An AI-enabled Ecosystem for Learning & Assessment
Alina von Davier, ACT NEXT
AI-based tools, integrative technology and standards for various purposes in education have undergone significant development in the past few years. The vision is to build towards processes and/or parts thereof that are automatic and seamlessly integrated.
In this presentation I will illustrate the architecture of a fluid infrastructure to effectively support learning and assessment systems. Each component is designed within a computational framework (AI blended with psychometrics) and each connection relies on construct taxonomy, database alignment, data exchange standards, and APIs.
I will describe a key AI-based content generator, Sphinx, developed at ACTNext. I’ll use the ACTNext Educational Companion App as an example of how the pieces come together. Last but not least, I’ll show how voice-based interface can be integrated within the versatile systems. The work has been conducted with an interdisciplinary team at ACTNEXT.
Alina von Davier, PhD., is the Chief Officer at ACTNext, a multidisciplinary innovation unit that is part of ACT and was founded in 2016. Her team is comprised of experts in fields ranging from psychometrics and learning sciences to software development, and artificial intelligence (AI) & machine learning (ML). Von Davier and her team operate at the forefront of Computational Psychometrics, an emerging interdisciplinary field concerned with the application of theoretical and data-driven computational methods and statistical modeling of multimodal, large scale/high dimensional learning and assessment data. Prior to leading ACTNext, von Davier was a senior research director at Educational Testing Service (ETS) where she led the Computational Psychometrics Research Center. Previously, she led the Center for Psychometrics for International Tests, where she was responsible for both the psychometrics in support of international tests, TOEFL® and TOEIC®, and the scores reported to millions of test takers annually.
Von Davier is currently an adjunct professor at Fordham University and the president of the International Association of Computerized Adaptive Testing (IACAT). She currently serves on the board of directors for the Association of Test Publishers (ATP), and she is also a member of the board of directors for Smart Sparrow and of the advisory board for Duolingo.
Contextualising Data Mining within Educational Experiences
Abelardo Pardo, University of South Australia
The use of technology to mediate learning experiences provides an unprecedented amount of information that can be used to increase our understanding and improve the overall quality of those experiences. However, learning in general is strongly mediated by a very rich set of contextual factors. The two crucial steps to translate data into knowledge, sensemaking and deriving actions, are especially sensitive to these factors, and as such, need to be carefully considered to maximise positive outcomes. Areas such as personalisation are highly sensitive to the context in which each learner is engaged in an experience. Data-intensive techniques need to factor in these elements and assure learners are not adversely affected by situations ignored or inadequately handled by algorithms. This talk aims to explore how data mining applications can be properly situated to have a positive impact in specific aspects such as learning outcomes or connecting insights derived from data analysis with actions.Bio:
Abelardo Pardo is Professor and Dean of Programs (Engineering), at UniSA STEM, University of South Australia. His research interests include the design and deployment of technology to increase the understanding and improve digital learning experiences. More specifically, his work examines the areas of learning analytics, personalized active learning, and technology for student support.
He is the author of over 150 research papers in scholarly journals and international conferences in the area of educational technology and engineering education. He is currently member of the executive board and president of the Society for Learning Analytics Research (SoLAR).
Online Collaborative Student Group Learning
Kobi Gal, Ben-Gurion University of the Negev, and University of Edinburgh.
Collaborative student learning has been shown to lead to significant academic benefits among students, and to improved social skills that are critical for the workforce, such as communication and teamwork. However, these benefits were limited to small face-to-face groups and required the support of human experts who actively monitored and guided the group’s learning.
Technological advances now enable globally dispersed teams to collaborate online, from Q&A forums to virtual laboratories. Augmenting these settings with AI technology can scale up the benefits of collaborative group learning to online groups.
I will describe challenges to EDM research for supporting this new type of online teamwork, as well as opportunities for combining AI and learning analytics towards supporting students’ learning and teachers’ understanding of how students learn.Bio:
Kobi Gal is an Associate Professor at the Department of Software and Information Systems Engineering at Ben-Gurion University of the Negev, and Reader at the School of Informatics at the University of Edinburgh. Gal’s work combines artificial intelligence algorithms with educational technology towards supporting students in their learning and teachers in their understanding how students learn. He has published widely in highly refereed venues on topics ranging from artificial intelligence to the learning and cognitive sciences.
Gal is the recipient of the Wolf foundation’s 2013 Krill prize for young Israeli scientists, a Marie Curie International fellowship, and a three-time recipient of Harvard University’s outstanding teacher award. He has received best paper awards at ACM Conference on User Modeling Adaptation and Personalization 2019 (UMAP-19), ACM conference on Economics and Computation 2016 (EC-16), Educational Data Mining 2014 (EDM-14). Gal is the acting president of the Israeli Association for Artificial Intelligence.