The LILE2016 papers are published with ACM as part of the WWW2016 Companion Proceedings.


  • 09:00 – 09:15 Gathering & Welcome
  • 09:15 – 10:30 Keynote: “On the analysis of student trace data” by Michel Desmarais
  • 10:30 – 11:00 Coffee
  • 11:00 – 12:30 Paper Session 1
    • “Competency Based Learning in the Web of Learning Data” – Guillaume Durand (National Research Council Canada), Nabil Belacel  (National Research Council Canada),  Cyril Goutte (National Research Council Canada)
      slides ]
    • “Towards embedded markup of Learning Resources on the Web: a quantitative analysis of the use of LRMI properties” – Davide Taibi (Italian National Research Council), Stefan Dietze (L3S Research Center)
      [ slides ]
    • “Metadata Extraction from Open edX Online Courses Using Dynamic Mapping of NoSQL Queries” – Dmitry Mouromtsev (ITMO University), Aleksei Romanov (ITMO University), Dmitry Volchek (ITMO University), Fedor Kozlov ( ITMO University)
      [ slides ]
  • 12:30 – 14:00 Lunch
  • 14:00 – 15:10 Keynote: “Mining User Behaviors for Modeling Learners in Interactive Simulations” by Cristina Conati
  • 15:10 – 15:30 Short Paper presentation
    • “Prerequisite Concept Maps Extraction for Automatic Assessment” – Shuting Wang (Pennsylvania State University), Lei Liu (HP Labs)
      [ slides ]
  • 15:30 – 16:00 Coffee
  • 16:00 – 17:30 Paper Session 2
    • “Linking Online Identities and Content in Connectivist MOOCs across Multiple Social Media Platforms” – Rafa Absar (Clarkson University),  Anatoliy Gruzd (Ryerson University), Caroline Haythornthwaite (University of British Columbia), Drew Paulin (University of British Columbia)
    • “Workload Study of a Media-Rich Educational Web Site” – Yang Liu (Department of Computer Science, University of Calgary), Carey Williamson (Department of Computer Science, University of Calgary)
      [ slides ]
    • “Correlational analysis between school performance and municipal indicators in Brazil supported by linked open data” – Bruno E. Penteado (University of São Paulo)
  • 17:30 Wrap-up & best-paper award
  • from 19:30 Workshop dinner


Keynote by Michel Desmarais

  • Michel Desmarais is a professor at the Computer and Software Engineering Department of Ecole Polytechnique de Montreal since 2002.  His field of expertise is in the domains of Intelligent learning environments and the analysis of user trace data.  He has 15 years of experience in software project management.  He was principal researcher of the Human-Computer Interaction and Computerized Learning Environments groups at the Computer Research Institute of Montreal between 1990 and 1998, where he directed a research program in HCI and computer assisted learning, and was involved in a number of research projects in close collaboration with private corporations.  From 1998 to 2002, he was director of the Web services department in a private company ( and leader of a number of R&D Web-based software projects. He is the editor of Journal of Educational Data Mining and co-author of over 100 scientific publications.

  • Title: On the analysis of student trace data

  • Abstract: We live in an exiting era where two trends meet: the data gathered is diversifying and expanding at exponential rate, and new tools and techniques to analyze them are emerging at a rate unseen before. These trends means old problems can be tackled with new data and techniques, and new problems arise.  In this talk I will focus on three problems for learning environments.  They span the space of data and techniques on the old-new dimension.  The first problem is how to visualize at a glance what our learners do in the learning environments they interact with?  We can collect detailed interaction traces from these environments, but it remains a challenge to bring them in a shape that is useful and easy to interpret.  The second problem is also about a new type of data collected from a learning environment called DALITE.  DALITE is a novel type of peer-input learning environment that implements the Peer Instruction paradigm.  We need to analyze the peer-generated data to fully exploit the learning potential of such environment. Standard text analysis techniques to yield some interesting results but major challenges remain.  The final problem is pervasive and time-old: how to determine what are the skills behind a task?  We have recently made substantial progress towards this goal using synthetic data training and ensemble techniques, and will discuss the challenges that remain to apply these approaches to data that is more typical of learning environments.

Keynote by Cristina Conati

  • Title: Mining User Behaviors for Modeling Learners in Interactive Simulations

  • Abstract: The field of Intelligent Tutoring System has successfully delivered techniques and environments that provide adaptive coaching and feedback  for problem solving in variety of  domains. There are, however, ot
    her educational activities that can help learners acquire the target skills and abilities at different stages of learning including, among others, exploring interactive simulations.Like for problem solving, learners can benefit from having individualized pedagogical support during these activities, especially as they are bound to become increasingly important with the advent of on-line courses and self-directed instruction. However, providing real-time personalize support for interactive simulations rises unique challenges, because it requires modeling   and responding to student behaviors and skills often not as structured and well-defined as those involved in traditional problem solving. We have developed a user modeling framework that mines student interaction data to perform behavior discovery and user classification suitable for providing real-time support. In this talk. I will summarize results we obtained for modeling students interacting with two different types of simulations, including a formal evaluation showing that a simulation that embeds adaptive support based on this user modeling technique fosters learning better than its non-adaptive counterpart


The #LILE2016 best paper awards were kindly sponsored by The decision was made by a panel of experts consisting of the LILE2016 keynote speakers Cristina Conati and Michel Desmarais. The panel took into account paper quality, review scores and the presentations decided on a split best paper award jointly shared amoing the following two submissions:

  • “Prerequisite Concept Maps Extraction for Automatic Assessment” – Shuting Wang (Pennsylvania State University), Lei Liu (HP Labs)
  • “Towards embedded markup of Learning Resources on the Web: a quantitative analysis of the use of LRMI properties” – Davide Taibi (Italian National Research Council), Stefan Dietze (L3S Research Center)

As one of the LILE co-organisers has been among the co-authors of the second selected submission, the authors will donate the respective share of the award to a charity, namely the education program of the UNHCR (United Nations Refugee Agency) which is part of the Educate A Child initiative.