Please use this identifier to cite or link to this item:
https://repository.isls.org/handle/1/10511| Title: | Inferential Detectors to Automate Feedback on Social Skills in the Wild: The Case of the Advice Hour Graphic Novel |
| Authors: | Corrigan, Seth |
| Keywords: | CSCL |
| Issue Date: | 2024 |
| Publisher: | International Society of the Learning Sciences |
| Citation: | Corrigan, S. (2024). Inferential Detectors to Automate Feedback on Social Skills in the Wild: The Case of the Advice Hour Graphic Novel. In Clarke-Midura, J., Kollar, I., Gu, X., & D'Angelo, C. (Eds.), Proceedings of the 17th International Conference on Computer-Supported Collaborative Learning - CSCL 2024 (pp. 201-204). International Society of the Learning Sciences. |
| Abstract: | While youth may benefit from coaching on complex social skills, human-provided solutions may not always be available or scalable. Automating detection of and feedback on social skills, however, requires development of systems that can detect social cues and provide feedback in potentially noisy environments. Advice Hour is an online, interactive graphic novel that is capable of making inferences about social cues of unscripted speakers in uncontrolled environments, i.e., in-the-wild. The Advice Hour system is an example of an inferential detector developed through use of a straightforward three-phase approach that utilizes measurement and machine-learning processes. Importantly, its architecture is flexible, allowing for multiple models that can be localized, or even personalized to reflect the likely inferences of multiple groups or single individuals. This paper describes the Advice Hour experience, the data and process used to develop its inferential detectors, and their level of performance to date. |
| Description: | Short Paper |
| URI: | https://doi.org/10.22318/cscl2024.305722 https://repository.isls.org//handle/1/10511 |
| Appears in Collections: | ISLS Annual Meeting 2024 |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| CSCL2024_201-204.pdf | 289.09 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.