Keynote Speeches







Peter Brusilovsky, University of Pittsburgh, USA

The return of Intelligent Textbooks




Early research on hypermedia learning and Web-based education featured a strong stream of work on intelligent and adaptive textbooks, which combined the knowledge modeling ideas from the field of intelligent tutoring with rich linking offered by the hypermedia and the Web. However, over the next ten years from 2005 to 2015 this area was relatively quiet as the focus of research in e-learning has shifted to other topics and other creative ideas to leverage the power of Internet. A recent gradual shift of the whole publication industry from printed books to electronic books followed by a rapid growth or the volume of online books re-ignited interests to  “more intelligent” textbooks. The research on the new generation of intelligent textbooks engaged a larger set of technologies and engaged scholars from a broader range of areas including machine learning, natural language understanding, social computing, etc. In my talk I will review the past and present of research on intelligent textbooks from its origins to the diverse modern work providing examples of most interesting technologies and research results.

Adina Magda Florea,University POLITEHNICA of Bucharest, Romania

Interpretability and Explanations in Intelligent Tutoring Systems




Since the first developments of ITSs, the capacity to understand and interpret student behavior while learning has been a key issue of the system. Interpreting the student model is important both for the teachers, making them able to evaluate the student progress, accumulated knowledge and week points, and for the students, in particular in the context of building open learner models, which allow the learner to view and understand information about himself/herself, thus better motivating and engaging the student. With the outburst of machine learning (ML) techniques, there is a strong interest in developing learner models based on different ML approaches. However, interpretability and explainability of such models are most of the time a challenge. The talk presents the recent advances in using machine learning methods to develop student models and analyses the extent to which these models can be interpreted and explained to both teachers and students. It compares these methods to the “traditional” knowledge-based approaches and explore the challenges of making ML an effective tool for delivering personalized learning experiences.

Spyros Vosinakis, University of the Aegean, Greece


Extended Reality Technologies in Education: Moving beyond the “Wow” factor



Virtual Reality (VR) has always been considered a medium with great potential for education, from the early days of expensive high-end immersive systems, through the era of massive multiuser virtual worlds, until the recent widespread releases of consumer headsets. Yet, despite the popularity and the strong research and commercial interest in these technologies, today their use as learning environments still not a commonplace. Mixed and Augmented reality are equally promising solutions that go beyond the ‘isolating’ nature of VR by effectively integrating digital content with the real world. As such, they bring new affordances for learning through the enhancement of real-world places and artifacts with learning content and activities. Again, their adoption in education is not as widespread as expected. So, although many researchers agree that extended reality technologies (XR – virtual, mixed or augmented reality) have the potential to deliver rich learning experiences, there seem to be several factors that hold them back. This talk introduces the main technological approaches and trends in XR and describes their affordances and limitations. It presents an overview of their usage in education and identifies good practices and paradigms. Additionally, it outlines our hands-on experience from the development and evaluation of a series of projects in the area of learning using XR technologies, focusing on critical observations, noteworthy results and usability issues. The talk concludes with a discussion on the prospects and pitfalls of XR as an educational tool and directions for future research that might further exploit their potential.


Amruth Kumar, University at Buffalo, USA

15 Years of Developing, Evaluating and Disseminating Programming Tutors: Lessons Learned

The past can inform the future when it comes to pushing the boundaries of ITS. Based on the experience of developing, evaluating and disseminating two suites of software tutors for computer programming, viz., problets and epplets, I would like to proffer some lessons learned. Among those are: How correct is a pragmatic alternative to why incorrect; Learning gains are not always commensurate with development costs; An ounce of direction is worth a pound of correction; Can do is not the same as should do; Solving ill-defined problems is about knowing what to ask and when; Mastery learning assessed in terms of effort rather than correctness; All that glitters in the laboratory may not be gold in the field; One size does not fit all; The path of least resistance can waylay the best of intentions; Learning is a whole person activity; When you are given lemons, make lemonade; Do it right and do it twice; If you build it, they will not come; and Dissemination is a Sisyphean task!



Stefano Cerri

For more information on his keynote speech click here – From individual rationality to crowd evolutionary wisdom

Ana Paiva

For more information on his keynote speech click here – Empathic Agents in Learning Environments



Colin Allison

For more information on his keynote speech click here – Open Virtual Worlds for Exploratory Learning

Maria Grigoriadou

For more information on his keynote speech click here – From learning theories to learning environments

Sheizaf Rafaeli

For more information on his keynote speech click here – Online games and Sharing in Learning

Norbert M. Seel

For more information on his keynote speech click here – The three learning Sciences (biological, artificial, human)