Affect and Inference in Bayesian Knowledge Tracing with a Robot Tutor
In this paper, we present work to construct a robotic tutoring system that can assess student knowledge in real time during an educational interaction. Like a good human teacher, the robot draws on multimodal data sources to infer whether students have mastered language skills. Specifically, the mod...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2017
|
| Online Access: | http://hdl.handle.net/1721.1/109395 https://orcid.org/0000-0002-0587-2065 |
| _version_ | 1826191105921646592 |
|---|---|
| author | Spaulding, Samuel Lee Breazeal, Cynthia Lynn |
| author2 | Massachusetts Institute of Technology. Media Laboratory |
| author_facet | Massachusetts Institute of Technology. Media Laboratory Spaulding, Samuel Lee Breazeal, Cynthia Lynn |
| author_sort | Spaulding, Samuel Lee |
| collection | MIT |
| description | In this paper, we present work to construct a robotic tutoring system that can assess student knowledge in real time during an educational interaction. Like a good human teacher, the robot draws on multimodal data sources to infer whether students have mastered language skills. Specifically, the model extends the standard Bayesian Knowledge Tracing algorithm to incorporate an estimate of the student's affective state (whether he/she is confused, bored, engaged, smiling, etc.) in order to predict future educational performance. We propose research to answer two questions: First, does augmenting the model with affective information improve the computational quality of inference? Second, do humans display more prominent affective signals in an interaction with a robot, compared to a screen-based agent? By answering these questions, this work has the potential to provide both algorithmic and human-centered motivations for further development of robotic systems that tightly integrate affect understanding and complex models of inference with interactive, educational robots. |
| first_indexed | 2024-09-23T08:50:17Z |
| format | Article |
| id | mit-1721.1/109395 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T08:50:17Z |
| publishDate | 2017 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1093952022-09-30T11:38:38Z Affect and Inference in Bayesian Knowledge Tracing with a Robot Tutor Spaulding, Samuel Lee Breazeal, Cynthia Lynn Massachusetts Institute of Technology. Media Laboratory Program in Media Arts and Sciences (Massachusetts Institute of Technology) Spaulding, Samuel Lee Breazeal, Cynthia L. In this paper, we present work to construct a robotic tutoring system that can assess student knowledge in real time during an educational interaction. Like a good human teacher, the robot draws on multimodal data sources to infer whether students have mastered language skills. Specifically, the model extends the standard Bayesian Knowledge Tracing algorithm to incorporate an estimate of the student's affective state (whether he/she is confused, bored, engaged, smiling, etc.) in order to predict future educational performance. We propose research to answer two questions: First, does augmenting the model with affective information improve the computational quality of inference? Second, do humans display more prominent affective signals in an interaction with a robot, compared to a screen-based agent? By answering these questions, this work has the potential to provide both algorithmic and human-centered motivations for further development of robotic systems that tightly integrate affect understanding and complex models of inference with interactive, educational robots. National Science Foundation (U.S.) (Grant CCF-1138986) National Science Foundation (U.S.). Graduate Research Fellowship Program (Grant No. 1122374) 2017-05-26T22:24:21Z 2017-05-26T22:24:21Z 2015-03 Article http://purl.org/eprint/type/ConferencePaper 978-1-4503-3318-4 http://hdl.handle.net/1721.1/109395 Spaulding, Samuel, and Cynthia Breazeal. “Affect and Inference in Bayesian Knowledge Tracing with a Robot Tutor.” Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction Extended Abstracts - HRI'15 Extended Abstracts. ACM Press, 2015. 219–220. https://orcid.org/0000-0002-0587-2065 en_US http://dx.doi.org/10.1145/2701973.2702720 Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction Extended Abstracts - HRI'15 Extended Abstracts Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT web domain |
| spellingShingle | Spaulding, Samuel Lee Breazeal, Cynthia Lynn Affect and Inference in Bayesian Knowledge Tracing with a Robot Tutor |
| title | Affect and Inference in Bayesian Knowledge Tracing with a Robot Tutor |
| title_full | Affect and Inference in Bayesian Knowledge Tracing with a Robot Tutor |
| title_fullStr | Affect and Inference in Bayesian Knowledge Tracing with a Robot Tutor |
| title_full_unstemmed | Affect and Inference in Bayesian Knowledge Tracing with a Robot Tutor |
| title_short | Affect and Inference in Bayesian Knowledge Tracing with a Robot Tutor |
| title_sort | affect and inference in bayesian knowledge tracing with a robot tutor |
| url | http://hdl.handle.net/1721.1/109395 https://orcid.org/0000-0002-0587-2065 |
| work_keys_str_mv | AT spauldingsamuellee affectandinferenceinbayesianknowledgetracingwitharobottutor AT breazealcynthialynn affectandinferenceinbayesianknowledgetracingwitharobottutor |