Research Introduction
At the intersection of learning sciences, artificial intelligence, and data science, our lab explores how educational data can be used to better understand, support, and personalize human learning. Led by Brendan Flanagan, the lab conducts interdisciplinary research in Learning Analytics, AI in Education, Educational Data Science, and Human–AI Collaborative Learning.
Our mission is to design educational technologies that not only analyze learning behavior, but also actively support learners and educators through meaningful, explainable, and human-centered feedback. We believe that future learning environments should combine the strengths of human intelligence and artificial intelligence to create adaptive, reflective, and engaging educational experiences.
Research Vision
Digital learning environments continuously generate rich traces of learner activity, reading behavior, interaction logs, collaborative discussions, writing processes, problem-solving actions, and AI-assisted learning interactions. Our research investigates how these learning traces can be transformed into actionable insights that improve learning outcomes while respecting privacy, transparency, and learner agency.
The lab focuses on three central themes:
Learning Analytics and Educational Data Science
We investigate methods for collecting, modeling, and analyzing large-scale educational data to better understand learning processes. This includes:
- Behavioral analytics from e-learning systems
- Reading analytics and language learning analytics
- Learning progression modeling
- Self-regulated learning analysis
- Predictive and explainable educational AI
- Learning dashboards and feedback systems
- Cross-platform learning analytics infrastructure
Our work int he past has contributed to large-scale learning analytics platform development in education and research into privacy-aware educational data ecosystems.
Human-Centered AI in Education
As generative AI becomes increasingly integrated into education, our lab explores how AI systems can collaborate with learners in ways that are transparent, supportive, and pedagogically meaningful.
Our recent work investigates:
- Explainable AI for personalized learning
- Human–AI collaborative learning systems
- AI-supported reflection and self-explanation
- Learning impasse detection
- Adaptive feedback generation
- Ethical and trustworthy educational AI
This research aligns with broader efforts toward human-centered learning analytics and hybrid human–AI intelligence in education.
Learning Infrastructure and Open Educational Data
Educational innovation increasingly depends on scalable and interoperable learning infrastructures. Our lab studies how educational systems can securely share, integrate, and utilize learning data across institutions and contexts.
Research topics include:
- Learning analytics platforms
- Privacy-preserving analytics systems
- Synthetic educational data
- Open educational datasets
- Educational interoperability and standards
- Evidence-based educational ecosystems
Recent research has examined the challenges of collaborative learning analytics using synthetic educational data and best practices for open educational datasets.
Research Areas
Our current research projects span multiple domains, including:
- Learning Analytics (LA)
- Educational Data Mining (EDM)
- Artificial Intelligence in Education (AIED)
- Educational Natural Language Processing
- Reading and Language Learning Analytics
- Explainable AI (XAI) for Education
- Human–AI Interaction
- Self-Regulated Learning
- Educational Recommender Systems
- Learning Dashboards and Visualization
- Generative AI for Learning Support
- Educational Big Data Infrastructure
Representative Research Contributions
Research by Brendan Flanagan and collaborators has contributed to international work on:
- Learning analytics infrastructures for seamless learning
- National-scale higher education learning analytics platforms in Japan
- Explainable AI tools for personalized learning
- Learning dashboards supporting self-directed reading behavior
- Educational data science for reading systems
- Privacy-preserving learning analytics systems
- Synthetic educational data and collaborative analytics
- Learning progression and wheel-spinning analysis
- AI-supported impasse detection in mathematics learning
International Collaboration and Community Engagement
Our lab actively collaborates with researchers and institutions worldwide in the fields of Learning Analytics, Educational Data Science, and AI in Education. Members contribute to leading international conferences and communities, including:
- Learning Analytics & Knowledge (LAK)
- Artificial Intelligence in Education (AIED)
- Educational Data Mining (EDM)
- International Conference on Computers in Education (ICCE)
Brendan Flanagan also served as a Program Chair for the international LAK 2024 conference held in Kyoto.
Our Goal
Ultimately, our lab aims to build educational technologies that empower learners, support educators, and advance evidence-based education through responsible and human-centered use of AI and learning data.
We welcome students and collaborators interested in interdisciplinary research spanning education, artificial intelligence, data science, and human-centered computing.