Malloum: An SMS-Based Generative AI Tutoring System for Contextualized Learning in Low-Connectivity Environments

Authors

DOI:

https://doi.org/10.65269/5p09zq79

Keywords:

Malloum, Generative AI, SMS-based learning, Intelligent tutoring system, Low-connectivity environments

Abstract

Limited internet connectivity continues to constrain access to digital learning resources across many low- and middle-income countries, particularly in Sub-Saharan Africa. While generative artificial intelligence has demonstrated strong potential for personalized tutoring, most existing systems assume reliable broadband access and smartphone availability. This paper presents Malloum, an SMS-based generative AI tutoring system designed to deliver contextualized, curriculum-aligned pedagogical support in low-connectivity environments. Malloum enables students to submit academic questions via standard SMS to a dedicated short code. The system integrates a backend orchestration layer with a hierarchical prompt architecture leveraging a state-of-the-art generative language model. A multi-layered prompting strategy combines a system-level pedagogical role definition, contextual curriculum injection aligned with the Cameroonian national syllabus, and user-level query input. An educational database (including validated exam banks, reference materials, and structured student profiles) enhances response accuracy, personalization, and pedagogical alignment. To address SMS-specific constraints, the platform implements structured micro-explanations, intelligent compression algorithms, automatic message concatenation, and adaptive bilingual output (French/English). A matched-pair cluster-assigned field study conducted with 1,000 secondary school students across 20 schools in the Far North Region of Cameroon using a pre-test/post-test design with a comparison group shows that the mean composite score of the Malloum group rose from 51.7% to 72.4%—an absolute gain of 20.7 percentage points, corresponding to a 40% relative improvement over baseline—compared with a gain of 4.3 percentage points (8.3% relative) in the control group, yielding an adjusted between-group difference of 16.1 percentage points (95% CI: 13.9–18.3, p < 0.001). Malloum provides a scalable, cost-aware, and culturally contextualized framework for AI-driven education, offering a practical pathway to narrowing the digital divide in secondary education systems.

Article Metrics

212 Views
167 Downloads
0 Citations Citation count provided by Crossref.

Readers by Country Unique usage is based on OJS/COUNTER-style deduplication and should not be interpreted as a count of identifiable people.

40 countries
  • Canada 68
  • Cameroon 53
  • United States 27
  • France 7
  • India 5
  • Brazil 4
  • Viet Nam 4
  • China 3
  • Germany 3
  • Kenya 3

Unique usage is based on OJS/COUNTER-style deduplication and should not be interpreted as a count of identifiable people.

About these metrics

Views: Article landing-page/abstract views reported by OJS usage statistics.

Downloads: Full-text file accesses reported by OJS usage statistics.

Citations: Citation count provided by Crossref.

Readers by Country: Unique usage is based on OJS/COUNTER-style deduplication and should not be interpreted as a count of identifiable people.

Author Biography

  • Isaac Touza, University of Maroua

    Isaac Touza, PhD is a Cameroonian researcher specializing in Artificial Intelligence and Knowledge Engineering and serves as an Lecturer in the Department of Mathematics and Computer Science, Faculty of Science, at the University of Maroua, Cameroon. His research focuses on artificial intelligence, knowledge engineering, ontology-based systems, automatic text classification, machine learning, deep learning, data mining, and software engineering. He is particularly interested in developing intelligent systems that integrate semantic technologies and AI to address complex real-world challenges. Beyond academia, Dr. Touza is actively involved in designing innovative digital solutions for education, agriculture, healthcare, and sustainable development, with a strong commitment to leveraging technology to foster socio-economic transformation across Africa.

References

GSMA. The Mobile Economy Sub-Saharan Africa 2024. Tech. rep. Accessed: 2026-04-02. London, UK: GSMA Intelligence, Nov. 2024. url: https://www.gsmaintelligence.com/research/the-mobile-economy-sub-saharan-africa-2024.

Anthony M. Kelly and Patrick N. Rutazihana. “Digital Divide and its Implications for Education in the Post-COVID-19 Era in Sub-Saharan Africa”. In: Innovation and Education 6.2 (2024), pp. 108–132. doi: 10.1163/25248502-bja00007. DOI: https://doi.org/10.1163/25248502-bja00007

International Telecommunication Union (ITU). Measuring Digital Development: Facts and Figures 2023. Tech. rep. Accessed: 2026-04-02. Geneva, Switzerland: International Telecommunication Union, 2023. url: https://www.itu.int/itu-d/reports/statistics/facts-figures-2023/.

Enkelejda Kasneci, Kathrin Sessler, Stefan Küchemann, Maria Bannert, Daryna Dementieva, Frank Fischer, and Gjergji Kasneci. “ChatGPT for good? On opportunities and challenges of large language models for education”. In: Learning and Individual Differences 103 (2023), p. 102274. doi: 10.1016/j.lindif.2023.102274. url: https://doi.org/10.1016/j.lindif.2023.102274. DOI: https://doi.org/10.1016/j.lindif.2023.102274

Zachary A. Pardos and Shreya Bhandari. “ChatGPT-generated help produces learning gains equivalent to human tutor-authored help on mathematics skills”. In: PLOS ONE 19.5 (2024), e0304013. doi: 10.1371/journal.pone.0304013. DOI: https://doi.org/10.1371/journal.pone.0304013

Greg Kestin, Kelly Miller, Allison Klales, et al. “AI tutoring outperforms in-class active learning: an RCT introducing a novel research-based design in an authentic educational setting”. In: Scientific Reports 15 (2025), p. 17458. doi: 10.1038/s41598-025-97652-6. DOI: https://doi.org/10.1038/s41598-025-97652-6

Angélique Létourneau, Marion Deslandes Martineau, Patrick Charland, John Alexander Karran, Jared Boasen, and Pierre Majorique Léger. “A Systematic Review of AI-Driven Intelligent Tutoring Systems (ITS) in K-12 Education”. In: npj Science of Learning 10.1 (2025), p. 29. doi: 10.1038/s41539-025-00320-7. url: https://doi.org/10.1038/s41539-025-00320-7. DOI: https://doi.org/10.1038/s41539-025-00320-7

Yuhao Dan, Zhikai Lei, Yiyang Gu, Yong Li, Jia Yin, Jiaming Lin, and Yuze Wang. “EduChat: A Large-Scale Language Model-Based Chatbot System for Intelligent Education”. In: 2023. doi: 10.48550/arXiv.2308.02773. url: https://doi.org/10.48550/arXiv.2308.02773.

Van Dat Nguyen, Ngoc Hung Tran, Kim Anh Dao, and Pham Van Nguyen. “Towards Personalized AI Education: Context-Aware Retrieval-Augmented Generation With Grade-Level LLM Adaptation”. In: Computer Applications in Engineering Education 34 (2026), e70153. doi: 10.1002/cae.70153. DOI: https://doi.org/10.1002/cae.70153

Benjamin S. Bloom. “The 2 sigma problem: The search for methods of group instruction as effective as one-to-one tutoring”. In: Educational Researcher 13.6 (1984), pp. 4–16. doi: 10.2307/1175554. DOI: https://doi.org/10.3102/0013189X013006004

Yunfan Gao et al. “Retrieval-Augmented Generation for Large Language Models: A Survey”. In: CoRR abs/2312.10997 (2023). doi: 10.48550/arXiv.2312.10997. arXiv: 2312.10997 [cs.CL]. url: https://doi.org/10.48550/arXiv.2312.10997.

Patrick Lewis et al. “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks”. In: Advances in Neural Information Processing Systems. Vol. 33. 2020, pp. 9459–9474. url: https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html.

Jakub Swacha and Mateusz Gracel. “Retrieval-Augmented Generation (RAG) Chatbots for Education: A Survey of Applications”. In: Applied Sciences 15.8 (2025), p. 4234. doi: 10.3390/app15084234. DOI: https://doi.org/10.3390/app15084234

Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models”. In: Advances in Neural Information Processing Systems. Vol. 35. 2022, pp. 24824–24837. doi: 10.52202/068431-1800. url: https://doi.org/10.52202/068431-1800. DOI: https://doi.org/10.52202/068431-1800

M-Shule. Personalized Learning Through SMS-Based AI in Kenya. https://m-shule.com/. 2022.

George Boateng, Sarah John, Alex Glago, Samuel Boateng, and Victor Kumbol. “Kwame for Science: An AI Teaching Assistant Based on Sentence-BERT for Science Education in West Africa”. In: arXiv preprint arXiv:2206.13703. 2022. doi: 10.48550/arXiv.2206.13703.

United Nations. AI and the Future of Learning. Africa Renewal. https://africarenewal.un.org/en/magazine/ai-and-future-learning. 2025.

Khan Academy. Khanmigo: AI-Powered Tutoring Assistant. https://www.khanacademy.org/khan-labs. 2023.

Nedim Slijepcevic and Ali Yaylali. “Leveraging “Khanmigo” Generative AI-Powered Tool for Personalized Tutoring to Learn Scientific Concepts”. In: Journal of Teaching and Learning 19.4 (2025). doi: 10.22329/jtl.v19i4.10052. DOI: https://doi.org/10.22329/jtl.v19i4.10052

Chris Piech, Jonathan Bassen, Jonathan Huang, Surya Ganguli, Mehran Sahami, Leonidas J. Guibas, and Jascha Sohl-Dickstein. “Deep Knowledge Tracing”. In: Advances in Neural Information Processing Systems. Vol. 28. 2015, pp. 505–513. url: https://proceedings.neurips.cc/paper/2015/hash/bac9162b47c56fc8a4d2a519803d51b3-Abstract.html.

Jean Piaget. Science of Education and the Psychology of the Child. Translated by Derek Coltman. New York: Orion Press, 1970. isbn: 9780671211967.

Lev S. Vygotsky. Mind in Society: The Development of Higher Psychological Processes. Ed. by Michael Cole, Vera John-Steiner, Sylvia Scribner, and Ellen Souberman. Cambridge, MA: Harvard University Press, 1978. isbn: 9780674576292.

Wayne Holmes and Fengchun Miao, eds. Guidance for Generative AI in Education and Research. Paris, France: UNESCO, 2023. isbn: 978-92-3-100612-8. doi: 10.54675/EWZM9535. url: https://doi.org/10.54675/EWZM9535. DOI: https://doi.org/10.54675/EWZM9535

UNESCO. The Cultural Cost of AI in Africa’s Education Systems. UNESCO Commentary. https://www.unesco.org. 2025.

Downloads

Published

2026-08-22 — Updated on 2026-09-28

Versions

Issue

Vol. 1 No. 1 (2026): AI, Education, Environment and Future Mobility: Machine Learning Applications for Sustainable Intelligent Systems

Section

Research Articles

License

Copyright (c) 2026 Isaac Touza (Author)

Creative Commons License

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

How to Cite

Touza, I. (2026). Malloum: An SMS-Based Generative AI Tutoring System for Contextualized Learning in Low-Connectivity Environments. Canadian Journal of Artificial Intelligence for Learning and Engineering Innovation, 1(1), 27–50. https://doi.org/10.65269/5p09zq79 (Original work published 2026)

Similar Articles

You may also start an advanced similarity search for this article.