Publications

Preprints

• Learning About AI to Learn About Learning: Artificial Intelligence as a Tool for Metacognitive Reflection
  Santiago Ojeda-Ramirez*, Sina Rismanchian*, Shayan Doroudi
  *Joint First Authors
  
  

Journal Papers:

• On the Paradigms of Learning Analytics: Machine Learning Meets Epistemology
  Shayan Doroudi
  Computers and Education: Artificial Intelligence (2024)
  
  

• What Happened to the Interdisciplinary Study of Learning in Humans and Machines?
  Shayan Doroudi
  Journal of the Learning Sciences (2023)
  
  

• The Forgotten African American Innovators of Educational Technology: Stories of Education, Technology, and Civil Rights
  Shayan Doroudi
  Learning, Media and Technology (2023)
  
  

• The Bias-Variance Tradeoff in Cognitive Science
  Shayan Doroudi, Seyed Ali Rastegar
  Cognitive Science (2023)
  
  

• What is a Related Work? A Typology of Relationships in Research Literature
  Shayan Doroudi
  Synthese (2023)
  
  

• The Intertwined Histories of Artificial Intelligence and Education
  Shayan Doroudi
  International Journal of Artificial Intelligence in Education (2022)
  
  

• Three Algorithms for Grouping Students: A Bridge Between Personalized Tutoring System Data and Classroom Pedagogy
  Christopher G. Lechuga, Shayan Doroudi
  International Journal of Artificial Intelligence in Education (2022)
  
  

• The Bias-Variance Tradeoff: How Data Science Can Inform Educational Debates
  Shayan Doroudi
  AERA Open (2020)
  Also presented at Conference on Educational Data Science 2020, Best Paper
  
  

• Where’s the Reward? A Review of Reinforcement Learning for Instructional Sequencing
  Shayan Doroudi, Vincent Aleven, Emma Brunskill
  International Journal of Artificial Intelligence in Education (2019)
  [Publisher’s Version] [Author’s Version]

Conference Papers:

• The Relevance of Ivan Illich’s Learning Webs 50 Years On
  Shayan Doroudi, Yusuf Ahmad
  In Proceedings of Learning & Scale (L@S) 2023
  
  

• Four Interactions Between AI and Education: Broadening Our Perspective on What AI Can Offer Education
  Sina Rismanchian, Shayan Doroudi
  In Proceedings of Artificial Intelligence in Education (AIED) 2023 — Blue Sky Track
  
  

• A Computational Model for the ICAP Framework: Exploring Agent-Based Modeling as an AIED Methodology
  Sina Rismanchian, Shayan Doroudi
  In Proceedings of Artificial Intelligence in Education (AIED) 2023
  
  

• Learnersourcing in Theory and Practice: Synthesizing the Literature and Charting the Future
  Anjali  Singh,  Christopher Brooks, Shayan Doroudi
  In Proceedings of Learning @ Scale  (L@S) 2022
  
  

• Towards Accurate and Fair Prediction of College Success: Evaluating Different Sources of Student Data
  Renzhe Yu, Qiujie Li, Christian Fischer, Shayan Doroudi, Di Xu
  In Proceedings of Educational Data Mining (EDM) 2020.
  
  

• Mastery Learning Heuristics and Their Hidden Models
  Shayan Doroudi
  In Proceedings of Artificial Intelligence in Education (AIED) 2020.
  [Supplementary Material]
  
  

• Probing Learning Scientists' Beliefs About Learning and Science
  Shayan Doroudi*, Kenneth Holstein*, Petr Johanes*
  In Proceedings of International Conference on the Learning Sciences (ICLS) 2020.
  *Joint First Authors
  
  

• Not Everyone Writes Good Examples But Good Examples Can Come From Anywhere
  Shayan Doroudi, Ece Kamar, Emma Brunskill
  In Proceedings of the AAAI Conference on Human Computation and Crowdsourcing (HCOMP) 2019.
  
  

• Fairer but Not Fair Enough: On the Equitability of Knowledge Tracing
  Shayan Doroudi, Emma Brunskill
  In Proceedings of Learning Analytics & Knowledge (LAK) 2019.
  
  

• Importance Sampling for Fair Policy Selection
  Shayan Doroudi, Philip S. Thomas, Emma Brunskill
  In Proceedings of Uncertainty in Artificial Intelligence (UAI) 2017.
  Best Paper
  Also see our shortened version of this paper presented at IJCAI 2018’s Sister Conference Best Paper Track.
  
  

• The Misidentified Identifiability Problem of Bayesian Knowledge Tracing
  Shayan Doroudi, Emma Brunskill
  In Proceedings of Educational Data Mining (EDM) 2017.
  Nominated for Best Paper
  
  

• Robust Evaluation Matrix: Towards a More Principled Offline Exploration of Instructional Policies
  Shayan Doroudi, Vincent Aleven, Emma Brunskill
  In Proceedings of Learning @ Scale (L@S) 2017.
  
  

• Sequence Matters, But How Exactly? A Method for Evaluating Activity Sequences from Data
  Shayan Doroudi, Kenneth Holstein, Vincent Aleven, Emma Brunskill
  In Proceedings of Educational Data Mining (EDM) 2016.
  
  

• Toward a Learning Science for Complex Crowdsourcing Tasks
  Shayan Doroudi, Ece Kamar, Emma Brunskill, Eric Horvitz
  In Proceedings of Computer Human Interaction (CHI) 2016.
  [Supplementary Materials]
  
  

• A PAC RL Algorithm for Episodic POMDPs
  Zhaohan (Daniel) Guo, Shayan Doroudi, Emma Brunskill
  In Proceedings of Artificial Intelligence and Statistics (AISTATS) 2016.
  
  

• Towards Understanding How to Leverage Sense-making, Induction and Refinement, and Fluency to Improve Robust Learning
  Shayan Doroudi, Kenneth Holstein, Vincent Aleven, Emma Brunskill.
  In Proceedings of Educational Data Mining (EDM) 2015.
  Subject to errata due to some additional data cleaning. At a high level, the results should be the same.

Workshop Papers:

• Importance Sampling for Fair Policy Selection
  Shayan Doroudi, Philip S. Thomas, Emma Brunskill
  Reinforcement Learning and Decision Making (RLDM) 2017.
  Extended abstract consisting of a subset of the content in our UAI paper with the same name.

• Sequence Matters, But How Do I Discover How? A Method for Evaluating Activity Sequences from Data
  Shayan Doroudi, Kenneth Holstein, Vincent Aleven, Emma Brunskill
  In Proceedings of Workshops of Educational Data Mining (EDM) 2016. Describes a workflow for the method in our paper with a similar name.