The 7th International Conference on Learning Analytics & Knowledge

Understanding, Informing and Improving Learning with Data

13-17 March 2017, Simon Fraser University,

Vancouver, BC, Canada

Main Submission Deadline: 17 October 2016

Poster / Tech Showcase Deadline: 2 December 2016

The 7th International Conference on Learning Analytics and Knowledge (LAK17) returns to the coastal city of Vancouver, BC, Canada from March 13-17, 2017. The LAK17 conference is organized by the Society for Learning Analytics Research (SOLAR) and will be hosted by Simon Fraser University (SFU), Canada’s leading community-engaged research university. Consolidating the experience from previous LAK conferences, we extend invitations to researchers, practitioners, administrators, government and industry professionals interested in the field of learning analytics and related disciplines. This annual conference provides a forum to address critical issues and challenges confronting the education sector today.  The success of LAK arises from its transdisciplinary nature which creates a unique intersection of cutting-edge learning technologies, educational research and practice, and data science.

Learning Analytics is defined more by its goals to better understand and improve learning processes using data than by a particular theory or methods. The challenges facing learning analytics require collaborations among a broad range of disciplinary experts to create holistic solutions generated from differing perspectives and approaches. This year LAK17 aims to bring more discussion and focus to these transdisciplinary efforts.


LAK17 welcomes contributions from researchers and practitioners in the field of Learning Analytics. The conference invites the following type of submissions:

Research Track

  • Full papers
  • Short papers
  • Posters (Printed or Powered)

Practitioner Track

  • Presentations
  • Technology Showcase

Workshops and Tutorials

In addition, LAK’17 will host a Doctoral Consortium (details to be announced soon).

See the guidelines on the website for more detailed information about the required content and format of each submission.


Research Papers (Full and Short) &  Practitioner Presentations

  • 17 October 2016: Deadline for submissions.  (extensions will not be considered)
  • 5 December 2016: Notification of acceptance.
  • 9 January 2017: Camera-ready version.

Research Posters (Printed and Powered) & Practitioner Technology Showcase

  • 2 December 2016: Deadline for submissions.  (extensions will not be considered)
  • 15 December 2016: Notification of acceptance.
  • 9 January 2017: Camera-ready version of poster description.

Workshops and Tutorials

  • 17 October 2016: Deadline for submissions.  (extensions will not be considered)
  • 7 November 2016: Notification of acceptance.
  • 9 January 2017: Camera-ready version of workshop or tutorial summary.


LAK17 seeks contributions focusing on understanding and improving learning through analyses of data traces generated during the learning process.  A special invitation is made for papers that cross disciplinary boundaries to provide highly innovative technological solutions grounded in learning theory.  Papers are welcome from any education context and setting: formal and informal learning; workplace, K-12 and tertiary education; online, distance, blended, mobile and traditional modes of learning.

The following categories represent the objectives of Learning Analytics research and practice and will be used to classify submissions:


  • Feature Finding: Studies that identify and explain useful data features for analyzing understanding and optimizing learning.
    Learning Metrics: Studies that assess the learning progress through the computation and analysis of learner actions or artefacts.
  • Data Storage and Sharing: Proposals of technical and methodological procedures to store, share and preserve learning traces.


  • Data-Informed Learning Theories: Proposal of new learning theories or revisions / reinterpretations of existing theories based on large-scale data analysis.
  • Insights into Particular Learning Processes: Studies to understand particular aspects of a learning process based on data analysis. Examples are inquiries that analyse traces of students’ cognition, metacognition, affect or motivation using various forms of data.
  • Modelling: Creating mathematical, statistical or computational models of a learning process, including its actors and context.


  • Feedback and Decision-Support Systems: Studies that evaluate the impact of feedback or decision-support systems based on learning analytics (dashboards, early-alert systems, automated messages, etc.).
  • Data-Informed Efforts:  Empirical evidence about the effectiveness of learning analytics implementations or educational initiatives guided by learning analytics.
  • Personalized and Adaptive Learning: Studies that evaluate the effectiveness and impact of (semi) automatic adaptive technologies based on learning analytics.


  • Ethics and Law: Exploration of issues and approaches to the lawful and ethical capture and use of educational data traces and the application of learning analytics tools and implementations
  • Adoption: Discussion and evaluation of strategies to adopt learning analytics initiatives in educational institutions
  • Scalability: Discussion and evaluation of strategies to scale the capture and analysis of information at the program, institution or national level


General Chairs

  • Alyssa Wise, Canada
  • Phil Winne, Canada
  • Grace Lynch, Australia

Program Chairs

  • Xavier Ochoa, Ecuador
  • Inge Molenaar, The Netherlands
  • Shane Dawson (ex officio), Australia

For more information please refer to the LAK’17 website at