael Derntl, RWTH Aachen University, Germany
  • Mimi Recker, Utah State University, USA
  • Sabine Graf, Athabasca University, Canada
  • Shane Dawson, University of South Australia
  • Stefan Dietze, L3S Research Center, Germany
  • Vanda Luengo, University Joseph Fourier, France

Track Description and Topics of Interest

The analysis and discovery of relations characterising human learning, and contextual factors that influence these relations have been one of the contemporary and critical global challenges faced by researchers in a number of areas, particularly in Education, Psychology, Sociology, Information Systems, and Computing. These relations typically concern learners’ achievements and the overall learning experience, and the effectiveness of the learning context. Be it the assessment marks distribution in a classroom context or the mined pattern of best practices in an apprenticeship context, analysis and discovery have always addressed the elusive causal question about the need to best serve learners’ learning efficiency, learning effectiveness, as well as the overall learning experience, and the need to make informed choices on a learning context’s instructional effectiveness.

Significant advances have been made in a number of areas from educational psychology to artificial intelligence in education, which explored factors contributing to learners’ proactive role in the learning process and instructional effectiveness. With the advent of new technologies such as eye-tracking, activities monitoring, video analysis, content analysis, sentiment analysis, social network analysis and interaction analysis, one could study these factors in a data-intensive fashion. This very notion is what is currently being explored at the intersection of big data and learning analytics, which includes related areas such as learning process analytics, institutional effectiveness, academic analytics, web analytics and information visualisation.

BDELA@ICALT2016 will explore continuous monitoring of learner progress and traces of skills development of individual learners as well as learning groups, both within and across programs and institutions. It will discuss issues concerning continuous evaluation of achievements resulting from institutional educational practices to gauge alignment with strategic plans and alignment of governmental strategies. It will examine assessment frameworks of academic productivity to continuously measure impact of teaching. It will discuss concerns such as quality of instruction, attrition, and measurement of curricular outcomes using big data and associated methods and techniques as the premise.

Big data theory, science and technology for education and learning

  • analysis of unstructured and semi-structured data
  • security, privacy and ethics of big data analytics
  • veracity in big data
  • scalability of machine learning and data mining algorithms for big data
  • computing infrastructure for big data – cloud, grid, autonomic, stream, mobile, high performance computing
  • search in big data
  • artificial intelligence in big data analytics
  • uncertainty handling in big data

Applications of big data in education and learning analytics

  • detecting student’s approach to learning
  • analytics in academic administration
  • data analytics in complex training
  • gaming analytics and sports analytics
  • evidence-driven instruction in inter and individual disciplines
  • big data and educational technology
  • analytics in academic strategic planning
  • cultural analytics
  • large-scale social networks

Techniques of big data in education, knowledge and learning analytics

  • evidence-driven mixed-initiative learning
  • data-intensive learning and instructional design
  • emerging standards in learning analytics
  • sentiment analysis
  • large-scale productivity analysis
  • big data infrastructure for academic institutions and SMEs
  • scalable knowledge management


Important dates about ICALT 2017 submissions can be found here.

The ICALT 2017 Author Guidelines can be found here.

The Track 7 CfP can be downloaded from here:

  • .txt version
  • .doc version