The Technology for Effective and Efficient Learning (TEEL) Lab at Carnegie Mellon University focuses on research in learning methods, technology for learning systems, curriculum development, and workforce training.

About TEELLab


The Technology for Effective and Efficient Learning (TEEL) Lab at Carnegie Mellon University focuses on research in learning methods, technology for learning systems, curriculum development, and workforce training. The ultimate goal is to forge a path for lifelong learning and career ever-readiness through innovative bridging of learning between formal education, informal education, and the workplace.

The TEEL Lab develops learning platforms that support learning through discussion and collaboration, focusing on hands-on technology areas such as cloud computing, machine learning, and data science. The target interoperable online learning ecosystem under development by the team is designed to enable effective and efficient learning through iterative and interactive learning coupled with contextualized and timely feedback, and by leveraging social interactions between students as a substantial learning resource.

The lab conducts research studies on student learning and evaluates innovative approaches for incorporating social and interactive learning as a driver for developing cognitive and meta-cognitive skills and motivation. Its work is based on research spanning more than a decade in Computer Science Education, Software Engineering, Learning Sciences, and Language Technologies.

In addition to scientific findings, technical advances, and principles for instructional design, the team’s past research has also produced open source resources to share with the broader community. Specific features of the in-progress LMS-pluggable online course infrastructure is that it enables project-based learning through auto-graded projects that provide contextualized feedback. We also incorporate social learning in the form of project reflection and feedback cycles after each project, timed and role-based online learning exercises and rubric-driven peer code-review.

Members of the TEEL Lab collaborate with other groups at CMU, other universities, community colleges as well as industry. Find out how you can get involved from our Call for Participation.

Funded in part by a grant from Microsoft and grants NSF grants ACI-1443068, IIS 1822831 and IIS 1546393.


Foundational Research

  1. Foster, D., Laurie W., Joshua A., Cenk Erdil, D., Hyman, H., Kurkovsky, S., Sakr, M., and Stott, L. (2018).  Cloud computing: developing contemporary computer science curriculum for a cloud-first future. In Proceedings Companion of the 23rd Annual ACM Conference on Innovation and Technology in Computer Science Education, pp. 130-147. ACM, 2018.
  2. Sankaranarayanan, S., Dashti, C., Bogart, C., Wang, X., Marshall An, Clarence Ngoh, Michael Hilton, Sakr, M., Rosé, C. (2019). Transactivity-Based Team-Formation as a Choice: Evaluation in a Large Online Project Course. Proceedings of Collective Intelligence
  3. Sankaranarayanan, S., Dashti, C., Bogart, C., Wang, X., Marshall An, Clarence Ngoh, Michael Hilton, Sakr, M., Rosé, C. (2019). An Intelligent-Agent Facilitated Scaffold for Fostering Reflection in a Team-Based Project Course, Proceedings of AI in Education (short paper)
  4. Sankaranarayanan, S., Dashti, C., Bogart, C., Wang, X., Marshall An, Clarence Ngoh, Michael Hilton, Sakr, M., Rosé, C. (2019). Online Mob Programming: Bridging the 21st Century Workplace and the Classroom, Proceedings of Computer-Supported Collaborative Learning
  5. Fiacco, J. & Rosé, C. P. (2018). Towards Domain General Detection of Transactive Knowledge Building Behavior, in Proceedings of Learning at Scale.
  6. Wen, M., Maki, K., Dow, S. P., Herbsleb, J., Rosé, C. P. (2018). Supporting Virtual Team Formation through Community-Wide Deliberation, in Proceedings of the 21st ACM Conference on Computer-Supported Cooperative Work and Social Computing
  7. Rosé, C. P. (2017).  Expediting the cycle of data to intervention, Learning: Research and Practice 3(1), special issue on Learning Analytics, pp 59-62
  8. Rosé, C. P. & Ferschke, O. (2016).  Technology Support for Discussion Based Learning: From Computer Supported Collaborative Learning to the Future of Massive Open Online Courses, International Journal of AI in Education, 25th Anniversary Edition, volume 26(2), pp 660-678
  9. Howley, I. & Rosé, C. P. (2016).  Towards Careful Practices for Automated Linguistic
  10. Analysis of Group Learning, Journal of Learning Analytics 3(3), pp 239-262.
  11. Wang, X., Wen, M., Rosé, C. P. (2017).  Contrasting Explicit and Implicit Support for Transactive Exchange in Team Oriented Project Based Learning, Proceedings of Computer-Supported Collaborative Learning
  12. Tomar, G., Sankaranaranayan, S., Wang, X., Rosé, C. P. (2016).  Coordinating Collaborative Chat in Massive Open Online Courses, in Proceedings of the International Conference of the Learning Sciences
  13. Nguyen, A. T., Hilton, M., Codoban, M., Nguyen, H. A., Mast, L., Rademacher, E., ... & Dig, D. (2016, November). API code recommendation using statistical learning from fine-grained changes. In Proceedings of the 2016 24th ACM SIGSOFT International Symposium on Foundations of Software Engineering (pp. 511-522). ACM.
  14. Rehman, S., Boles, J., Hammoud, M. and Sakr, M. (2015). A Cloud Computing Course: From Systems To Services, Proceedings of the 46th ACM Special Interest Group on Computer Science Education Conference (SIGCSE 2015), Kansas City, USA, March 2015.
  15. damson, D., Dyke, G., Jang, H. J., Rosé, C. P. (2014). Towards an Agile Approach to Adapting Dynamic Collaboration Support to Student Needs, International Journal of AI in Education 24(1), pp91-121.
  16. 15. Kumar, R. & Rosé, C. P. (2014). Triggering Effective Social Support for Online Groups. ACM Transactions on Interactive Intelligent Systems 3 (4).
  17. Dyke, G., Adamson, A., Howley, I., & Rosé, C. P. (2013). Enhancing Scientific Reasoning and Discussion with Conversational Agents, IEEE Transactions on Learning Technologies 6(3), special issue on Science Teaching, pp 240-247.
  18. Kumar, R. & Rosé, C. P. (2011).  Architecture for building Conversational Agents that support Collaborative Learning, IEEE Transactions on Learning Technologies, 4(1), pp 21-34

Leadership Team

Teaching Professor, Computer Science Department

View Website

Majd Sakr

Project Lead

Assistant Teaching Professor, Institute for Software Research

View Website

Michael Hilton


Professor, Language Technologies Institute and Human-Computer Interaction Institute

View Website

Carolyn Rosé


Associate Professor, Computer Science Department

View Website

Seth Goldstein


Project Members

Systems Scientist, Institute for Software Research

View Website

Chris Bogart

Project Scientist, Computer Science Department Research

View Website

Marshall An

PhD student, Language Technologies Institute

View Website

Sreecharan Sankaranarayanan

Project Scientist, Computer Science Department

View Website

Siddharth Kandimalla

Senior Systems/Software Engineer, Computer Science Department

View Website

Aaron Madved

Master's Student, Carnegie Mellon University

View Website

Eric Song



DiscourseDB is an NSF funded data infrastructure project designed to bridge data sources from multiple platforms for hosting those learning experiences. Our vision is to provide a common data model designed to accommodate data from diverse sources including but not limited to Chat, Threaded Discussions, Blogs, Twitter, Wikis, and Text messaging. We will make available analytics components related to constructs including role taking, help exchange, collaborative knowledge construction, showing openness, taking an authoritative stance, attitudes, confusion, alliance and opposition. In enabling application of such metrics across datasets from multiple platforms, research questions related to the mediating and moderating effect of these process and state measures on information transfer, learning, and attrition can be conducted, building on the earlier research of our team.


Bazaar is a publicly available architecture for orchestrating conversational agent-based support for group learning. It is a powerful tool for facilitating research in collaborative learning. It hosts a library of reusable behavioral components that each trigger a simple form of support. More complex supportive interventions are constructed by orchestrating multiple simple behaviors. Its flexibility and simplicity mean it can be used to very rapidly develop platforms for investigating a wide range of important questions within the design space of dynamic support for collaborative learning.


The open-source LightSide platform, including the machine-learning and feature-extraction core as well as the researcher's workbench UI, has been and continues to be funded in part through Carnegie Mellon University, in particular by grants from the National Science Foundation and the Office of Naval Research. See the full acknowledgments and grant details below! We make the LightSide research platform freely available for research and education. In exchange, we ask that you provide us with basic information about who you are and how you're making use of LightSide's capabilities.

Social Recommendation

Massive Open Online Courses have experienced a recent boom in interest. Problems students struggle with in the discussion forums, such as difficulty in finding interesting discussion opportunities or attracting helpers to address posted problems, provide new opportunities for recommender systems. We developed a social recommendation technology to support help seekers in MOOC discussion forums implemented using a context-aware Matrix Factorization model to predict students' preferences for answering a given question. This recommendation framework allows for this two-way recommendation. .



The TEEL Lab at Carnegie Mellon University is excited to issue a call for collaboration on the development and deployment of our SAIL Platform and Curriculum. We plan to collaborate with faculty at community colleges on offering a variety of hands-on project-based courses as part of community college course offerings. We focus on curricula, developed by domain experts, that are targeted to the needs of a variety of learners to prepare them for jobs in the domains of cloud computing, machine learning, and data science, with the goal of helping meet the expected job growth in these fields. We prepare learners for these domains by developing foundational skills and providing opportunities to exercise industry’s best practices. This collaboration is meant to influence both the curricular content and its delivery while leveraging the expertise of faculty at community colleges in order to best meet the needs of our target learners in terms of career preparedness and the ability to cope with life-challenges that impact the learners’ ability to engage in a sustained upskilling effort. Mentorship and professional development in the domain will be made available to collaborating faculty.

Our SAIL platform offers content and scaffolded activities within the Open Learning Initiative (OLI) that integrate with Learning Management Systems that are already in use at community colleges. The design builds on an empirical foundation and software infrastructure emerging from our experience of offering online and hands-on project-based courses since 2013 to Carnegie Mellon's global campuses. Our platform offers learn-by-doing projects with scaffolding and opportunities to iterate by using auto-graded projects that provide timely and contextualized feedback. We incorporate social learning reflection and feedback cycles for each project, timed and role-based online group learning exercises and rubric-driven peer code-review opportunities. All of these are industry-standard job-relevant activities further reinforce the connection between the course content and software engineering best practices.

The TEEL Lab hopes to partner with community colleges to collaboratively adapt our existing curricular content to create new offerings or augment existing classes within the community college context. The SAIL Platform and collaboration is an effort to evaluate the efficacy of our innovative learning methods. We also are interested in research endeavors to investigate how to incorporate upskilling as part of a learner's current job.

Call to action:

  • Inform us of your interest in this collaboration
  • Identify existing programs that our initial cloud computing course offering fits within
  • Supply a list of faculty who would be interested in participating in this collaboration
  • Work through the IRB process to enable research towards continual improvement of the platform from student data



Get in touch