Affect-Aware Student Models for Robot Tutors
Copyright © 2016, International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved. Computational tutoring systems, such as educational software or interactive robots, have the potential for great societal benefit. Such systems track and assess students�...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
2021
|
| Online Access: | https://hdl.handle.net/1721.1/137902 |
| _version_ | 1826209550483587072 |
|---|---|
| author | Spaulding, Samuel Gordon, Goren Breazeal, Cynthia |
| author2 | Massachusetts Institute of Technology. Media Laboratory |
| author_facet | Massachusetts Institute of Technology. Media Laboratory Spaulding, Samuel Gordon, Goren Breazeal, Cynthia |
| author_sort | Spaulding, Samuel |
| collection | MIT |
| description | Copyright © 2016, International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved. Computational tutoring systems, such as educational software or interactive robots, have the potential for great societal benefit. Such systems track and assess students' knowledge via inferential methods, such as the popular Bayesian Knowledge Tracing (BKT) algorithm. However, these methods do not typically draw on the affective signals that human teachers use to assess knowledge, such as indications of discomfort, engagement, or frustration. In this paper we present a novel extension to the BKT model that uses affective data, derived autonomously from video records of children playing an interactive story-telling game with a robot, to infer student knowledge of reading skills. We find that, compared to a control group of children who played the game with only a tablet, children who interacted with an embodied social robot generated stronger affective data signals of engagement and enjoyment during the interaction. We then show that incorporating this affective data into model training improves the quality of the learned knowledge inference models. These results suggest that physically embodied, affect-aware robot tutors can provide more effective and empathic educational experiences for children, and advance both algorithmic and human-centered motivations for further development of systems that tightly integrate affect understanding and complex models of inference with interactive, educational robots. |
| first_indexed | 2024-09-23T14:24:16Z |
| format | Article |
| id | mit-1721.1/137902 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T14:24:16Z |
| publishDate | 2021 |
| record_format | dspace |
| spelling | mit-1721.1/1379022021-11-10T03:15:10Z Affect-Aware Student Models for Robot Tutors Spaulding, Samuel Gordon, Goren Breazeal, Cynthia Massachusetts Institute of Technology. Media Laboratory Copyright © 2016, International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved. Computational tutoring systems, such as educational software or interactive robots, have the potential for great societal benefit. Such systems track and assess students' knowledge via inferential methods, such as the popular Bayesian Knowledge Tracing (BKT) algorithm. However, these methods do not typically draw on the affective signals that human teachers use to assess knowledge, such as indications of discomfort, engagement, or frustration. In this paper we present a novel extension to the BKT model that uses affective data, derived autonomously from video records of children playing an interactive story-telling game with a robot, to infer student knowledge of reading skills. We find that, compared to a control group of children who played the game with only a tablet, children who interacted with an embodied social robot generated stronger affective data signals of engagement and enjoyment during the interaction. We then show that incorporating this affective data into model training improves the quality of the learned knowledge inference models. These results suggest that physically embodied, affect-aware robot tutors can provide more effective and empathic educational experiences for children, and advance both algorithmic and human-centered motivations for further development of systems that tightly integrate affect understanding and complex models of inference with interactive, educational robots. 2021-11-09T15:00:13Z 2021-11-09T15:00:13Z 2016 2019-07-22T11:53:47Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/137902 Spaulding, Samuel, Gordon, Goren and Breazeal, Cynthia. 2016. "Affect-Aware Student Models for Robot Tutors." en https://dl.acm.org/citation.cfm?id=2937050 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf website |
| spellingShingle | Spaulding, Samuel Gordon, Goren Breazeal, Cynthia Affect-Aware Student Models for Robot Tutors |
| title | Affect-Aware Student Models for Robot Tutors |
| title_full | Affect-Aware Student Models for Robot Tutors |
| title_fullStr | Affect-Aware Student Models for Robot Tutors |
| title_full_unstemmed | Affect-Aware Student Models for Robot Tutors |
| title_short | Affect-Aware Student Models for Robot Tutors |
| title_sort | affect aware student models for robot tutors |
| url | https://hdl.handle.net/1721.1/137902 |
| work_keys_str_mv | AT spauldingsamuel affectawarestudentmodelsforrobottutors AT gordongoren affectawarestudentmodelsforrobottutors AT breazealcynthia affectawarestudentmodelsforrobottutors |