Elamur Research⌕
☰
home / papers / 2025 / Arabic Chatbot Technologies in Education: An Overview

Arabic Chatbot Technologies in Education: An Overview

Summary

This short survey asks how far Arabic educational chatbots have come. Two 2022 reviews had already catalogued Arabic conversational agents, but neither focused on education, and both predate recent work. The authors combine those reviews with a fresh literature search up to August 2024. They count each distinct system once rather than each publication, which leaves 10 educational Arabic bots. Each bot is described along three dimensions: how it produces answers (rule-based, retrieval-based or generation-based), which Arabic variety it handles (Classical Arabic, Modern Standard Arabic or a dialect), and how it was evaluated (human feedback or automatic metrics). The picture is of an immature field. Most systems match user input against fixed patterns. Nearly all work only in MSA. Evaluation mostly relies on subjective user-satisfaction judgments. The authors call for deep-learning and generative methods, standard automatic metrics that could form a shared benchmark, and larger corpora for Classical Arabic and dialects. They present this as the first survey devoted specifically to educational Arabic chatbots.

Key points

  • Sources: an earlier scoping review listed 13 Arabic chatbots across all domains, only one of them generative. A second 2022 review found 50 studies, 15 in education, but several of those described the same bot.
  • Of the 10 unique educational bots, 8 came from the earlier reviews and 2 are newer.
  • 7 of the 10 are retrieval-based and rely on pattern matching. 2 were built with frameworks such as Google DialogFlow or RASA. Only 1 is generative.
  • Language coverage is almost entirely MSA. One bot handles Classical Arabic and one handles Saudi dialect.
  • Only the two newest bots report automatic metrics (Accuracy, F1-score, precision, BLEU). The rest depend on human satisfaction ratings, which the authors consider prone to bias.

Interesting ideas

  • I1. Count underlying systems instead of papers, since several publications may describe one bot and inflate the apparent size of a field. — For Mova (learn): When reporting evaluation coverage or silver-data sources, deduplicate witnesses and datasets by their real origin so that agreement between parsers is not overstated.
  • I2. Describe every system on a few fixed axes (answer strategy, language variety, evaluation type), which turns a loose literature list into a comparable table and exposes gaps at a glance. — For Mova (answer): A similar small grid could catalogue Mova's readers by task type, text register and scoring method, showing which combinations are still untested.
  • I3. Treat evaluation driven mainly by user satisfaction as a weakness, and push for automatic, standard metrics that could serve as a shared benchmark. — For Mova (answer): School tests and word-problem QA should be scored by exact, reproducible criteria with negative controls, not by impressions of answer quality.
  • I4. The rule / retrieval / generation ladder separates systems that only pick stored replies from those that compose new ones. — For Mova (back): This scale could be used to place Mova's generation from the meaning graph honestly, distinguishing template fill-ins from genuinely composed sentences.
  • I5. Track language variety (classical, standard, dialect) as an explicit property of each system and resource, since most tools quietly cover only the standard form. — For Mova (tree): Labelling treebanks and test texts by register or dialect, for example archaic fable English versus modern news, would show where the parser has no data and where UD dialect conversion is needed.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.54988/uaj.000027.001 · arXiv 2509.04066

@misc{bourhil2025arabic,
  title = {{Arabic Chatbot Technologies in Education: An Overview}},
  author = {Bourhil, Hicham and Younoussi, Yacine El},
  year = {2025},
  doi = {10.54988/uaj.000027.001},
  eprint = {2509.04066},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.54988/uaj.000027.001}
}

References

20 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Okonkwo, C.W., Ade-Ibijola, A.: Chatbots applications in education: A systematic review, (2021). https://doi.org/10.1016/j.caeai.2021.100033. ↗
  2. Darwish, K., Habash, N., Abbas, M., Al-Khalifa, H., Al-Natsheh, H.T., Bouamor, H., Bouzoubaa, K., Cavalli-Sforza, V., El-Beltagy, S.R., El-Hajj, W., Jarrar, M., Mubarak, H.: A panoramic survey of natural language processing in the Arab world, (2021). https://doi.org/10.1145/3447735. ↗
  3. Guellil, I., Saâdane, H., Azouaou, F., Gueni, B., Nouvel, D.: Arabic natural language processing: An overview, https://www.sciencedirect.com/science/article/pii/S1319157818310553, (2021). https://doi.org/10.1016/j.jksuci.2019.02.006. ↗ our card
  4. Alazzam, B.A., Alkhatib, M., Shaalan, K.: Arabic Educational Neural Network Chat-bot. Information Sciences Letters. 12, (2023). https://doi.org/10.18576/isl/120654. ↗
  5. Ahmed, A., Ali, N., Alzubaidi, M., Zaghouani, W., Abdalrazaq, A., Househ, M.: Arabic chatbot technologies: A scoping review. Computer Methods and Programs in Biomedicine Update. 2, (2022). https://doi.org/10.1016/j.cmpbup.2022.100057. ↗
  6. Brown, T.B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D.M., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., Amodei, D.: Language Models are Few-Shot Learners. (2020). find
  7. El Hefny, W., Mansy, Y., Abdallah, M., Abdennadher, S.: Jooka: A Bilingual Chatbot for University Admission. In: Advances in Intelligent Systems and Computing (2021). https://doi.org/10.1007/978-3-030-72660-7_64. ↗
  8. Alqahtani, Q., Alrwais, O.: Building a Machine Learning Powered Chatbot for KSU Blackboard Users. International Journal of BOURHIL, B., y EL YOUNOUSSI, Y. (2024). Arabic Chatbot Technologies in Education: An Overview. En C. Rusu et al., (1ª ed.), Transformación digital en la educación: innovaciones y desafíos desde los campus virtuales (pp. 11-14). Huelva (España): United Academic Journals (UA Journals). https://doi.org/10.54988/uaj.000027.001 UNITED ACADEMIC JOURNALS Advanced Computer Science and Applications. 14, (2023). https://doi.org/10.14569/IJACSA.2023.0140290. ↗ our card
  9. Alsheddi, A.S., Alhenaki, L.S.: English and Arabic Chatbots: A Systematic Literature Review. International Journal of Advanced Computer Science and Applications. 13, (2022). https://doi.org/10.14569/IJACSA.2022.0130876. ↗
  10. Alobaidi, O.G., Crockett, K.A., O’Shea, J.D., Jarad, T.M.: Abdullah: An intelligent arabic conversational tutoring system for modern islamic education. In: Lecture Notes in Engineering and Computer Science (2013). find
  11. Alobaidi, O.G., Smieee, K.A.C., Mieee, J.D.O.S., Jarad, T.M.: The application of learning theories into Abdullah: An intelligent Arabic conversational agent tutor. In: ICAART 2015 - 7th International Conference on Agents and Artificial Intelligence, Proceedings (2015). https://doi.org/10.5220/0005197003610369. ↗
  12. Hijjawi, M., Bandar, Z., Crockett, K., McLean, D.: ArabChat: An arabic conversational agent. In: 2014 6th International Conference on Computer Science and Information Technology, CSIT 2014 - Proceedings (2014). https://doi.org/10.1109/CSIT.2014.6806005. ↗
  13. Hijjawi, M., Qattous, H., Alsheiksalem, O.: Mobile Arabchat: An Arabic Mobile-Based Conversational Agent. International Journal of Advanced Computer Science and Applications. 6, (2015). https://doi.org/10.14569/ijacsa.2015.061016. ↗
  14. Hijjawi, M., Bandar, Z., Crockett, K.: The Enhanced Arabchat: An Arabic Conversational Agent. International Journal of Advanced Computer Science and Applications. 7, (2016). https://doi.org/10.14569/ijacsa.2016.070247. ↗
  15. Aljameel, S.S., O’Shea, J.D., Crockett, K.A., Latham, A., Kaleem, M.: Development of an Arabic Conversational Intelligent Tutoring System for Education of children with ASD. In: 2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications, CIVEMSA 2017 - Proceedings (2017). https://doi.org/10.1109/CIVEMSA.2017.7995296. ↗
  16. Aljameel, S., O’Shea, J., Crockett, K., Latham, A., Kaleem, M.: LANAI: An Arabic Conversational Intelligent Tutoring System for Children with ASD. In: Advances in Intelligent Systems and Computing (2019). https://doi.org/10.1007/978-3-030-22871-2_34. ↗
  17. ALMURTADHA, Y.: LABEEB: Intelligent Conversational Agent Approach to Enhance Course Teaching and Allied Learning Outcomes attainment. Journal of Applied Computer Science & Mathematics. 13, (2019). https://doi.org/10.4316/jacsm.201901001. ↗
  18. Elgibreen, H., Almazyad, S., Shuail, S. Bin, Qahtani, M. Al, Alhwiseen, L.: Robot Framework for Anti-Bullying in Saudi Schools. In: Proceedings - 4th IEEE International Conference on Robotic Computing, IRC 2020 (2020). https://doi.org/10.1109/IRC.2020.00033. ↗
  19. Sweidan, S.Z., Abu Laban, S.S., Alnaimat, N.A., Darabkh, K.A.: SIAAAC: A student interactive assistant android application with chatbot during COVID-19 pandemic. Computer Applications in Engineering Education. 29, (2021). https://doi.org/10.1002/cae.22419. ↗
  20. Sweidan, S.Z., Abu Laban, S.S., Alnaimat, N.A., Darabkh, K.A.: SEG-COVID: A Student Electronic Guide within Covid-19 Pandemic. In: 2021 9th International Conference on Information and Education Technology, ICIET 2021 (2021). https://doi.org/10.1109/ICIET51873.2021.9419656. UNITED ACADEMIC JOURNALS BOURHIL, B., y EL YOUNOUSSI, Y. (2024). Arabic Chatbot Technologies in Education: An Overview. En C. Rusu et al., (1ª ed.), Transformación digital en la educación: innovaciones y desafíos desde los campus virtuales (pp. 11-14). Huelva (España): United Academic Journals (UA Journals). https://doi.org/10.54988/uaj.000027.001 ↗ our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/bourhil-2025-arabic-chatbot-technologies-education-overview/