Evidence-centered Assessment for Writing with Generative AI
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913198734573568 |
|---|---|
| author | Cheng, Yixin Lyons, Kayley Chen, Guanliang Gasevic, Dragan Swiecki, Zachari |
| author_facet | Cheng, Yixin Lyons, Kayley Chen, Guanliang Gasevic, Dragan Swiecki, Zachari |
| contents | We propose a learning analytics-based methodology for assessing the collaborative writing of humans and generative artificial intelligence. Framed by the evidence-centered design, we used elements of knowledge-telling, knowledge transformation, and cognitive presence to identify assessment claims; we used data collected from the CoAuthor writing tool as potential evidence for these claims; and we used epistemic network analysis to make inferences from the data about the claims. Our findings revealed significant differences in the writing processes of different groups of CoAuthor users, suggesting that our method is a plausible approach to assessing human-AI collaborative writing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08964 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evidence-centered Assessment for Writing with Generative AI Cheng, Yixin Lyons, Kayley Chen, Guanliang Gasevic, Dragan Swiecki, Zachari Human-Computer Interaction We propose a learning analytics-based methodology for assessing the collaborative writing of humans and generative artificial intelligence. Framed by the evidence-centered design, we used elements of knowledge-telling, knowledge transformation, and cognitive presence to identify assessment claims; we used data collected from the CoAuthor writing tool as potential evidence for these claims; and we used epistemic network analysis to make inferences from the data about the claims. Our findings revealed significant differences in the writing processes of different groups of CoAuthor users, suggesting that our method is a plausible approach to assessing human-AI collaborative writing. |
| title | Evidence-centered Assessment for Writing with Generative AI |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2401.08964 |