The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Facilitating Student Learning With a Chatbot in an Online Math Learning Platform
Abstract
Chatbots represent a promising technology for engaging students in math learning. Guided by Jerome Bruner’s constructivism and Lev Vygotsky’s Zone of Proximal Development, we designed and developed a chatbot that incorporates scaffolding strategies and social-emotional considerations, and we integrated it into ASSISTments, an online math learning platform. We conducted an experimental study to examine the influence of learning math with the chatbot compared to traditional learning with hints. This study involved 85 middle and high school students from three diverse school settings in the United States. The results revealed no significant differences in students' math learning performance and perceived helpfulness and interest between the chatbot and traditional hints conditions. However, students in the chatbot condition displayed significantly lower confidence in solving a similar problem after the intervention, likely due to the removal of the high level of support provided by the chatbot. Despite this, students’ open responses indicated that a significantly higher number of students had positive attitudes towards chatbots. They appreciated the chatting feature, breaking down a problem into steps, and real-time support. The study concludes with a discussion of the findings and implications for chatbot designers and developers and presents avenues for future research and practice in chatbot-assisted learning. In support of Open Science, this study has been preregistered and both the data and the analysis code used in this study are publicly available at https://osf.io/am3p8/ .
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hattie, J., & Timperley, H. (2007) · Review of Educational Research · doi:10.3102/003465430298487 · Cited by 12,905
I.—COMPUTING MACHINERY AND INTELLIGENCE
TURING, A. M. (1950) · Mind · doi:10.1093/mind/lix.236.433 · Cited by 10,290 · cited 1×
“Key milestones, such as the introduction of the Turing Test by Turing (1950) as a foundational AI evaluation method, and the development of ELIZA by Weizenbaum (1966) as a pioneering natural language processing program, signi fi cantly shaped the chatbot landscape.”
MethodKirschner, P. A., Sweller, J., & Clark, R. E. (2006) · Educational Psychologist · doi:10.1207/s15326985ep4102_1 · Cited by 7,776 · cited 1×
“Kirschner et al. (2006) noted that minimal guidance during instruction can often be ineffective.”
BackgroundShute, V. J. (2008) · Review of Educational Research · doi:10.3102/0034654307313795 · Cited by 4,631
ELIZA—a computer program for the study of natural language communication between man and machine
Weizenbaum, J. (1966) · Communications of the ACM · doi:10.1145/365153.365168 · Cited by 4,452
Pekrun, R., Goetz, T., Titz, W., & Perry, R. P. (2002) · Educational Psychologist · doi:10.1207/s15326985ep3702_4 · Cited by 3,931
The 2 Sigma Problem: The Search for Methods of Group Instruction as Effective as One-to-One Tutoring
BLOOM, B. S. (1984) · Educational Researcher · doi:10.3102/0013189x013006004 · Cited by 2,734 · cited 1×
“In the realm of education, providing effective support to students is crucial for improving their learning experiences and outcomes (Bloom, 1984).”
BackgroundEffectiveness of Intelligent Tutoring Systems: A Meta-Analytic Review
Kulik, J. A., & Fletcher, J. D. (2016) · Review of Educational Research · doi:10.3102/0034654315581420 · Cited by 930 · cited 1×
“The lack of immediate improvement in math performance aligns with Bower ’ s Technology-Mediated Learning Theory (2019) and insights from both Kulik and Fletcher (2016) and Pane et al. (2017), which suggest that the effects of technology on learning outcomes might not manifest immediately and may…”
BackgroundBALFANZ, R., HERZOG, L., & MAC IVER, D. J. (2007) · Educational Psychologist · doi:10.1080/00461520701621079 · Cited by 804 · cited 1×
“Mathematics serves as a gateway to STEM fi elds and is a signi fi cant predictor of students ’ high school graduation, especially in urban middle schools (Balfanz et al., 2007; Rotermund & Burke, 2021).”
BackgroundDo AI chatbots improve students learning outcomes? Evidence from a meta‐analysis
Wu, R., & Yu, Z. (2024) · British Journal of Educational Technology · doi:10.1111/bjet.13334 · Cited by 576 · cited 1×
“A meta-analysis of 24 randomized studies found chatbots had a large overall effect on students ’ learning outcomes including learning performance, learning motivation, learning self-ef fi cacy, learning interest, and perceived value of learning (Wu & Yu, 2023).”
Method
Research works printed but not linked: 28
- 10.1080/15391523.2023.2255698 · DOI
- 10.1007/978-1-4614-3185-5_39 · DOI
- Bii P. (2013). Chatbot technology: A possible means of unlocking student potential to learn how to learn. Educational Research, 4(2), 218–221.
- 10.1111/bjet.12771 · DOI
- Bruner J. S. (1961). The act of discovery. Harvard Educational Review, 31(1), 21–32.
- 10.3102/00028312019002237 · DOI · Paper page
- Creswell J. W., Creswell J. D. (2017). Research design: Qualitative, quantitative, and mixed methods approaches. Sage publications.
- 10.1002/wics.1524 · DOI
- Goleman D. (2005). Emotional intelligence: Why it can matter more than IQ. Random House Publishing Group.
- 10.3758/BF03195563 · DOI
- 10.1016/S1389-0417(99)00005-4 · DOI
- Grossman J. Lin Z. Sheng H. Wei J. T. Z. Williams J. J. Goel S. (2019). MathBot: Transforming online resources for learning math into conversational interactions. AAAI 2019 story-enabled intelligence. https://logical.ai/story-enabled-intelligence/papers/mathbot.pdf
- Hattie J. (2009). Visible learning: A synthesis of over 800 meta-analyses relating to achievement. Routledge.
- Holmes W., Bialik M., Fadel C. (2019). Artificial intelligence in education: Promises and implications for teaching and learning. The Center for Curriculum Redesign.
- 10.1111/jcal.12610 · DOI · Paper page
- 10.3102/0013189X20965918 · DOI · Paper page
- Mauldin M. L. (1994). CHATTERBOTs, TINYMUDs, and the turing test: Entering the loebner prize competition. AAAI, 94, 16–21.
- 10.1037/0003-066X.59.1.14 · DOI · Paper page
- OpenAI. (2023). GPT-4 technical report (Report No. arXiv:2303.08774). arXiv. https://arxiv.org/pdf/2303.08774.pdf · arXiv
- 10.1002/pits.20306 · DOI · Paper page
- Ruan S. He J. Ying R. Burkle J. Hakim D. Wang A. Yin Y. Zhou L. Xu Q. AbuHashem A. DietzMurnane G. E. L. Brunskill E. Landay J. A. (2020 June) Supporting children’s math learning with feedback-augmented narrative technology. In Proceedings of the interaction design and children conference (pp. 567–580). https://dl.acm.org/doi/abs/10.1145/3392063.3394400 · DOI
- Sharpe D. (2015). Chi-square test is statistically significant: Now what? Practical Assessment, Research and Evaluation, 20(8), 1–10.
- 10.1207/s15327809jls0302_1 · DOI
- Sonkar S. Liu L. Mallick D. B. Baraniuk R. G. (2023). CLASS meet SPOCK: An education tutoring chatbot based on learning science principles (Report No. arXiv:2305.13272). arXiv. https://arxiv.org/pdf/2305.13272v1.pdf · arXiv
- Vygotsky L. S., Cole M. (1978). Mind in society: Development of higher psychological processes. Harvard University Press.
- 10.1007/978-1-4020-6710-5_13 · DOI
- Woolf B. P. (2010). Building intelligent interactive tutors: Student-centered strategies for revolutionizing e-learning. Morgan Kaufmann.
- 10.1007/s10639-023-11805-6 · DOI
Cited by
Sorted by citations
Opportunities and challenges of using generative AI to personalize educational assessment
Arslan, B., Lehman, B., Tenison, C., Sparks, J. R., López, A. A., Gu, L., & Zapata-Rivera, D. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1460651 · Cited by 52
Exploring ChatGPT ‐Facilitated Scaffolding in Undergraduates' Mathematical Problem Solving
Zhou, R., He, X., Fan, Q., Li, Y., Li, Y., Xiao, X., & Fang, J. (2025) · Journal of Computer Assisted Learning · doi:10.1111/jcal.70077 · Cited by 15
Metadata
- Authors
- Cheng, L., Croteau, E., Baral, S., Heffernan, C., & Heffernan, N.
- Venue
- Journal of Educational Computing Research
- Publisher
- SAGE Publications
- Published
- 2024-01-31
- Volume
- 62
- Issue
- 4
- Pages
- 687-717
- ISSN
- 0735-6331
- 1541-4140
- Cited by
- 49
- References
- 13
- Language
- en
- Licence
- Funders
- NSF (2118725, 2118904, 1950683, 1917808, 1931523, 1940236, 1917713, 1903304, 1822830, 1759229, 1724889, 1636782 & 1535428)
- IES (R305N210049, R305D210031, R305A170137, R305A170243, R305A180401, R305A120125 & R305R220012)
- GAANN (P200A120238, P200A180088 & P200A150306)
- EIR (U411B190024, S411B210024 & S411B220024)
- ONR (N00014-18-1-2768)
- NIH (SBIR R44GM146483)
- Schmidt Futures
- BMGF
- CZI
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
