Joe Michaelis

Position title: Assistant Professor - Learning Sciences and Computer Science in University of Illinois at Chicago

Email: jmich@uic.edu

About

Joseph E Michaelis is an Assistant Professor of Learning Sciences, and of Computer Science in UIC’s College of Engineering. Joe’s research sits at the nexus of learning sciences and human-computer interaction disciplines.

His research focuses on designing and assessing educational technologies by utilizing human-centered methods and interaction modeling in HCI, and on interest, motivation and social-cultural learning perspectives in the learning sciences. These technologies are designed for social connection-making with learners to support learning and interest through long-term engagement, in ways that seamlessly integrate into existing educational activities in classrooms, informal learning environments, and at home.

Joe’s current research focuses on designing learning companion robots to work with children while they read at home and while learning science. These companion robots “talk” to children while they read augmented books or participate in science activities by providing comments tailored to their interests and ability. The goal of each child-robot interaction is to build social connections, provide comprehension support, and promote interest in reading and STEM learning.

Prior to joining UIC, Dr. Michaelis received a Ph.D. in learning sciences from University of Wisconsin-Madison with a Ph.D. minor in computer science and a MS in science education leadership from the Illinois Institute of Technology.

  • White, N., B. Cagiltay, J. Michaelis, and B. Mutlu. “Designing Emotionally Expressive Social Commentary to Facilitate Child-Robot Interaction”. Interaction Design and Children, Association for Computing Machinery, 2021, pp. 314–325.
    Read more Document
  • Design_Learning_Companion_Bot
    Cagiltay, B., H. R. Ho, J. Michaelis, and B. Mutlu. “Investigating Family Perceptions and Design Preferences for an in-Home robot”. Proceedings of the Interaction Design and Children Conference, 2020, pp. 229-42.

    Abstract

    Child-robot interactions in educational, developmental, and health domains are widely explored, but little is known about how families perceive the presence of a social robot in their home environment and its participation in day-to-day activities. To close this gap, we conducted a participatory design (PD) study with six families, with children aged 10–12, to examine how families perceive in-home social robots participating in shared activities. Our analysis identified three main themes: (1) the robot can have a range of roles in the home as a companion or as an assistant; (2) family members have different preferences for how they would like to interact with the robot in group or personal interactions; and (3) families have privacy, confidentiality, and ethical concerns regarding a social robot’s presence in the home. Based on these themes and existing literature, we provide guidelines for the future interaction design of in-home social robots for children.

    DOI: 10.1145/3392063.3394411

    Bibtex

    @inproceedings{Cagiltay_2020,
    	doi = {10.1145/3392063.3394411},
    	url = {https://doi.org/10.1145%2F3392063.3394411},
    	year = 2020,
    	month = {jun},
    	publisher = {{ACM}},
    	author = {Bengisu Cagiltay and Hui-Ru Ho and Joseph E Michaelis and Bilge Mutlu},
    	title = {Investigating family perceptions and design preferences for an in-home robot},
    	booktitle = {Proceedings of the Interaction Design and Children Conference}
    }
    Read more Read more Document
  • Michaelis, J., A. Siebert-Evenstone, D. Shaffer, B. Mutlu, and B. Mutlu. “Collaborative or Simply Uncaged? Understanding Human-Cobot Interactions in Automation”. Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, 2020, pp. 1-12.

    Abstract

    Collaborative robots, or cobots, represent a breakthrough technology designed for high-level (e.g. collaborative) interactions between workers and robots with capabilities for flexible deployment in industries such as manufacturing. Understanding how workers and companies use and integrate cobots is important to inform the future design of cobot systems and educational technologies that facilitate effective worker-cobot interaction. Yet, little is known about typical training for collaboration and the application of cobots in manufacturing. To close this gap, we interviewed nine experts in manufacturing about their experience with cobots. Our thematic analysis revealed that, contrary to the envisioned use, experts described most cobot applications as only low-level (e.g. pressing start/stop buttons) interactions with little flexible deployment, and experts felt traditional robotics skills were needed for collaborative and flexible interaction with cobots. We conclude with design recommendations for improved future robots, including programming and interface designs, and educational technologies to support collaborative use.

    DOI:10.1145/3313831.3376547

    Bibtex

    @inproceedings{Michaelis_2020,
    	doi = {10.1145/3313831.3376547},
    	url = {https://doi.org/10.1145%2F3313831.3376547},
    	year = 2020,
    	month = {apr},
    	publisher = {{ACM}},
    	author = {Joseph E. Michaelis and Amanda Siebert-Evenstone and David Williamson Shaffer and Bilge Mutlu},
    	title = {Collaborative or Simply Uncaged? Understanding Human-Cobot Interactions in Automation},
    	booktitle = {Proceedings of the 2020 {CHI} Conference on Human Factors in Computing Systems}
    }
  • Design Learning
    Michaelis, J., and B. Mutlu. “Supporting Interest in Science Learning With a Social robot”. Proceedings of the 18th ACM International Conference on Interaction Design and Children, ACM, 2019, pp. 71-82.

    Abstract

    Education research offers strong evidence that social supports, learning interventions situated in meaningful social interaction, during learning can aid in developing interest and promote understanding for the content. However, children are often asked to complete homework tasks in isolation. To address this discrepancy, we build on prior work in social robotics to demonstrate the effectiveness of a socially adept robot, as compared to a socially neutral robot to generate situational interest and improve learning while reading a science textbook. We conducted a randomized controlled experiment (N = 63) of one reading interaction with either the socially adept or socially neutral robot. Our results show that children who read with a socially adept robot found the robot to be friendlier and more attractive, reported a higher level of closeness and mutual-liking for the robot, had higher situational interest, and made more scientifically accurate statements on a concept-map activity. We discuss the practical and theoretical implications of these findings.

    DOI: 10.1145/3311927.3323154

    BibTex

    @inproceedings{Michaelis_2019,
    	doi = {10.1145/3311927.3323154},
    	url = {https://doi.org/10.1145%2F3311927.3323154},
    	year = 2019,
    	month = {jun},
    	publisher = {{ACM}},
    	author = {Joseph E. Michaelis and Bilge Mutlu},
    	title = {Supporting Interest in Science Learning with a Social Robot},
    	booktitle = {Proceedings of the 18th {ACM} International Conference on Interaction Design and Children}
    }
    Read more
  • Michaelis, J., and B. Mutlu. “Social Reading: Field Study With an In-Home Learning Companion Robot”. Science Robotics , International Society of the Learning Sciences, Inc.[ISLS]., 2018.

    Abstract

    This study explores changes in childrens’ (N = 12) responses to interacting with a learning companion robot for reading over time. Initial comparisons of pre- and post- interviews with the children revealed that social companionship, and situational interest were maintained after two weeks of in-home interaction.

    DOI: 10.1126/scirobotics.aat5999

    Bibtex

    @article{Michaelis_2018,
    	doi = {10.1126/scirobotics.aat5999},
    	url = {https://doi.org/10.1126%2Fscirobotics.aat5999},
    	year = 2018,
    	month = {aug},
    	publisher = {American Association for the Advancement of Science ({AAAS})},
    	volume = {3},
    	number = {21},
    	pages = {eaat5999},
    	author = {Joseph E. Michaelis and Bilge Mutlu},
    	title = {Reading socially: Transforming the in-home reading experience with a learning-companion robot},
    	journal = {Science Robotics}
    }
    Read more
  • Design_Learning_Companion_Bot
    Michaelis, J., and B. Mutlu. “Someone to Read With: Design of and Experiences With an In-Home Learning Companion Robot for Reading”. Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, ACM, 2017, pp. 301-12.

    Abstract

    The development of literacy and reading proficiency is a building block of lifelong learning that must be supported both in the classroom and at home. While the promise of interactive learning technologies has widely been demonstrated, little is known about how an interactive robot might play a role in this development. We used eight design features based on recommendations from interest-development and human-robot-interaction literatures to design an in-home learning companion robot for children aged 11–12. The robot was used as a technology probe to explore families’ (N=8) habits and views about reading, how a reading technology might be used, and how children perceived reading with the robot. Our results indicate reading with the learning companion to be a way to socially engage with reading, which may promote the development of reading interest and ability. We discuss design and research implications based on our findings.

    DOI: 10.1145/3025453.3025499

    BibTex

    @inproceedings{Michaelis_2017,
    	doi = {10.1145/3025453.3025499},
    	url = {https://doi.org/10.1145%2F3025453.3025499},
    	year = 2017,
    	month = {may},
    	publisher = {{ACM}},
    	author = {Joseph E. Michaelis and Bilge Mutlu},
    	title = {Someone to Read with},
    	booktitle = {Proceedings of the 2017 {CHI} Conference on Human Factors in Computing Systems}
    }
    Read more Read more