Tutorly: Turning Programming Videos Into Apprenticeship Learning Environments with LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911883430199296 |
|---|---|
| author | Li, Wengxi Pea, Roy Haber, Nick Subramonyam, Hari |
| author_facet | Li, Wengxi Pea, Roy Haber, Nick Subramonyam, Hari |
| contents | Online programming videos, including tutorials and streamcasts, are widely popular and contain a wealth of expert knowledge. However, effectively utilizing these resources to achieve targeted learning goals can be challenging. Unlike direct tutoring, video content lacks tailored guidance based on individual learning paces, personalized feedback, and interactive engagement necessary for support and monitoring. Our work transforms programming videos into one-on-one tutoring experiences using the cognitive apprenticeship framework. Tutorly, developed as a JupyterLab Plugin, allows learners to (1) set personalized learning goals, (2) engage in learning-by-doing through a conversational LLM-based mentor agent, (3) receive guidance and feedback based on a student model that steers the mentor moves. In a within-subject study with 16 participants learning exploratory data analysis from a streamcast, Tutorly significantly improved their performance from 61.9% to 76.6% based on a post-test questionnaire. Tutorly demonstrates the potential for enhancing programming video learning experiences with LLM and learner modeling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_12946 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Tutorly: Turning Programming Videos Into Apprenticeship Learning Environments with LLMs Li, Wengxi Pea, Roy Haber, Nick Subramonyam, Hari Human-Computer Interaction Machine Learning Online programming videos, including tutorials and streamcasts, are widely popular and contain a wealth of expert knowledge. However, effectively utilizing these resources to achieve targeted learning goals can be challenging. Unlike direct tutoring, video content lacks tailored guidance based on individual learning paces, personalized feedback, and interactive engagement necessary for support and monitoring. Our work transforms programming videos into one-on-one tutoring experiences using the cognitive apprenticeship framework. Tutorly, developed as a JupyterLab Plugin, allows learners to (1) set personalized learning goals, (2) engage in learning-by-doing through a conversational LLM-based mentor agent, (3) receive guidance and feedback based on a student model that steers the mentor moves. In a within-subject study with 16 participants learning exploratory data analysis from a streamcast, Tutorly significantly improved their performance from 61.9% to 76.6% based on a post-test questionnaire. Tutorly demonstrates the potential for enhancing programming video learning experiences with LLM and learner modeling. |
| title | Tutorly: Turning Programming Videos Into Apprenticeship Learning Environments with LLMs |
| topic | Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2405.12946 |