---
title: "Is ChatGPT a Good Teacher Coach? Measuring Zero-Shot"
description: "They define three tasks: (A) scoring transcript segments against rubric items drawn from the CLASS… 40 references, cited by 32 papers here."
authors: ["Rose E. Wang", "Dorottya Demszky"]
year: 2023
venue: "arXiv:2306.03090"
source: "https://arxiv.org/abs/2306.03090"
doi: "10.48550/arxiv.2306.03090"
arxiv: "2306.03090"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wang-2023-chatgpt-good-teacher-coach-measuring/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2023-chatgpt-good-teacher-coach-measuring/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/9/) / Is ChatGPT a Good Teacher Coach? Measuring Zero-Shot Performance For Scoring and Providing Actionable Insights on Classroom Instruction

# Is ChatGPT a Good Teacher Coach? Measuring Zero-Shot Performance For Scoring and Providing Actionable Insights on Classroom Instruction

**Authors:** [Rose E. Wang](https://md.research.elamur.ai/free/en/authors/rose-wang/) and [Dorottya Demszky](https://md.research.elamur.ai/free/en/authors/dorottya-demszky/) · **Year:** 2023 · **Venue:** arXiv:2306.03090 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2306.03090) · [PDF](https://arxiv.org/pdf/2306.03090) · [DOI 10.48550/arxiv.2306.03090](https://doi.org/10.48550/arxiv.2306.03090) · [arXiv 2306.03090](https://arxiv.org/abs/2306.03090) · [OpenAlex](https://openalex.org/W4379548478)

**Citations:** 4 citations (OpenAlex, 2026-10-14) · [32](https://md.research.elamur.ai/free/en/papers/wang-2023-chatgpt-good-teacher-coach-measuring/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Classroom observation followed by expert coaching is central to teacher development. Most teachers, however, rarely receive regular, high-quality feedback because skilled coaches are scarce and expensive. The authors test whether ChatGPT, used zero-shot, could serve as a low-cost supplement to human coaching. They define three tasks: (A) scoring transcript segments against rubric items drawn from the CLASS and MQI frameworks, (B) pointing out moments where the instruction worked well and moments where chances to teach effectively were passed up, and (C) suggesting concrete ways to draw out more student reasoning. The inputs come from the NCTE transcript dataset of US elementary math lessons. Task A predictions were compared with expert raters' scores, and experienced math teachers judged Task B and C outputs on several helpfulness criteria. ChatGPT's scores barely track human ratings. Its feedback is generally on-topic and often actionable, but it tends to lack novelty and insight and sometimes misreads the lesson. The work contributes a reusable task and evaluation framework and shows how far current LLMs remain from expert coaches.

## Key points
- Data: NCTE Transcript dataset, which contains 1,660 anonymized 4th–5th grade math lessons (45–60 min each, recorded 2010–2013) from 317 teachers in 4 US school districts. The lessons were scored by experts with CLASS and MQI.
- Items evaluated: CLASS items CLPC, CLBM and CLINSTD (1–7 scale, 15-minute segments) and MQI items EXPL, REMED, LANGIMP and SMQR (1–3 scale, 7.5-minute segments).
- Task A: correlation with human scores stayed low for every item, even after rubric descriptions and reasoning steps were added to the prompt.
- Task B: teachers judged 50–70% of outputs as not insightful and 35–50% as not relevant to the instrument item. Across tasks, roughly 15–30% of responses were unfaithful (hallucinated) interpretations of the lesson.
- Task C: 82% of suggestions recommended practices the teacher was already using in the transcript, although most suggestions were actionable. Code and model outputs are released on GitHub (rosewang2008/zero-shot-teacher-feedback).

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Stanford University](https://md.research.elamur.ai/free/en/universities/stanford-university/) — University, Stanford, United States · 434 works · 314,419 citations

📚 Shelves (3): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works

## Cite

Cite as: Rose E. Wang and Dorottya Demszky. 2023. Is ChatGPT a Good Teacher Coach? Measuring Zero-Shot Performance For Scoring and Providing Actionable Insights on Classroom Instruction. arXiv:2306.03090.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{wang2023is,
  title = {{Is ChatGPT a Good Teacher Coach? Measuring Zero-Shot Performance For Scoring and Providing Actionable Insights on Classroom Instruction}},
  author = {Rose E. Wang and Dorottya Demszky},
  year = {2023},
  doi = {10.48550/arxiv.2306.03090},
  eprint = {2306.03090},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2306.03090}
}
```

- [← previous Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing](https://md.research.elamur.ai/free/en/papers/jung-2023-impossible-distillation-low-quality-model/)
- [next → The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR](https://md.research.elamur.ai/free/en/papers/sanabria-2023-edinburgh-international-accents-english-corpus/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/9/)

## References

40 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Clement Adelman and Roy Walker. 2003. A guide to classroom observation. Routledge. [find](https://scholar.google.com/scholar?q=Clement+Adelman+and+Roy+Walker%2E+2003%2E+A+guide+to+classroom+observation%2E+Routledge%2E)
2. L. Alrajhi, A. Alamri, F. D. Pereira, and A. I. Cristea. 2021. Urgency analysis of learners’ comments: An automated intervention priority model for mooc. In International Conference on Intelligent Tutoring Systems, pages 148–160. [find](https://scholar.google.com/scholar?q=L%2E+Alrajhi%2C+A%2E+Alamri%2C+F%2E+D%2E+Pereira%2C+and+A%2E+I%2E+Cristea%2E+2021%2E+Urgency+analysis+of+learners%E2%80%99+comments%3A+An+automated+intervention+priority+model+for+mooc%2E+In+International+Conference+on+Intelligent+Tut)
3. S. Aslan, N. Alyuz, C. Tanriover, S. E. Mete, E. Okur, S. K. D’Mello, and A. Arslan Esme. 2019. Investigating the impact of a real-time. In multimodal student engagement analytics technology in authentic classrooms, pages 1–12. of the 2019 CHI conference on human factors in computing systems. [find](https://scholar.google.com/scholar?q=S%2E+Aslan%2C+N%2E+Alyuz%2C+C%2E+Tanriover%2C+S%2E+E%2E+Mete%2C+E%2E+Okur%2C+S%2E+K%2E+D%E2%80%99Mello%2C+and+A%2E+Arslan+Esme%2E+2019%2E+Investigating+the+impact+of+a+real%2Dtime%2E+In+multimodal+student+engagement+analytics+technology+in+authen)
4. Zeljana Basic, Ana Banovac, Ivana Kruzic, and Ivan Jerkovic. 2023. Better by you, better than me, chatgpt3 as writing assistance in students essays. [find](https://scholar.google.com/scholar?q=Zeljana+Basic%2C+Ana+Banovac%2C+Ivana+Kruzic%2C+and+Ivan+Jerkovic%2E+2023%2E+Better+by+you%2C+better+than+me%2C+chatgpt3+as+writing+assistance+in+students+essays%2E)
5. Nathalie Bonneton-Botté, Sylvain Fleury, Nathalie Girard, Maëlys Le Magadou, Anthony Cherbonnier, Mickaël Renault, Eric Anquetil, and Eric Jamet. 2020. Can tablet apps support the learning of handwriting? an investigation of learning outcomes in kindergarten classroom. Computers & Education, 151:103… [find](https://scholar.google.com/scholar?q=Nathalie+Bonneton%2DBott%C3%A9%2C+Sylvain+Fleury%2C+Nathalie+Girard%2C+Ma%C3%ABlys+Le+Magadou%2C+Anthony+Cherbonnier%2C+Micka%C3%ABl+Renault%2C+Eric+Anquetil%2C+and+Eric+Jamet%2E+2020%2E+Can+tablet+apps+support+the+learning+of+handwrit)
6. Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems, 30. [find](https://scholar.google.com/scholar?q=Paul+F+Christiano%2C+Jan+Leike%2C+Tom+Brown%2C+Miljan+Martic%2C+Shane+Legg%2C+and+Dario+Amodei%2E+2017%2E+Deep+reinforcement+learning+from+human+preferences%2E+Advances+in+neural+information+processing+systems%2C+30%2E)
7. Wei Dai, Jionghao Lin, Flora Jin, Tongguang Li, Yi-Shan Tsai, Dragan Gasevic, and Guanliang Chen. 2023. Can large language models provide feedback to students? a case study on chatgpt. [find](https://scholar.google.com/scholar?q=Wei+Dai%2C+Jionghao+Lin%2C+Flora+Jin%2C+Tongguang+Li%2C+Yi%2DShan+Tsai%2C+Dragan+Gasevic%2C+and+Guanliang+Chen%2E+2023%2E+Can+large+language+models+provide+feedback+to+students%3F+a+case+study+on+chatgpt%2E)
8. Dorottya Demszky and Heather Hill. 2022. The NCTE Transcripts: A dataset of elementary math classroom transcripts. arXiv preprint arXiv:2211.11772. [find](https://scholar.google.com/scholar?q=Dorottya+Demszky+and+Heather+Hill%2E+2022%2E+The+NCTE+Transcripts%3A+A+dataset+of+elementary+math+classroom+transcripts%2E+arXiv+preprint+arXiv%3A2211%2E11772%2E)
9. Dorottya Demszky and Jing Liu. 2023. M-Powering Teachers: Natural language processing powered feedback improves 1:1 instruction and student outcomes. [find](https://scholar.google.com/scholar?q=Dorottya+Demszky+and+Jing+Liu%2E+2023%2E+M%2DPowering+Teachers%3A+Natural+language+processing+powered+feedback+improves+1%3A1+instruction+and+student+outcomes%2E)
10. Dorottya Demszky, Jing Liu, Heather Hill, Dan Jurafsky, and Chris Piech. 2023a. Can automated feedback improve teachers’ uptake of student ideas? evidence from a randomized controlled trial in a large-scale online. Education Evaluation and Policy Analysis (EEPA). [find](https://scholar.google.com/scholar?q=Dorottya+Demszky%2C+Jing+Liu%2C+Heather+Hill%2C+Dan+Jurafsky%2C+and+Chris+Piech%2E+2023a%2E+Can+automated+feedback+improve+teachers%E2%80%99+uptake+of+student+ideas%3F+evidence+from+a+randomized+controlled+trial+in+a+large)
11. Dorottya Demszky, Jing Liu, Heather C Hill, Dan Jurafsky, and Chris Piech. 2023b. Can automated feedback improve teachers’ uptake of student ideas? evidence from a randomized controlled trial in a large-scale online course. Educational Evaluation and Policy Analysis. [find](https://scholar.google.com/scholar?q=Dorottya+Demszky%2C+Jing+Liu%2C+Heather+C+Hill%2C+Dan+Jurafsky%2C+and+Chris+Piech%2E+2023b%2E+Can+automated+feedback+improve+teachers%E2%80%99+uptake+of+student+ideas%3F+evidence+from+a+randomized+controlled+trial+in+a+lar)
12. Laura M Desimone and Katie Pak. 2017. Instructional coaching as high-quality professional development. Theory into practice, 56(1):3–12. [find](https://scholar.google.com/scholar?q=Laura+M+Desimone+and+Katie+Pak%2E+2017%2E+Instructional+coaching+as+high%2Dquality+professional+development%2E+Theory+into+practice%2C+56%281%29%3A3%E2%80%9312%2E)
13. P. J. Donnelly, N. Blanchard, A. M. Olney, S. Kelly, M. Nystrand, and S. K. D’Mello. 2017. Words matter: Automatic detection of teacher questions in live classroom discourse using linguistics, acoustics and context. 218–227. Proceedings of the Seventh International Learning Analytics & Knowledge Con… [find](https://scholar.google.com/scholar?q=P%2E+J%2E+Donnelly%2C+N%2E+Blanchard%2C+A%2E+M%2E+Olney%2C+S%2E+Kelly%2C+M%2E+Nystrand%2C+and+S%2E+K%2E+D%E2%80%99Mello%2E+2017%2E+Words+matter%3A+Automatic+detection+of+teacher+questions+in+live+classroom+discourse+using+linguistics%2C+acousti)
14. Fabrizio Gilardi, Meysam Alizadeh, and Maël Kubli. 2023. [Chatgpt outperforms crowd-workers for text-annotation tasks](https://md.research.elamur.ai/free/en/papers/gilardi-2023-chatgpt-outperforms-crowd-workers-text/).
15. Xingwei He, Zhenghao Lin, Yeyun Gong, A-Long Jin, Hang Zhang, Chen Lin, Jian Jiao, Siu Ming Yiu, Nan Duan, and Weizhu Chen. 2023. [Annollm: Making large language models to be better crowdsourced annotators](https://md.research.elamur.ai/free/en/papers/he-2023-annollm-making-large-language-models/).
16. Heather C Hill, Merrie L Blunk, Charalambos Y Charalambous, Jennifer M Lewis, Geoffrey C Phelps, Laurie Sleep, and Deborah Loewenberg Ball. 2008. Mathematical knowledge for teaching and the mathematical quality of instruction: An exploratory study. Cognition and instruction, 26(4):430–511. [find](https://scholar.google.com/scholar?q=Heather+C+Hill%2C+Merrie+L+Blunk%2C+Charalambos+Y+Charalambous%2C+Jennifer+M+Lewis%2C+Geoffrey+C+Phelps%2C+Laurie+Sleep%2C+and+Deborah+Loewenberg+Ball%2E+2008%2E+Mathematical+knowledge+for+teaching+and+the+mathematic)
17. Pihel Hunt, Äli Leijen, and Marieke van der Schaaf. 2021. Automated feedback is nice and human presence makes it better: Teachers’ perceptions of feedback by means of an e-portfolio enhanced with learning analytics. Education Sciences, 11(6):278. [find](https://scholar.google.com/scholar?q=Pihel+Hunt%2C+%C3%84li+Leijen%2C+and+Marieke+van+der+Schaaf%2E+2021%2E+Automated+feedback+is+nice+and+human+presence+makes+it+better%3A+Teachers%E2%80%99+perceptions+of+feedback+by+means+of+an+e%2Dportfolio+enhanced+with+lear)
18. Jennifer Jacobs, Karla Scornavacco, Charis Harty, Abhijit Suresh, Vivian Lai, and Tamara Sumner. 2022. Promoting rich discussions in mathematics classrooms: Using personalized, automated feedback to support reflection and instructional change. Teaching and Teacher Education, 112:103631. [find](https://scholar.google.com/scholar?q=Jennifer+Jacobs%2C+Karla+Scornavacco%2C+Charis+Harty%2C+Abhijit+Suresh%2C+Vivian+Lai%2C+and+Tamara+Sumner%2E+2022%2E+Promoting+rich+discussions+in+mathematics+classrooms%3A+Using+personalized%2C+automated+feedback+to+s)
19. E. Jensen, M. Dale, P. J. Donnelly, C. Stone, S. Kelly, A. Godley, and S. K. D’Mello. 2020. Toward automated feedback on teacher discourse to enhance teacher learning. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems. 1–13. [find](https://scholar.google.com/scholar?q=E%2E+Jensen%2C+M%2E+Dale%2C+P%2E+J%2E+Donnelly%2C+C%2E+Stone%2C+S%2E+Kelly%2C+A%2E+Godley%2C+and+S%2E+K%2E+D%E2%80%99Mello%2E+2020%2E+Toward+automated+feedback+on+teacher+discourse+to+enhance+teacher+learning%2E+In+Proceedings+of+the+2020+CHI+C)
20. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. [Survey of hallucination in natural language generation](https://md.research.elamur.ai/free/en/papers/ji-2022-survey-hallucination-natural-language-generation/). ACM Computing Surveys, 55(12):1–38.
21. S. Kelly, A. M. Olney, P. Donnelly, M. Nystrand, and S. K. D’Mello. 2018. Automatically measuring question authenticity in real-world classrooms. Educational Researcher, 47:7. [find](https://scholar.google.com/scholar?q=S%2E+Kelly%2C+A%2E+M%2E+Olney%2C+P%2E+Donnelly%2C+M%2E+Nystrand%2C+and+S%2E+K%2E+D%E2%80%99Mello%2E+2018%2E+Automatically+measuring+question+authenticity+in+real%2Dworld+classrooms%2E+Educational+Researcher%2C+47%3A7%2E)
22. Sean Kelly, Robert Bringe, Esteban Aucejo, and Jane Cooley Fruehwirth. 2020. Using global observation protocols to inform research on teaching effectiveness and school improvement: Strengths and emerging limitations. Education Policy Analysis Archives, 28:62–62. [find](https://scholar.google.com/scholar?q=Sean+Kelly%2C+Robert+Bringe%2C+Esteban+Aucejo%2C+and+Jane+Cooley+Fruehwirth%2E+2020%2E+Using+global+observation+protocols+to+inform+research+on+teaching+effectiveness+and+school+improvement%3A+Strengths+and+emerg)
23. M. A. Kraft, D. Blazar, and D. Hogan. 2018. The effect of teacher coaching on instruction and achievement: A meta-analysis of the causal evidence. Review of Educational Research, 88(4):547–588. [find](https://scholar.google.com/scholar?q=M%2E+A%2E+Kraft%2C+D%2E+Blazar%2C+and+D%2E+Hogan%2E+2018%2E+The+effect+of+teacher+coaching+on+instruction+and+achievement%3A+A+meta%2Danalysis+of+the+causal+evidence%2E+Review+of+Educational+Research%2C+88%284%29%3A547%E2%80%93588%2E)
24. Matthew A Kraft and David Blazar. 2018. Taking teacher coaching to scale: Can personalized training become standard practice? Education Next, 18(4):68– 75. [find](https://scholar.google.com/scholar?q=Matthew+A+Kraft+and+David+Blazar%2E+2018%2E+Taking+teacher+coaching+to+scale%3A+Can+personalized+training+become+standard+practice%3F+Education+Next%2C+18%284%29%3A68%E2%80%93+75%2E)
25. Taja Kuzman, Igor Mozetic, and Nikola Ljubešic. 2023. [Chatgpt: Beginning of an end of manual linguistic data annotation? use case of automatic genre identification](https://md.research.elamur.ai/free/en/papers/kuzman-2023-chatgpt-beginning-end-manual-linguistic/). arXiv e-prints, pages arXiv–2303.
26. Yiheng Liu, Tianle Han, Siyuan Ma, Jiayue Zhang, Yuanyuan Yang, Jiaming Tian, Hao He, Antong Li, Mengshen He, Zhengliang Liu, et al. 2023. [Summary of chatgpt/gpt-4 research and perspective towards the future of large language models](https://md.research.elamur.ai/free/en/papers/liu-2023-summary-chatgpt-related-research-perspective/). arXiv preprint arXiv:2304.01852.
27. Felipe Martinez, Sandy Taut, and Kevin Schaaf. 2016. Classroom observation for evaluating and improving teaching: An international perspective. Studies in Educational Evaluation, 49:15–29. [find](https://scholar.google.com/scholar?q=Felipe+Martinez%2C+Sandy+Taut%2C+and+Kevin+Schaaf%2E+2016%2E+Classroom+observation+for+evaluating+and+improving+teaching%3A+An+international+perspective%2E+Studies+in+Educational+Evaluation%2C+49%3A15%E2%80%9329%2E)
28. Jacob Menick, Maja Trebacz, Vladimir Mikulik, John Aslanides, Francis Song, Martin Chadwick, Mia Glaese, Susannah Young, Lucy Campbell-Gillingham, Geoffrey Irving, et al. 2022. [Teaching language models to support answers with verified quotes](https://md.research.elamur.ai/free/en/papers/menick-2022-teaching-language-models-support-answers/). arXiv preprint arXiv:2203.11147.
29. Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, Xu Jiang, Karl Cobbe, Tyna Eloundou, Gretchen Krueger, Kevin Button, Matthew Knight, Benjamin Chess, and John Schulman. 2022. [Webgpt: Browser-assis…](https://md.research.elamur.ai/free/en/papers/nakano-2021-webgpt-browser-assisted-question-answering/)
30. Zachary A. Pardos and Shreya Bhandari. 2023. Learning gain differences between chatgpt and human tutor generated algebra hints. [find](https://scholar.google.com/scholar?q=Zachary+A%2E+Pardos+and+Shreya+Bhandari%2E+2023%2E+Learning+gain+differences+between+chatgpt+and+human+tutor+generated+algebra+hints%2E)
31. Robert C Pianta, Karen M La Paro, and Bridget K Hamre. 2008. Classroom Assessment Scoring System™: Manual K-3. Paul H Brookes Publishing. [find](https://scholar.google.com/scholar?q=Robert+C+Pianta%2C+Karen+M+La+Paro%2C+and+Bridget+K+Hamre%2E+2008%2E+Classroom+Assessment+Scoring+System%E2%84%A2%3A+Manual+K%2D3%2E+Paul+H+Brookes+Publishing%2E)
32. B. Samei, A. M. Olney, S. Kelly, M. Nystrand, S. D’Mello, N. Blanchard, X. Sun, M. Glaus, and A. Graesser. 2014. Domain independent assessment of dialogic properties of classroom discourse. [find](https://scholar.google.com/scholar?q=B%2E+Samei%2C+A%2E+M%2E+Olney%2C+S%2E+Kelly%2C+M%2E+Nystrand%2C+S%2E+D%E2%80%99Mello%2C+N%2E+Blanchard%2C+X%2E+Sun%2C+M%2E+Glaus%2C+and+A%2E+Graesser%2E+2014%2E+Domain+independent+assessment+of+dialogic+properties+of+classroom+discourse%2E)
33. Baruch B Schwarz, Naomi Prusak, Osama Swidan, Adva Livny, Kobi Gal, and Avi Segal. 2018. Orchestrating the emergence of conceptual learning: A case study in a geometry class. International Journal of Computer-Supported Collaborative Learning, 13:189–211. [find](https://scholar.google.com/scholar?q=Baruch+B+Schwarz%2C+Naomi+Prusak%2C+Osama+Swidan%2C+Adva+Livny%2C+Kobi+Gal%2C+and+Avi+Segal%2E+2018%2E+Orchestrating+the+emergence+of+conceptual+learning%3A+A+case+study+in+a+geometry+class%2E+International+Journal+of+)
34. Yen-Ning Su, Chia-Cheng Hsu, Hsin-Chin Chen, Kuo-Kuang Huang, and Yueh-Min Huang. 2014. Developing a sensor-based learning concentration detection system. Engineering Computations, 31(2):216–230. [find](https://scholar.google.com/scholar?q=Yen%2DNing+Su%2C+Chia%2DCheng+Hsu%2C+Hsin%2DChin+Chen%2C+Kuo%2DKuang+Huang%2C+and+Yueh%2DMin+Huang%2E+2014%2E+Developing+a+sensor%2Dbased+learning+concentration+detection+system%2E+Engineering+Computations%2C+31%282%29%3A216%E2%80%93230%2E)
35. A. Suresh, J. Jacobs, V. Lai, C. Tan, W. Ward, J. H. Martin, and T. Sumner. 2021. Using transformers to provide teachers with personalized feedback on their classroom discourse: The talkmoves application. arxiv. Preprint. [find](https://scholar.google.com/scholar?q=A%2E+Suresh%2C+J%2E+Jacobs%2C+V%2E+Lai%2C+C%2E+Tan%2C+W%2E+Ward%2C+J%2E+H%2E+Martin%2C+and+T%2E+Sumner%2E+2021%2E+Using+transformers+to+provide+teachers+with+personalized+feedback+on+their+classroom+discourse%3A+The+talkmoves+applicat)
36. Earl E Thomas, David L Bell, Maureen Spelman, and Jennifer Briody. 2015. The growth of instructional coaching partner conversations in a prek-3rd grade teacher professional development experience. Journal of Adult Education, 44(2):1–6. [find](https://scholar.google.com/scholar?q=Earl+E+Thomas%2C+David+L+Bell%2C+Maureen+Spelman%2C+and+Jennifer+Briody%2E+2015%2E+The+growth+of+instructional+coaching+partner+conversations+in+a+prek%2D3rd+grade+teacher+professional+development+experience%2E+Jou)
37. Walton Family Foundation. 2023. ChatGPT Used by Teachers More Than Students, New Survey from Walton Family Foundation Finds. [find](https://scholar.google.com/scholar?q=Walton+Family+Foundation%2E+2023%2E+ChatGPT+Used+by+Teachers+More+Than+Students%2C+New+Survey+from+Walton+Family+Foundation+Finds%2E)
38. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed Chi, Quoc Le, and Denny Zhou. 2022. [Chain of thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). arXiv preprint arXiv:2201.11903.
39. Ted Wragg. 2011. An introduction to classroom observation (Classic edition). Routledge. [find](https://scholar.google.com/scholar?q=Ted+Wragg%2E+2011%2E+An+introduction+to+classroom+observation+%28Classic+edition%29%2E+Routledge%2E)
40. Example of Task A • Figure 11 for EXPL Consider the following classroom transcript. • Figure 12 for REMED [find](https://scholar.google.com/scholar?q=Example+of+Task+A+%E2%80%A2+Figure+11+for+EXPL+Consider+the+following+classroom+transcript%2E+%E2%80%A2+Figure+12+for+REMED)

*Updated 1 November 2026*