Research Projects 3/4

Research Projects

We engage in multidisciplinary, iterative, and evidence-based research and development with diverse stakeholders to create new technologies, activities, practices and programs for real-world impact in homes, schools, afterschool programs and online communities. A list of publications for these projects can be found here.

PopBots: Early AI Education

The PopBots Platform is a tool to introduce young children to programming, robotics, and artificial intelligence by allowing them to build and program their own robots.

AI & Data Privacy Activities

Data and privacy design activities developed for the Girl Scouts of Eastern MA.

Primary School AI for K-2nd Grade

Primary AI for K-2nd grade introduces early elementary school students to robotics and artificial intelligence.

Creativity with Scratch and AI

Scratch helps kids learn to think creatively, reason systematically, and collaborate.

Conversational AI with Zhorai

Zhorai is an artificially intelligence conversational agent through which children grades 3-5 can learn about AI.

BeaverWorks at MIT

A project-based summer STEM program for talented high school students.

GANPaint for Kids

Children can create artwork using GANPaint in Scratch and learn about GANs.

AI & Growth Mindset

We developed a novel cognitive-affective architecture that integrates models of curiosity, understanding of mindsets, and expressive social behaviors to advance the state-of the-art of robot companions.

Learning Literacy with Social Robots

This project, supported by a National Science Foundation (NSF) grant, is designed to develop new learning games focused on improving children’s vocabulary and early literacy skills.

Conversational AI Tools

MIT App Inventor uses block-based coding tools to simplify mobile app development. New blocks simplify Alexa's Skill development and neural network implementation.

Supervised Polygons: AI and Fairness

Supervised Polygons helps 6-8 grade students think critically about fairness in AI models by identifying ways that bias can manifest in algorithm-based decisions and exploring user impact.

Embeducation: Word Embeddings for Kids

Embeducation is a web app for middle schoolers that generates word embeddings and plots these in three-dimensional space to show words can be represented by features.

Selected Publications

AI Education Peer-reviewed Research Articles and Preprints

MIT App Inventor - 2019

Design of a Virtual Tool for Estimating Vocabulary Acquisition through Reading

Ovienmhada, U., Lao, N., & Van Brummelen, J. (2019). Design of a Virtual Tool for Estimating Vocabulary Acquisition through Reading. 2019 International Conference of Education, Research and Innovation (ICERI), 7724-7732.

Learning to program conversationally: A conversational agent to further democratize programming

Van Brummelen, J., Yeo, C., & Weng, K. (2019). Learning to program conversationally: A conversational agent to further democratize programming. 14th annual International Technology, Education and Development Conference (INTED2020).

A Semantics-based Model for Predicting Children's Vocabulary

Grover, I., Park, HW., & Breazeal, C. (2019). A Semantics-Based Model for Predicting Children’s Vocabulary. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19), 1358–1365.

Conversational Agents to Democratize Artificial Intelligence

Van Brummelen, J. (2019). Conversational Agents to Democratize Artificial Intelligence. 2019 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC), 239-240.

The Popstar, the Poet, and the Grinch: Relating Artificial Intelligence to the Computational Thinking Framework with Block-based Coding

Van Brummelen, J., Shen, J.W., & Patton, E.W. (2019). The Popstar, the Poet, and the Grinch: Relating Artificial Intelligence to the Computational Thinking Framework with Block-based Coding. Proceedings of International Conference on Computational Thinking Education, 160-161.

A Model-Free Affective Reinforcement Learning Approach to Personalization of an Autonomous Social Robot Companion for Early Literacy Education

Park, HW., Grover, I., Spaulding, S., Gomez, L., & Breazeal, C. (2019). A Model-Free Affective Reinforcement Learning Approach to Personalization of an Autonomous Social Robot Companion for Early Literacy Education. Proceedings of the AAAI Conference on Artificial Intelligence 33, 687–694.

PopBots: Designing an Artificial Intelligence Curriculum for Early Childhood Education

Williams, R., Park, HW., Oh,L., & Breazeal, C. (2019). PopBots: Designing an Artificial Intelligence Curriculum for Early Childhood Education. Proceedings of the AAAI Conference on Artificial Intelligence 33, 9729–9736.

Can Children Learn Creativity from a Social Robot?

Ali, S., Moroso, T., & Breazeal, C. (2019). Can Children Learn Creativity from a Social Robot?. Proceedings of the 2019 on Creativity and Cognition, 359-368.

A is for Artificial Intelligence: The Impact of Artificial Intelligence Activities on Young Children's Perceptions of Robots

Williams, R., Park, HW., & Breazeal, C. (2019). A Is for Artificial Intelligence: The Impact of Artificial Intelligence Activities on Young Children’s Perceptions of Robots. Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, 1–11.

A Social Robot System for Modeling Children’s Word Pronunciation

Spaulding, S., Chen, H., Ali, S., Kulinski, M., & Breazeal, C. (2018). A Social Robot System for Modeling Children’s Word Pronunciation. Proceedings of the International Conference on Autonomous Agents and MultiAgent Systems (Socially Interactive Agents Track), 1658-1666.

Learning to Program Conversationally: A Conversational Agent to Further Democratize Programming

Patton, E.W., Druga, S., & Van Brummelen, J. (2018). Panel: Block Abstractions for AI. Proceedings of the BLOCKS+ at Systems, Programming, Languages and Applications: Software for Humanity (SPLASH), 1-2.

Growing Growth Mindset with a Social Robot Peer

Park, HW., Rosenberg-Kima, R., Rosenberg, M., Gordon, G., & Breazeal, C. (2017). Growing Growth Mindset with a Social Robot Peer. Proceedings of the 2017 ACM/IEEE International Conference on Human-Robot Interaction, 137-145.