Just Accepted Manuscripts
Research Articles

Implementing ChatGPT as Tutor, Tutee, and Tool in Physics and Chemistry

PDF (Just Accepted)
  • Chitnarong Sirisathitkul,
  • Nawee Jaroonchokanan
Chitnarong Sirisathitkul
School of Science, Walailak University, Nakhon Si Thammarat, Thailand
Bio
Nawee Jaroonchokanan
School of Science, Walailak University, Nakhon Si Thammarat, Thailand
Bio
DOI: https://doi.org/10.36253/Substantia-2808

Published 2024-09-23

Keywords

  • Artificial intelligence,
  • ChatGPT,
  • Physics,
  • Chemistry,
  • Science education

How to Cite

Sirisathitkul, C., & Jaroonchokanan, N. (2024). Implementing ChatGPT as Tutor, Tutee, and Tool in Physics and Chemistry. Substantia. https://doi.org/10.36253/Substantia-2808

Copyright (c) 2024 Chitnarong Sirisathitkul, Nawee Jaroonchokanan

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Crossref
Scopus
Google Scholar
Europe PMC

Abstract

In the age of modern technology, generative artificial intelligience-powered chatbots offer a variety of uses for different purposes. Undoubtedly, ChatGPT is one of the most widely used chatbots in science education. In this paper, we review the implementations of chatbots, focusing particularly in teaching and learning physics and chemistry. Their roles in the context of science education are classified as tutee, tutor, and tool. We found the development of ChatGPT to be quite impressive. As a tutee, the latest version of ChatGPT is a fast learner, capable of passing standard tests and providing accurate scientific answers using approaches like Chain-of-Thought and Socratic-style dialogue. As a tutor, it can help students learn through classroom teaching techniques such as scaffolding and enhance critical thinking by acting as a personal tutor that offers instantaneous feedback. As a tool, ChatGPT can assist in reviewing students’ handwritten homework, drafting scientific writing, and generating code for science programming. Although ChatGPT offers many benefits, it can sometimes provide inaccurate information, necessitating human oversight in science education. Importantly, students should be taught to critically assess the responses provided by ChatGPT and understand its ethical use to ensure effective utilization.

PDF (Just Accepted)

References

  1. M. Ivanova, G. Grosseck, C. Holotescu, Unveiling insights: A bibliometric analysis of artificial intelligence in teaching. Informatics 2024, 11, 10. DOI 10.3390/informatics11010010
  2. M. R. Zheltukhina, O. V. Sergeeva, A. R. Masalimova, R. L. Budkevich, N. N. Kosarenko, G. V. Nesterov, A bibliometric analysis of publications on ChatGPT in education: Research patterns and topics. Online J. Commun. Media Technol. 2024, 14(1), e202405. DOI 10.30935/ojcmt/14103
  3. E. Dimitriadou, A. Lanitis, A critical evaluation, challenges, and future perspectives of using artificial intelligence and emerging technologies in smart classrooms. Smart Learn. Environ. 2024 DOI 10.1186/s40561-023-00231-3
  4. F. Jia, D. Sun, C.-K. Looi, Artificial intelligence in science education (2013–2023): Research trends in ten years. J. Sci. Educ. Technol. 2024, 33, 94-117. DOI 10.1007/s10956-023-10077-6
  5. P. Lo Nostro, Artificial intelligence vs. Natural stupidity. Substantia 2023, 7, 5-6, DOI 10.36253/Substantia-2250
  6. L. S. Balhorn, J. M. Weber, S. Buijsman, J. R. Hildebrandt, M. Ziefle, A. M. Schweidtmann, Empirical assessment of ChatGPT’s answering capabilities in natural science and engineering. Sci. Rep. 2024, 14, 4998. DOI 10.1038/s41598-024-54936-7
  7. C. K. Lo, What is the impact of ChatGPT on education? A rapid review of the literature. Educ. Sci. 2023, 13, 410. DOI 10.3390/educsci13040410
  8. J. Weizenbaum, Eliza—a computer program for the study of natural language communication between man and machine. Commun. ACM 1966, 9, 36-45.
  9. E. Adamopoulou, L. Moussiades, Chatbots: History, technology, and applications. Machine Learn. Appl. 2020, 2, 100006. DOI 10.1016/j.mlwa.2020.100006
  10. S. Schobel, A. Schmitt, D. Benner, M. Saqr, A. Janson, J. M. Leimeister, Charting the evolution and future of conversational agents: A research agenda along five waves and new frontiers. Inform. Sys. Front. 2024, online first. DOI 10.1007/s10796-023-10375-9
  11. J. Wang, ChatGPT: A test drive. Am. J. Phys. 2023, 91, 255-256. DOI 10.1119/5.0145897
  12. G. Kortemeyer, Could an artificial-intelligence agent pass an introductory physics course? Phys. Rev. Phys. Educ. Res. 2023, 19, 010132. DOI 10.1103/PhysRevPhysEducRes.19.020163
  13. D. Hestenes, I. Halloun, Interpreting the force concept inventory: A response to Huffman and Heller. Phys. Teach. 1995, 33. 502-502. DOI 10.1119/1.2344278
  14. W. Yeadon, O. Inyang, A. Mizouri, A. Peach, C. Testrow, The death of the short-form physics essay in the coming AI revolution. Phys. Educ. 2023, 58, 035027. DOI 10.1088/1361-6552/acc5cf
  15. V. López, M. Rezende, Challenging ChatGPT with different types of physics education questions. Phys. Teach. 2024, 62. 290-294. DOI 10.1119/5.0160160
  16. D. Tong, Y. Tao, K. Zhang, X. Dong, Y. Hu, S. Pan, Investigating ChatGPT-4’s performance in solving physics problems and its potential implications for education. Asia Pac. Educ. Rev. 2024, DOI 10.1007/s12564-023-09913-6
  17. D. Maloney, T. O’Kuma, C. Hieggelke, A. Heuvelen, Surveying students' conceptual knowledge of electricity & magnetism. Am. J. Phys. 2001, 69, S12-S23. DOI 10.1119/1.1371296.
  18. H. Xing, W. Gong, P. Wang, Y. Zhai, Y. Zhao, The measuring instrument of primitive physics problem for junior high school students: Compilation and research. J Baltic Sci Educ. 2022, 21, 305-324. DOI 10.33225/jbse/22.21.305
  19. C. West, AI and the FCI: Can ChatGPT project an understanding of introductory physics? Arxiv 2023, DOI 10.48550/arXiv.2303.01067
  20. T. Kumar, M. A. Kats; ChatGPT-4 with Code Interpreter can be used to solve introductory college-level vector calculus and electromagnetism problems. Am. J. Phys. 2023, 91, 955-956. DOI 10.1119/5.0182627
  21. W. Yeadon, D. P. Halliday, Exploring Durham University physics exams with large language models. Arxiv 2023, DOI 10.48550/arXiv.2306.15609
  22. G. Polverini, B. Gregorcic, Performance of ChatGPT on the test of understanding graphs in kinematics. Phys. Rev. Phys. Educ. Res. 2024, 20, 010109. DOI 10.1103/PhysRevPhysEducRes.20.010109
  23. G. Polverini, B. Gregorcic, How understanding large language models can inform the use of ChatGPT in physics education. Eur. J. Phys. 2024, 45, 025701. DOI 10.1088/1361-6404/ad1420
  24. Y. Liang, D. Zou, H. Xie, L. Wang, Exploring the potential of using ChatGPT in physics education. Smart Learn. Environ. 2024, 10, 52. DOI 10.1186/s40561-023-00273-7
  25. P. Bitzenbauer, ChatGPT in physics education: A pilot study on easy-to-implement activities. Contemp. Educ. Technol. 2023, 15, ep430. DOI 10.30935/cedtech/13176
  26. S. Alneyadi, Y. Wardat, ChatGPT: Revolutionizing student achievement in the electronic magnetism unit for eleventh-grade students in Emirates schools. Contemp. Educ. Technol. 2023, 15. 448-1309. DOI 10.30935/cedtech/13417
  27. M. Dahlkemper, S. Lahme, P. Klein, How do physics students evaluate artificial intelligence responses on comprehension questions? A study on the perceived scientific accuracy and linguistic quality of ChatGPT. Phys. Rev. Phys. Educ. Res. 2023, 19, 010142. DOI 10.1103/PhysRevPhysEducRes.19.010142.
  28. L. Ding, T. Li, S. Jiang, A. Gapud, Students’ perceptions of using ChatGPT in a physics class as a virtual tutor. Int. J. Educ. Technol. Higher Educ. 2023, 20, 63. DOI 10.1186/s41239-023-00434-1
  29. B. Gregorcic, A.-M. Pendrill, ChatGPT and the frustrated Socrates. Phys. Educ. 2023, 58. 035021. DOI 10.1088/1361-6552/acc299
  30. B. Gregorcic, G. Polverini, A. Sarlah, ChatGPT as a tool for honing teachers’ Socratic dialogue skills. Phys. Educ. 2024, 59. 045005. DOI 10.1088/1361-6552/ad3d21
  31. G. Kortemeyer, Toward AI grading of student problem solutions in introductory physics: A feasibility study. Phys. Rev. Phys. Educ. Res. 2023, 19, 020163. DOI 10.1103/PhysRevPhysEducRes.19.010132
  32. T. M. Clark, E. Anderson, N. M. Dickson-Karn, C. Soltanirad, N. Tafini, Comparing the performance of college chemistry students with ChatGPT for calculations involving acids and bases. J. Chem. Educ. 2023, 100, 3934-3944. DOI 10.1021/acs.jchemed.3c00500
  33. A. J. Leon, D. Vidhani, ChatGPT needs a chemistry tutor too. J. Chem. Educ. 2023, 100, 3859-3865. DOI 10.1021/acs.jchemed.3c00288
  34. S. Fergus, M. Botha, M. Ostovar, Evaluating academic answers generated using ChatGPT. J. Chem. Educ. 2023, 100,1672-1675. DOI 10.1021/acs.jchemed.3c00087
  35. T. M. Clark, Investigating the use of an artificial intelligence chatbot with general chemistry exam question. J. Chem. Educ. 2023, 100, 1905-1916. DOI 10.1021/acs.jchemed.3c00027
  36. C. M. C. Nascimento, A. S. Pimentel, Do large language models understand chemistry? A conversation with ChatGPT. J. Chem. Inform. Model. 2023, 63, 1649-1655. DOI 10.1021/acs.jcim.3c00285
  37. W. Daher, H. Diab, A. Rayan, Artificial intelligence generative tools and conceptual knowledge in problem solving in chemistry. Information 2023, 14, 409. DOI 10.3390/info14070409
  38. E. A. Alasadi, C. R. Baiz, Generative AI in education and research: Opportunities, concerns, and solutions. J. Chem. Educ. 2023, 100, 2965-2971. DOI 10.1021/acs.jchemed.3c00323
  39. Y. Guo, D. Lee, Leveraging ChatGPT for enhancing critical thinking skills. J. Chem. Educ. 2023, 100, 4876-4883. DOI 10.1021/acs.jchemed.3c00505
  40. B. Exintaris, N. Karunaratne, E. Yuriev, Metacognition and critical thinking: Using ChatGPT-generated responses as prompts for critique in a problem-solving workshop (SMARTCHEMPer). J. Chem. Educ. 2023, 100, 2972-2980. DOI 10.1021/acs.jchemed.3c00481
  41. J. K. West, J. L. Franz, S. M. Hein, H. R. Leverentz-Culp, J. F. Mauser, E. F. Ruff, J. M. Zemke, An analysis of ai-generated laboratory reports across the chemistry curriculum and student perceptions of ChatGPT. J. Chem. Educ. 2023, 100, 4351-4359. DOI 10.1021/acs.jchemed.3c00581
  42. A. J. Rojas, An investigation into ChatGPT’s application for a scientific writing assignment. J. Chem. Educ. 2024, DOI 10.1021/acs.jchemed.4c00034
  43. M. J. Clark, M. Reynders, T. A. Holme, Students’ experience of a ChatGPT enabled final examina non majors chemistry course. J. Chem. Educ. 2024, DOI 10.1021/acs.jchemed.4c00161
  44. H. Desaire, A. E. Chua, M.-G. Kim, D. Hua, Accurately detecting AI text when ChatGPT is told to write like a chemist. Cell Rep. Phys. Sci. 2023, 4, 101672. DOI 10.1016/j.xcrp.2023.10167
  45. J. L. Araujo, I. Saude, Can ChatGPT enhance chemistry laboratory teaching? using prompt engineering to enable AI in generating laboratory activities. J. Chem. Educ. 2024, DOI 10.1021/acs.jchemed.3c00745
  46. J. Scoggin, K. C. Smith, Enabling general chemistry students to take part in experimental design activities. Chem. Educ. Res. Pract. 2023, 24, 1229. DOI 10.1039/d3rp00088e
  47. Z. Zheng, O. Zhang, C. Borgs, J. T. Chayes, O. M. Yaghi, ChatGPT chemistry assistant for text mining and the prediction of MOF synthesis. J. Am. Chem. Soc. 2023, 145, 18048-18062. DOI 10.1021/jacs.3c05819
  48. B. Mahjour, J. Hoffstadt, T. Cernak, Designing chemical reaction arrays using Phactor and ChatGPT. Org. Process Res. Dev. 2023, 27, 1510-1516. DOI 10.1021/acs.oprd.3c00186
  49. Z. Y. Kong, V. S. K. Adi, J. Sunarso, J. G. Segovia-Hernandez, Complementary role of large language models in educating undergraduate design of distillation column: Methodology development. Digit. Chem. Eng. 2023, 9, 100126. DOI 10.1016/j.dche.2023.100126
  50. T. Hasrod, Y. B. Nuapia, H. Tutu, ChatGPT helped me build a chemistry App, and here’s how you can make one also. J. Chem. Educ. 2024, 101, 653-660. DOI 10.1021/acs.jchemed.3c01170
  51. R. Dos Santos, Enhancing physics learning with ChatGPT, Bing Chat, and Bard as agents-to-think-with: A comparative case study. arXiv 2023, DOI 10.48550/arXiv.2306.00724
  52. S. Nikolic, C. Sandison, R. Haque, S. Daniel, S. Grundy, M. Belkina, S. Lyden, G. M. Hassan, P. Neal. ChatGPT, Copilot, Gemini, SciSpace and Wolfram versus higher education assessments: an updated multi-institutional study of the academic integrity impacts of Generative Artificial Intelligence (GenAI) on assessment, teaching and learning in engineering. Australasian J. Eng. Educ. 2024, online first. DOI 10.1080/22054952.2024.2372154.
  53. F. M. Watts, A. J. Dood, G. V. Shultz, J.-M. G. Rodriguez, Comparing student and generative artificial intelligence chatbot responses to organic chemistry writing-to-learn assignments. J. Chem. Educ. 2023, 100, 3806-3817. DOI 10.1021/acs.jchemed.3c00664
  54. K. Hallal, R. Hamdan, S. Tlais, Exploring the potential of AI-Chatbots in organic chemistry: An assessment of ChatGPT and Bard. Comput. Educ.: Artif. Intel. 2023, 5, 100170. DOI 10.1016/j.caeai.2023.100170
  55. B. Leite, Generative Artificial Intelligence in chemistry teaching: ChatGPT, Gemini, and Copilot’s content responses. J. Appl. Learn. Teach. 2024, 7(2), 1-15. DOI 10.37074/jalt.2024.7.2.13
  56. W. J. D. Nascimento Jr, C. Morais, G. Girotto Jr, Enhancing AI Responses in Chemistry: Integrating Text Generation, Image Creation, and Image Interpretation through Different Levels of Prompts. J. Chem. Educ. 2024, 101, 3767-3779. DOI 10.1021/acs.jchemed.4c00230
  57. N. Rana, N. Katoch, AI for biophysical phenomena: A comparative study of ChatGPT and Gemini in explaining liquid–liquid phase separation. Appl. Sci. 2024, 14, 5065. DOI 10.3390/app14125065
  58. G. Rossettini, L. Rodeghiero, F. Corradi, C. Cook, P. Pillastrini, A. Turolla, G. Castellini, S. Chiappinotto, S. Gianola, A. Palese, Comparative accuracy of ChatGPT-4, Microsoft Copilot and Google Gemini in the Italian entrance test for healthcare sciences degrees: a cross-sectional study. BMC Med. Educ. 2024, 24, 694. DOI 10.1186/s12909-024-05630-9
  59. A. Meyer, A. Soleman, J. Riese, T. Streichert, Comparison of ChatGPT, Gemini, and Le Chat with physician interpretations of medical laboratory questions from an online health forum. Clin. Chem. Lab. Med. 2024, online first. DOI 10.1515/cclm-2024-0246
  60. S. Saeedi, M. Aghajanzadeh, Investigating the role of artificial intelligence in predicting perceived dysphonia level. Eur. Arch. Otorhinolaryngol. 2024, online first. DOI 10.1007/s00405-024-08868-7
  61. E. Kaba, H. M. Bülbül, G. Burakgazi, A. T. Varlık, N. Hürsoy, M. Solak, S. Tabakoğlu, F. B. Çeliker. Large language models on magnetic resonance imaging safety-related questions: accuracy of ChatGPT-3.5, ChatGPT-4, Gemini, and Perplexity. Curr. Res. MRI 2024, 3, 16-19. DOI 10.5152/CurrResMRI.2024.24095
  62. M. Shukla, I. Goyal, B. Gupta, J. Sharma, A comparative study of ChatGPT, Gemini, and Perplexity. Int. J. Innov. Res. Comput. Sci. Technol. 2024, 12(4), 10-15. DOI 10.55524/ijircst.2024.12.4.2
  63. C. Sirisathitkul, Slow writing with ChatGPT: Turning the hype into a right way forward. Postdigit. Sci. Educ. 2024, 6, 431-438. DOI 10.1007/s42438-023-00441-5
  64. A. Brailas, Postdigital duoethnography: An inquiry into human artificial intelligence synergies. Postdigit. Sci. Educ. 2024, 6, 486-515. DOI 10.1007/s42438-024-00455-7
  65. F. F.-H. Nah, R. Zheng, J. Cai, K. Siau, L. Chen, Generative AI and ChatGPT: Applications, challenges, and AI-human collaboration, J. Inform. Technol. Case Appl. Res. 2023, 25, 277-304. DOI 10.1080/15228053.2023.2233814
  66. T. Adiguzel, M. H. Kaya, F. K. Cansu, Revolutionizing education with AI: Exploring the transformative potential of ChatGPT. Contemp. Educ. Technol. 2023, 15, ep429. DOI 10.30935/cedtech/13152
  67. H. Crompton, D. Burke, The educational affordances and challenges of ChatGPT: State of the field. TechTrends 2024, 68, 380-392. DOI 10.1007/s11528-024-00939-0
  68. A. O. Ifelebuegu, P. Kulume, P. Cherukut, Chatbots and AI in Education (AIEd) tools: The good, the bad, and the ugly. J. Appl. Learn. Teach. 2023, 6, 332-345. DOI 10.37074/jalt.2023.6.2.29
  69. A. Jobin, M. Ienca, E. Vayena, The global landscape of AI ethics guidelines. Nature Machine Intell. 2019, 1, 389-399. DOI 10.1038/s42256-019-0088-2
  70. T. Petricini, What would Aristotle do? Navigating generative artificial intelligence in higher education. Postdigit. Sci. Educ. 2024, 6, 439-445. DOI 10.1007/s42438-024-00463-7