File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/978-3-031-36336-8_73
- Scopus: eid_2-s2.0-85164952744
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Annotating Educational Dialog Act with Data Augmentation in Online One-on-One Tutoring
| Title | Annotating Educational Dialog Act with Data Augmentation in Online One-on-One Tutoring |
|---|---|
| Authors | |
| Keywords | Data augmentation Educational dialog act GPT-3.5 Multi-label annotation Online tutoring |
| Issue Date | 3-Jul-2023 |
| Publisher | Springer |
| Abstract | During the COVID-19 pandemic, educational activities have shifted online, providing opportunities for researchers to analyze interaction data between teachers and students. In this study, we focus on automatically annotating dialog acts in one-on-one tutoring on online platforms. We address the challenge of limited training data, particularly for “rare codes”, by proposing a data augmentation pipeline that leverages GPT-3.5’s generative ability to create synthetic, multi-labeled dialog data. Experiments with real online tutoring platform data demonstrate the effectiveness of our approach in enhancing the machine annotator’s accuracy. |
| Persistent Identifier | http://hdl.handle.net/10722/333811 |
| ISSN | 2023 SCImago Journal Rankings: 0.203 |
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Shan, Dapeng | - |
| dc.contributor.author | Wang, Deliang | - |
| dc.contributor.author | Zhang, Chenwei | - |
| dc.contributor.author | Kao, Ben | - |
| dc.contributor.author | Chan, Carol K K | - |
| dc.date.accessioned | 2023-10-06T08:39:16Z | - |
| dc.date.available | 2023-10-06T08:39:16Z | - |
| dc.date.issued | 2023-07-03 | - |
| dc.identifier.issn | 1865-0929 | - |
| dc.identifier.uri | http://hdl.handle.net/10722/333811 | - |
| dc.description.abstract | <p>During the COVID-19 pandemic, educational activities have shifted online, providing opportunities for researchers to analyze interaction data between teachers and students. In this study, we focus on automatically annotating dialog acts in one-on-one tutoring on online platforms. We address the challenge of limited training data, particularly for “rare codes”, by proposing a data augmentation pipeline that leverages GPT-3.5’s generative ability to create synthetic, multi-labeled dialog data. Experiments with real online tutoring platform data demonstrate the effectiveness of our approach in enhancing the machine annotator’s accuracy.<br></p> | - |
| dc.language | eng | - |
| dc.publisher | Springer | - |
| dc.relation.ispartof | The 24th International Conference on Artificial Intelligence in Education - AIED2023 (03/07/2023-07/07/2023, Tokyo, Japan) | - |
| dc.subject | Data augmentation | - |
| dc.subject | Educational dialog act | - |
| dc.subject | GPT-3.5 | - |
| dc.subject | Multi-label annotation | - |
| dc.subject | Online tutoring | - |
| dc.title | Annotating Educational Dialog Act with Data Augmentation in Online One-on-One Tutoring | - |
| dc.type | Conference_Paper | - |
| dc.identifier.doi | 10.1007/978-3-031-36336-8_73 | - |
| dc.identifier.scopus | eid_2-s2.0-85164952744 | - |
| dc.identifier.volume | 1831 CCIS | - |
| dc.identifier.spage | 472 | - |
| dc.identifier.epage | 477 | - |
| dc.identifier.issnl | 1865-0929 | - |