A Comparison of Responsive and General Guidance to Promote Learning in an Online Science Dialog
Students benefit from dialogs about their explanations of complex scientific phenomena, and middle school science teachers cannot realistically provide all the guidance they need. We study ways to extend generative teacher–student dialogs to more students by using AI tools. We compare Responsive web...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Education Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7102/14/12/1383 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850050114715910144 |
|---|---|
| author | Libby Gerard Marcia C. Linn Marlen Holtmann |
| author_facet | Libby Gerard Marcia C. Linn Marlen Holtmann |
| author_sort | Libby Gerard |
| collection | DOAJ |
| description | Students benefit from dialogs about their explanations of complex scientific phenomena, and middle school science teachers cannot realistically provide all the guidance they need. We study ways to extend generative teacher–student dialogs to more students by using AI tools. We compare Responsive web-based dialogs to General web-based dialogs by evaluating the ideas students add and the quality of their revised explanations. We designed the General guidance to motivate and encourage students to revise their explanations, similar to how an experienced classroom teacher might instruct the class. We designed the Responsive guidance to emulate a student–teacher dialog, based on studies of experienced teachers guiding individual students. The analyses comparing the Responsive and the General condition are based on a randomized assignment of a total sample of 507 pre-college students. These students were taught by five different teachers in four schools. A significantly higher proportion of students added new accurate ideas in the Responsive condition compared to the General condition during the dialog. This research shows that by using NLP to identify ideas and assign guidance, students can broaden and refine their ideas. Responsive guidance, inspired by how experienced teachers guide individual students, is more valuable than General guidance. |
| format | Article |
| id | doaj-art-45415deb7f6d4e75b02484707ac137b1 |
| institution | DOAJ |
| issn | 2227-7102 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Education Sciences |
| spelling | doaj-art-45415deb7f6d4e75b02484707ac137b12025-08-20T02:53:33ZengMDPI AGEducation Sciences2227-71022024-12-011412138310.3390/educsci14121383A Comparison of Responsive and General Guidance to Promote Learning in an Online Science DialogLibby Gerard0Marcia C. Linn1Marlen Holtmann2School of Education, UC Berkeley, Berkeley Way West Building (BWW), 2121 Berkeley Way, Berkeley, CA 94720-1670, USASchool of Education, UC Berkeley, Berkeley Way West Building (BWW), 2121 Berkeley Way, Berkeley, CA 94720-1670, USAInternational Association for the Evaluation of Educational Achievement, Überseering 27, 22297 Hamburg, GermanyStudents benefit from dialogs about their explanations of complex scientific phenomena, and middle school science teachers cannot realistically provide all the guidance they need. We study ways to extend generative teacher–student dialogs to more students by using AI tools. We compare Responsive web-based dialogs to General web-based dialogs by evaluating the ideas students add and the quality of their revised explanations. We designed the General guidance to motivate and encourage students to revise their explanations, similar to how an experienced classroom teacher might instruct the class. We designed the Responsive guidance to emulate a student–teacher dialog, based on studies of experienced teachers guiding individual students. The analyses comparing the Responsive and the General condition are based on a randomized assignment of a total sample of 507 pre-college students. These students were taught by five different teachers in four schools. A significantly higher proportion of students added new accurate ideas in the Responsive condition compared to the General condition during the dialog. This research shows that by using NLP to identify ideas and assign guidance, students can broaden and refine their ideas. Responsive guidance, inspired by how experienced teachers guide individual students, is more valuable than General guidance.https://www.mdpi.com/2227-7102/14/12/1383knowledge integrationtechnologyguidancemachine learningAInatural language processing |
| spellingShingle | Libby Gerard Marcia C. Linn Marlen Holtmann A Comparison of Responsive and General Guidance to Promote Learning in an Online Science Dialog Education Sciences knowledge integration technology guidance machine learning AI natural language processing |
| title | A Comparison of Responsive and General Guidance to Promote Learning in an Online Science Dialog |
| title_full | A Comparison of Responsive and General Guidance to Promote Learning in an Online Science Dialog |
| title_fullStr | A Comparison of Responsive and General Guidance to Promote Learning in an Online Science Dialog |
| title_full_unstemmed | A Comparison of Responsive and General Guidance to Promote Learning in an Online Science Dialog |
| title_short | A Comparison of Responsive and General Guidance to Promote Learning in an Online Science Dialog |
| title_sort | comparison of responsive and general guidance to promote learning in an online science dialog |
| topic | knowledge integration technology guidance machine learning AI natural language processing |
| url | https://www.mdpi.com/2227-7102/14/12/1383 |
| work_keys_str_mv | AT libbygerard acomparisonofresponsiveandgeneralguidancetopromotelearninginanonlinesciencedialog AT marciaclinn acomparisonofresponsiveandgeneralguidancetopromotelearninginanonlinesciencedialog AT marlenholtmann acomparisonofresponsiveandgeneralguidancetopromotelearninginanonlinesciencedialog AT libbygerard comparisonofresponsiveandgeneralguidancetopromotelearninginanonlinesciencedialog AT marciaclinn comparisonofresponsiveandgeneralguidancetopromotelearninginanonlinesciencedialog AT marlenholtmann comparisonofresponsiveandgeneralguidancetopromotelearninginanonlinesciencedialog |