Pengaruh Chatbot Scaffolding Sokratik Berbasis AI terhadap Penalaran Ilmiah Siswa Sekolah Dasar: Kuasi-Eksperimental Model Inkuiri 5E
DOI:
https://doi.org/10.52436/1.jpti.1626Keywords:
chatbot berbasis AI, model inkuiri 5E, penalaran ilmiah, pendidikan dasar, scaffolding SokratikAbstract
Penalaran ilmiah siswa sekolah dasar di Indonesia masih rendah; skor sains PISA 2022 hanya 383 (peringkat 67 dari 81 negara) dengan sekitar 34% siswa mencapai kompetensi minimum, sementara keterbatasan waktu guru menyulitkan pemberian scaffolding dialogis yang adaptif secara individual di kelas besar. Penelitian ini bertujuan menguji efektivitas chatbot Sokratik berbasis AI sebagai instrumen scaffolding dialogis dalam model inkuiri 5E untuk meningkatkan penalaran ilmiah siswa kelas 5 sekolah dasar. Menggunakan desain kuasi-eksperimental pretest-posttest non-equivalent control group pada 60 siswa (30 eksperimen, 30 kontrol) dari dua kelas paralel, intervensi chatbot berbasis aturan (rule-based) diberikan selama enam minggu (12 sesi) pada fase Explore dan Explain; data dianalisis menggunakan ANCOVA dan pengkodean Toulmin's Argument Pattern (TAP). Hasil menunjukkan kelompok eksperimen mengalami peningkatan penalaran ilmiah yang signifikan secara statistik (F(1,57) = 28,45; p < 0,001) dengan ukuran efek besar (?p² = 0,333); 74% episode dialog menghasilkan penjelasan berbasis bukti secara mandiri, dan miskonsepsi persisten berkurang 46%. Temuan ini memberikan bukti empiris bahwa chatbot Sokratik berbasis AI dapat berperan sebagai mediator epistemis yang memperkuat koordinasi teori-bukti sekaligus menawarkan model scaffolding individual yang skalabel bagi kelas besar dengan keterbatasan sumber daya guru.
Downloads
References
OECD, "PISA 2022 Results (Volume I): The State of Learning and Equity in Education," OECD Publishing, Paris, 2023, doi: 10.1787/53f23881-en.
D. Vo and G. Simmie, "Assessing Scientific Inquiry: A Systematic Literature Review of Tasks, Tools and Techniques," Int. J. Sci. Math. Educ., vol. 23, pp. 871–906, 2024, doi: 10.1007/s10763-024-10498-8.
S. Afroogh, A. Akbari, E. Malone, M. Kargar, and H. Alambeigi, "Trust in AI: progress, challenges, and future directions," Humanit. Soc. Sci. Commun., vol. 11, 2024, doi: 10.1057/s41599-024-04044-8.
O. Yeti?ensoy and H. Karaduman, "The effect of AI-powered chatbots in social studies education," Educ. Inf. Technol., vol. 29, pp. 17035–17069, 2024, doi: 10.1007/s10639-024-12485-6.
L. Caño and J. Sanz, "Young Children's Epistemic Operations and Emergent Argumentation in Inquiry-Based Discussions: The Role of Teacher Questioning and Collaborative Interactions," J. Res. Sci. Teach., 2025, doi: 10.1002/tea.70010.
J. Dempere, K. Modugu, A. Hesham, and L. K. Ramasamy, "The impact of ChatGPT on higher education," Front. Educ., vol. 8, 2023, doi: 10.3389/feduc.2023.1206936.
O. De Los Santos et al., "Scientific Thinking Promotes the Development of Critical Thinking in Primary Education," Educ. Sci., 2025, doi: 10.3390/educsci15091174.
G. Bhusari, K. Tawalare, M. Nikumbh, and K. Tawalare, "Development And Psychometric Validation of Questionnaire to Assess Medovaha Srotas Dushti," vol. 11, no. 22, pp. 4929–4938, 2025.
P.-B. Degen and I. Asanov, "Beyond Automation: Socratic AI, Epistemic Agency, and the Implications of the Emergence of Orchestrated Multi-Agent Learning Architectures," ArXiv, abs/2508.05116, 2025, doi: 10.48550/arxiv.2508.05116.
T.-T. Wu et al., "Integrating Computational Thinking Diagnostic Mechanism and Reflective Learning: An Innovative Approach to Enhance Learning Outcomes in Introductory Programming," J. Comput. Assist. Learn., vol. 41, no. 5, e70121, 2025, doi: 10.1111/jcal.70121.
Z. Arkan and M. Bal, "The relationship between school-age students' literacy skills and digital well-being: a systematic review," BMC Psychol., vol. 13, 2025, doi: 10.1186/s40359-025-03573-4.
H. Fakour and M. Imani, "Socratic wisdom in the age of AI: a comparative study of ChatGPT and human tutors in enhancing critical thinking skills," Front. Educ., 2025.
W. Jung, K. Lee, H.-H. Kim, and C. Lim, "How to construct analysis of covariance in clinical trials: ANCOVA with one covariate in a completely randomized design structure," Korean J. Anesthesiol., vol. 78, pp. 315–320, 2025, doi: 10.4097/kja.24820.
M. Küçükaydin and E. Ayaz, "Validation of the Scientific Reasoning Competencies Instrument: Relationships with Epistemological Beliefs and Analytical Thinking," Int. J. Sci. Math. Educ., vol. 23, pp. 343–363, 2024, doi: 10.1007/s10639-024-12485-6.
J. A. S. Muñoz et al., "GenAI as a cognitive mediator: a critical-constructivist inquiry into computational thinking in pre-university education," Front. Educ., 2025.
F. Paillusson and M. Booth, "Embracing Representational Plurality to Bypass Misconceptions in Science Education," Sci. Educ., vol. 34, pp. 1955–1969, 2024, doi: 10.1007/s11191-024-00590-4.
S. Noroozi and H. Karami, "A Rasch-based validation of the University of Tehran English Proficiency Test (UTEPT)," Lang. Test. Asia, vol. 14, pp. 1–18, 2024, doi: 10.1186/s40468-024-00290-4.
Y. Topkaya, Y. Do?an, V. Batdi, and S. Aydin, "Artificial Intelligence Applications in Primary Education: A Quantitatively Complemented Mixed-Meta-Method Study," Sustainability, 2025.
M. Gordon et al., "A scoping review of artificial intelligence in medical education: BEME Guide No. 84," Med. Teach., vol. 46, pp. 446–470, 2024, doi: 10.1080/0142159x.2024.2314198.
L. Kaldaras et al., "Employing technology-enhanced feedback and scaffolding to support the development of deep science understanding using computer simulations," Int. J. STEM Educ., vol. 11, 2024, doi: 10.1186/s40594-024-00490-7.
P. M. Newton and S. Jones, "Education and Training Assessment and Artificial Intelligence. A Pragmatic Guide for Educators," Br. J. Biomed. Sci., vol. 81, 2025.
J. T. E. Richardson, "Eta squared and partial eta squared as measures of effect size in educational research," Educ. Res. Rev., vol. 6, no. 2, pp. 135–147, 2011, doi: 10.1016/j.edurev.2010.12.001.
L. Wu and K. A. Bakar, "Language Scaffolding Strategies Based on Vygotsky's Zone of Proximal Development in Early Reading Education: A Cross-Cultural Comparison," Forum Linguist. Stud., 2025.
K. Tang and G. Cooper, "The Role of Materiality in an Era of Generative Artificial Intelligence," Sci. Educ., vol. 34, pp. 731–746, 2024, doi: 10.1007/s11191-024-00508-0.
I. Pesovski, R. Santos, R. Henriques, and V. Trajkovik, "Generative AI for Customizable Learning Experiences," Sustainability, 2024, doi: 10.3390/su16073034.
Y. Ding, G. Zhu, Q. Bian, and L. Bao, "Analysis of students' conceptual change in learning Newton's third law with an integrated framework of model analysis and knowledge integration," Phys. Rev. Phys. Educ. Res., 2024.
Y. Hou, Q. Xie, N. Zhang, and J. Lv, "Cognitive load classification of mixed reality human computer interaction tasks based on multimodal sensor signals," Sci. Rep., vol. 15, 2025.
J. Crawford, M. Cowling, S. Ashton-Hay, J. Kelder, R. Middleton, and G. Wilson, J. Univ. Teach. Learn. Pract., 2023.
H. Güner and E. Er, "AI in the classroom: Exploring students' interaction with ChatGPT in programming learning," Educ. Inf. Technol., vol. 30, pp. 12681–12707, 2025.
C. Lin, "Developing Workplace Training and Learning: An Extended Cognitive-Load Framework," Hum. Resour. Dev. Q., 2025, doi: 10.1002/hrdq.21567.
N. Mathé and A. S. Christensen, "Show and tell: scaffolding practices in lower secondary social science classrooms," J. Curric. Stud., 2024, doi: 10.1080/00220272.2024.2378315.
M. Nashaat and J. Miller, "Towards Efficient Fine-Tuning of Language Models With Organizational Data for Automated Software Review," IEEE Trans. Softw. Eng., 2024.
C. Osterhaus and S. Koerber, "The personal epistemology of parents predicts the development of scientific reasoning in children aged 6-10 years," Dev. Sci., 2024.
X. Lu, Y. Zhang, S. Wu, and G. Shan, "The impact of randomization techniques on the performance of pre-post design models," BMC Med. Res. Methodol., vol. 25, 2025.
A. Postema et al., "Investigating sources of non-response bias in a population-based seroprevalence study of vaccine-preventable diseases in the Netherlands," BMC Infect. Dis., vol. 24, 2024.
E. Beard, J. Brown, and L. Shahab, "Sample size requirements to evaluate policies in addiction research using interrupted time series analysis (ITS): Tools and guidance," Addiction, 2025.
C. Xu et al., "Few-shot network intrusion detection method based on multi-domain fusion and cross-attention," PLOS One, vol. 20, 2025, doi: 10.1371/journal.pone.0327161.
