Full-day Workshop as part of the 2026 International Learning Analytics & Knowledge Conference
April 27, 2026, 9am-5pm CET at the Radisson Blu Royal Hotel, Bergen, Norway
Tutoring is one of the most consistently effective educational interventions, with high-dosage models showing especially strong results. Yet the field still lacks a systematic understanding of why tutoring works—particularly which instructional moves drive learning. The emerging area of “teacher move analytics” addresses this gap by analyzing discourse, feedback, and interaction patterns. Advances in NLP, multimodal analytics, and AI-assisted annotation make large-scale analysis possible, but progress is hindered by fragmented data, high annotation costs, and privacy concerns.
The National Tutoring Observatory (NTO) offers a unifying infrastructure to overcome these barriers—enabling systematic analysis of tutoring, predictive and causal models of effectiveness, and the design of human–AI tutoring systems. By convening the LAK community, this workshop will help advance a shared agenda for uncovering the instructional moves that make tutoring and teaching instruction effective.
Date and time:
April 27, 2026, 9 am - 5 pm (Central European Time)
Location:
Dræggen 4b, Radisson Blu Royal Hotel, Dreggsallmenningen 1, 5003 Bergen, Norway
We will demo a tool that allows for the annotation of tutoring and teaching dialog data using AI. Then attendies will work individually or in groups to annotate and analyze their own data sets or data provided by the NTO.
We encourage paper submissions related to:
Examples of Methods and Implementations of AI Annotation in Learning Analytics Contexts
Research on Understanding Teaching Behaviors and Practices in Authentic Learning Environments
https://easychair.org/conferences/?conf=lak26-nto-ai-annotat
This workshop will feature presentations of selected papers alongside guided discussion sessions. We invite submissions of up to six pages in length that align with the workshop’s central themes, following the formatting requirements outlined in the conference proceedings. All submissions will undergo a single-blind review process, where authors are identified but reviewers remain anonymous. Reviewers will assess each paper on three criteria—relevance to the workshop’s themes, level of interest to the LAK community, and overall scholarly quality—using a three-point scale (-1, 0, 1). Based on these evaluations, reviewers will recommend acceptance or rejection and justify their decisions. Authors of accepted papers will be asked to present their work during the workshop. The call for papers timeline and details will be released once the workshop has been formally accepted.
Submission Deadline: February 1, 2026 (papers will be reviewed on a rolling basis up until the deadline)
Final Acceptance Notifications: February 16, 2026
Camara-Ready: April 1, 2026 (optional)
Accepted papers and presentations will be disseminated on this website at the author's request.
The NTO is a first-of-its-kind research infrastructure that advances the science of teaching by capturing and analyzing tutoring interactions at scale. Its two core components are: (1) the Million Tutor Moves (MTM) repository, a large collection of multimodal tutoring data—transcripts, video, audio, and metadata—linked to student outcomes; and (2) open-source tools for securely de-identifying and annotating these data. Together, they enable researchers, practitioners, and developers to identify which instructional moves and interaction patterns most effectively drive learning.
The NTO partners with leading tutoring providers (Saga Education, UPChieve, Carnegie Learning, Third Space Learning, PLUS, Eedi), teacher feedback platforms like TeachFX, and infrastructures such as Databrary and LearnSphere. These collaborations pool diverse datasets and advance community standards for interoperability, annotation, and responsible sharing. By lowering barriers to fine-grained tutoring data, the NTO empowers the learning analytics community to explore new questions of instructional effectiveness. For LAK participants, it offers datasets, workflows, and a collaborative hub for advancing tutoring research.
Kirk Vanacore is the Research Director for the NTO and an Assistant Research Professor in the Bowers College of Computing and Information Science at Cornell University. His research blends statistics, machine learning, and artificial intelligence to uncover causal learning mechanisms in environments that combine human and AI instruction.
Email: kpv27@cornell.edu
Main Contact for this Workshop
Kizilcec is an Associate Professor in the Bowers College of Computing and Information Science at Cornell University, where he directs the Cornell Future of Learning Lab. He is a PI of the National Tutoring Observatory. Kizilcec studies behavioral, psychological, and computational aspects of technology in education to inform practices and policies that promote learning, equity, and academic and career success. Kizilcec has authored over 100 research papers, won numerous Best Paper awards, and received funding from the NSF, Schmidt Futures Foundation, Gates Foundation, Jacobs Foundation, Chan Zuckerberg Initiative, and Google.
Email: kizilcec@cornell.edu
Rachel is the Associate Director of the Future of Learning Lab in the Bowers College of Computing and Information Science at Cornell University. Slama’s research focuses on the role of technology in accelerating learning in the rapidly changing world of education and training. She also serves as a co-principal investigator and the partnerships director of the National Tutoring Observatory. Slama held previous roles leading workforce and training portfolios at RAND, MIT, and the National Science Foundation. Slama received her doctorate in Education Policy, Leadership, and Instructional Practice from Harvard University where she was an Ambach Fellow-- an opportunity designed to promote innovation in state education agencies. A former teacher in New York City and mother of four public school students, Slama is deeply committed to ensuring that technology is developed with—and for the educators and learners it aims to serve.
Email: rslama@cornell.edu
Josh is the Managing Director for the NTO. He has worked in a variety of education data and technology roles for almost 20 years. Josh is driven by finding new ways to create opportunities for those not served by traditional systems and has focused his research at the intersection of equitable measurement and policy. He earned a Master's degree from Brown University in Urban Education Policy and a Doctorate in Research, Educational Measurement, and Psychometrics from the University of Massachusetts Amherst. Josh is the first in his family to go to college and a proud community college graduate.
Email: jm2945@cornell.edu
Zhuqian Zhou is a postdoctoral researcher at the National Tutoring Observatory. Her work brings together data from diverse sources to deepen understanding of learners’ cognitive processes, guide the design of effective learning interventions, and address ethical considerations in artificial intelligence and education (AIEd) research. Beyond academia, she co-founded an EdTech company that supports high school students in exploring career pathways and serves as a board member of a nonprofit organization dedicated to supporting the Chinese community in the Greater New York area.
Email: zz968@cornell.edu
Bakhtawar Ahtisham is a Learning Analyst and Engineer at the National Tutoring Observatory. She holds a Master’s degree in Information Science from Cornell University and brings a multidisciplinary background in UX research, education technology, and AI-powered learning systems. Her work focuses on developing data-driven tools to support equitable, effective tutoring by combining qualitative research with scalable engineering solutions. At the NTO, Bakhtawar contributes to the design and analysis of open-source annotation systems and AI-driven insights that support researchers and practitioners in understanding tutoring practices at scale.
Email: ba453@cornell.edu
Danielle is a Systems Scientist at Carnegie Mellon University, the Research Lead on the PLUS tutoring project, and the Director of Research to Practice at the NTO. She is a former middle school teacher, instructional coach, and school administrator. Danielle wishes every child had their own human math tutor. Given that's not feasbile, she is striving to improve human-AI tutoring so that its not only impactful but cost-effective and scalable. In recent years, she has first-authored over a dozen papers in conferences, such as Artificial Intelligence in Education and International Learning Analytics and Knowledge.
Email: drthomas@cmu.edu
PLUS: http://tutors.plus
Ken is the Hillman professor of Computer Science and Psychology at Carnegie Mellon University and founder of PLUS tutoring. He is a co-founder of CarnegieLearning, Inc. that has brought Cognitive Tutor based courses to millions of students since it was formed in 1998, and leads LearnLab, the scientific arm of CMU's Simon Initiative. Through extensive research and development in human-AI tutoring, Ken has demonstrated a doubling of math learning among middle school students and aims to bring similar high-quality tutoring that is cost-effective to scale. He has authored over 300 research papers and over 60 grant proposals.
Email: koedinger@cmu.edu
PLUS: http://tutors.plus
Doug is the Technology Director of the NTO and the CEO of Freshcognate, an instructional design firm tackling the most challenging educational situations at scale. Doug is an educator at heart, as he was a former CPS English teacher focused on equity who combines his passion for technology and education to drive impactful teaching and learning experiences and products at scale. He is one of the original members of Lynda.com and EdX and was a major contributor to education at Google.
Email: doug@freshcognate.com
Justin is an associate professor of digital media in the Comparative Media Studies/Writing department at MIT and the director of the Teaching Systems Lab. He is the author of Iterate: The Secret to Innovation in Schools and Failure to Disrupt: Why Technology Alone Can’t Transform Education, and he is the host of the TeachLab Podcast. He earned his doctorate from the Harvard Graduate School of Education is a past Fellow at the Berkman-Klein Center for Internet and Society. His writings have been published in Science, Proceedings of the National Academy of Sciences, Washington Post, The Atlantic, and other scholarly venues. He started his career as a high school history teacher and wrestling coach.
Email: jreich@mit.edu
The International Conference on Learning Analytics & Knowledge Workshop
For questions about the LAK26 workshop, contact:
Danielle R. Thomas: drthomas@cmu.edu
Rene Kizilcec: kizilcec@cornell.edu