Exploring and Comparing Scaffolding Strategies of ChatGPT-3.5 and a Customized GPT for Reading Comprehension
Article Sidebar
Main Article Content
Abstract
This study compares scaffolding strategies generated by ChatGPT-3.5 and a customized GPT in reading comprehension exercises to assist Thai university students in achieving a minimum CEFR B2 level as a requirement for Thai bachelor’s degree programs. A prompt for ChatGPT-3.5 was designed to generate four reading passages, each with five multiple-choice questions. A similar approach was used to configure a customized GPT, also with a prepared file containing four reading passages and five multiple-choice questions. Data were collected based on the responses from both versions when two incorrect and one correct answer were selected respectively for each question. The results revealed that the customized GPT generated more meaningful and diverse scaffolding strategies, whereas ChatGPT-3.5 produced consistent but limited responses focused on specific reading strategies. Furthermore, the study found that some valuable strategies, such as misconception correction and the promotion of critical thinking, were absent in ChatGPT-3.5. While both versions offer educational value, they differ in the depth and range of scaffolds provided. Educators and researchers should carefully consider these differences when integrating generative AI into instructional design. In particular, this study highlights the importance of grounding AI-assisted learning in established pedagogical theories, such as scaffolding, to support core language skills like reading comprehension. As generative AI becomes more common in classrooms, thoughtful implementation and training for both instructors and students will be key to maximizing its potential within the Thai educational context.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Anderson, L. W., & Krathwohl, D. R. (2001). A taxonomy for learning, teaching, and assessing: A revision of Bloom’s taxonomy of educational objectives: Complete edition. Addison Wesley Longman.
Anthony, L. (2022). AntConc (Version 4.2.0) [Computer software]. Waseda University. https://www.laurenceanthony.net/software/AntConc
Bangprapa, M. (2024, January 26). Mandatory English tests for uni students. Bangkok Post. https://www.bangkokpost.com/thailand/general/2730885/mandatory-english-tests-for-uni-students
Barrot, J. S. (2023). ChatGPT as a language learning tool: An emerging technology report. Technology, Knowledge and Learning, 29(2), 1151–1156. https://doi.org/10.1007/s10758-023-09711-4
Cai, L., Msafiri, M. M., & Kangwa, D. (2025). Exploring the impact of integrating AI tools in higher education using the Zone of Proximal Development. Education and Information Technologies, 30(6), 7191–7264. https://doi.org/10.1007/s10639-024-13112-0
Cheung, K. K. C., Pun, J. K. H., & Li, W. (2024). Students’ holistic reading of socio-scientific texts on climate change in a ChatGPT scenario. Research in Science Education, 54(5), 957–976. https://doi.org/10.1007/s11165-024-10177-2
Commission on Higher Education Standards. (2024). Policy for raising the standard of English in higher education institutions. Office of the Permanent Secretary. https://www.ops.go.th/th/ches-downloads/edu-standard/item/9625–2567
Council of Europe. (2020). Common European framework of reference for languages: Learning, teaching, assessment – Companion volume. Council of Europe Publishing. https://rm.coe.int/common-european-framework-of-reference-for-languages-learning-teaching/16809ea0d4
Dhillon, P. S., Molaei, S., Li, J., Golub, M., Zheng, S., & Robert, L. P. (2024). Shaping human-AI collaboration: Varied scaffolding levels in co-writing with language models. Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, Article 1044. https://doi.org/10.1145/3613904.3642134
Dreyer, C., & Nel, C. (2003). Teaching reading strategies and reading comprehension within a technology-enhanced learning environment. System, 31(3), 349–365. https://doi.org/10.1016/S0346-251X(03)00047-2
Essel, H. B., Vlachopoulos, D., Essuman, A. B., & Amankwa, J. O. (2024). ChatGPT effects on cognitive skills of undergraduate students: Receiving instant responses from AI-based conversational large language models (LLMs). Computers and Education: Artificial Intelligence, 6, Article 100198. https://doi.org/10.1016/j.caeai.2023.100198
Ghafouri, M. (2024). ChatGPT: The catalyst for teacher-student rapport and grit development in L2 class. System, 120, Article 103209. https://doi.org/10.1016/j.system.2023.103209
Gonulal, T., & Loewen, S. (2018). Scaffolding technique. In The TESOL encyclopedia of English language teaching. https://doi.org/10.1002/9781118784235.eelt0180
Hattan, C., & Alexander, P. (2018). Scaffolding reading comprehension for competent readers. Literacy Research: Theory, Method, and Practice, 67(1), 296–309. https://doi.org/10.1177/2381336918786885
Jitpaisarnwattana, N. (2024). Idea sharing: Using ChatGPT for diagnostic writing assessment. PASAA, 69, 561–574.
https://doi.org/10.58837/CHULA.PASAA.69.18
Karakoç, A. I., Ruegg, R., & Gu, P. (2022). Beyond comprehension: Reading requirements in first-year undergraduate courses. Journal of English for Academic Purposes, 55, Article 101071. https://doi.org/10.1016/j.jeap.2021.101071
Kohnke, L., Moorhouse, B. L., & Zou, D. (2023). ChatGPT for language teaching and learning. RELC Journal, 54(2), 537–550. https://doi.org/10.1177/00336882231162868
Lam, Y. Y., Chu, S. K. W., Ong, E. L. C., Suen, W. W. L., Xu, L., Lam, L. C. L., & Wong, S. M. Y. (2024). Comparative study of GenAI (ChatGPT) vs. human in generating multiple choice questions based on the PIRLS reading assessment framework. Proceedings of the Association for Information Science and Technology, 61(1), 537–540. https://doi.org/10.1002/pra2.1054
Lee, M. L. (2012). A study of the selection of reading strategies among genders by EFL college students. Procedia-Social and Behavioral Sciences, 64, 310–319. https://doi.org/10.1016/j.sbspro.2012.11.037
Li, T., Nath, D., Cheng, Y., Fan, Y., Li, X., Raković, M., Khosravi, H., Swiecki, Z., Tsai, Y. S., & Gašević, D. (2025). Turning real-time analytics into adaptive scaffolds for self-regulated learning using generative artificial intelligence. In N. Dowell, S. Joksimovic, M. Scheffel, & G. Siemens (Eds.), Proceedings of the 15th International Learning Analytics and Knowledge Conference (pp. 667–679). Association for Computing Machinery.
https://doi.org/10.1145/3706468.3706559
Lim, L., Bannert, M., van der Graaf, J., Fan, Y., Rakovic, M., Singh, S., Molenaar, I., & Gašević, D. (2024). How do students learn with real‐time personalized scaffolds? British Journal of Educational Technology, 55(4), 1309–1327. https://doi.org/10.1111/bjet.13414
Lin, Z., & Chen, H. (2024). Investigating the capability of ChatGPT for generating multiple-choice reading comprehension items. System, 123, Article 103344. https://doi.org/10.1016/j.system.2024.103344
Melero, J., Hernández-Leo, D., & Blat, J. (2012). A review of constructivist learning methods with supporting tooling in ICT higher education: Defining different types of scaffolding. Journal of Universal Computer Science, 18(16), 2334–2360. http://dx.doi.org/10.3217/jucs-018-16-2334
OpenAI. (2023, November 3). ChatGPT — Release notes. https://help.openai.com/en/articles/6825453-chatgptrelease-notes OpenAI. (2024). ChatGPT (Apr 27 version) [Large language model]. https://chatgpt.com
Pan, M., Lai, C., & Guo, K. (2025). Effects of GenAI-empowered interactive support on university EFL students’ self-regulated strategy use and engagement in reading. The Internet and Higher Education, 65, Article 100991. https://doi.org/10.1016/j.iheduc.2024.100991
Pojanapunya, P., & Watson Todd, R. (2018). Log-likelihood and odds ratio: Keyness statistics for different purposes of keyword analysis. Corpus Linguistics and Linguistic Theory, 14(1), 133–167. https://doi.org/10.1515/cllt-2015-0030
Reiser, B. J. (2004). Scaffolding complex learning: The mechanisms of structuring and problematizing student work. Journal of the Learning Sciences, 13(3), 273–304.
Saengboon, S. (2019). Shadow education in Thailand: A case study of Thai English tutors’ perspectives towards the roles of private supplementary tutoring in improving English language skills. LEARN Journal: Language Education and Acquisition Research Network, 12(1), 38–54. https://so04.tci-thaijo.org/index.php/LEARN/article/view/168575
Sanmuang, K., Boonmoh, A., Inree, T., & Kha-angku, P. (2024). Exploring ChatGPT prompts used by Thai EFL elderly students to promote community products and their attitudes towards ChatGPT: Case study of Sakon Nakhon School for the elderly, Thailand. Kasetsart Journal of Social Sciences, 45(4), 1269–1278. https://so04.tci-thaijo.org/index.php/kjss/article/view/276995
Sheorey, R., & Mokhtari, K. (2001). Differences in the metacognitive awareness of reading strategies among native and non-native readers. System, 29(4), 431–449. https://doi.org/10.1016/S0346-251X(01)00039-2
Syarifah, E. F., & Gunawan, W. (2015). Scaffolding in the teaching of writing discussion texts based on SFL genre-based approach. English Review: Journal of English Education, 4(1), 39–53. https://doi.org/10.25134/erjee.v4i1.306
Tantivejakul, N., Chantharasombat, J., & Kongpolphrom, W. (2024). Voices of the future: Exploring students’ views on the use of GenAI in academic and professional PR writing. LEARN Journal: Language Education and Acquisition Research Network, 17(2), 511–537. https://doi.org/10.70730/PVTD8302
Wang, F., Zhou, X., Li, K., Cheung, A. C. K., & Tian, M. (2025). The effects of artificial intelligence-based interactive scaffolding on secondary students’ speaking performance, goal setting, self-evaluation, and motivation in informal digital learning of English. Interactive Learning Environments, 33(7), 4633–4652. https://doi.org/10.1080/10494820.2025.2470319
Wang, T., Zheng, J., Tan, C., & Lajoie, S. P. (2023). Computer‐based scaffoldings influence students’ metacognitive monitoring and problem‐solving efficiency in an intelligent tutoring system. Journal of Computer Assisted Learning, 39(5), 1652–1665. https://doi.org/10.1111/jcal.12824
Watson Todd, R. (2014). Support adaptive testing: The effects of scaffolds in computer-based tests. Computer-Assisted Language Learning Electronic Journal, 15(1), 1–20. https://callej.org/index.php/journal/article/view/211
Watson Todd, R. (2019). How is English assessed at Thai schools? THAITESOL Journal, 32(1), 1–15. https://so05.tci-thaijo.org/index.php/thaitesoljournal/article/view/193942
Wiliam, D. (2011). What is assessment for learning? Studies in Educational Evaluation, 37(1), 3–14. https://doi.org/10.1016/j.stueduc.2011.03.001
Wilson, K., & Devereux, L. (2014). Scaffolding theory: High challenge, high support in Academic Language and Learning (ALL) contexts. Journal of Academic Language and Learning, 8(3), A91–A100. https://journal.aall.org.au/index.php/jall/article/view/353
Yukselir, C. (2014). An investigation into the reading strategy use of EFL prep-class students. Procedia - Social and Behavioral Sciences, 158, 65–72. https://doi.org/10.1016/j.sbspro.2014.12.034
Yussof, Y. M., Jamian, A. R., Roslan, S., Hamzah, Z. A. Z., & Kabilan, M. K. (2012). Enhancing reading comprehension through cognitive and graphic strategies: A constructivism approach. Procedia-Social and Behavioral Sciences, 64, 151–160. https://doi.org/10.1016/j.sbspro.2012.11.018
