AI's Struggle with Arabic: A Study on Pragmatic Failures in Contextual Communication

Authors

  • Shadi Majed Alshraah

    English Department, Prince Sattam bin Abdulaziz University, Al-Kharj 11942, Saudi Arabia
  • Ashwaq Abdulrahman Aldaghri

    Department of English Language and Literature, College of Languages and Translation, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 3204, Saudi Arabia
  • Iman Mohammad Oraif

    Department of English Language and Literature, College of Languages and Translation, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 3204, Saudi Arabia

DOI:

https://doi.org/10.30564/fls.v7i11.9252
Received: 27 March 2025 | Revised: 17 April 2025 | Accepted: 10 September 2025 | Published Online: 29 October 2025

Abstract

AI systems, such as ChatGPT, often face challenges when using language in ways that fit social and cultural contexts, especially when making requests. While these models are strong in grammar and meaning, they frequently face challenges in capturing social and cultural aspects, leading to misunderstandings. To explore this issue, two frameworks were used: Taguchi’s Pragmatic Appropriateness Model and Brown and Levinson's Politeness Theory. A mixed-methods approach compared AI and human responses to specific scenarios testing power, familiarity, and obligation. The findings reveal common problems, such as AI being overly formal in casual situations, misusing honorifics, mixing dialects, and misunderstanding context. These issues highlight the need for AI to better adapt to social and cultural differences, particularly in diverse environments. Integrating linguistic theories into AI training can enhance its ability to comprehend context and establish trust with users. This research stated that AI struggles to adapt to social norms, especially in situations where making requests requires accuracy. Most concerns involve being too formal, using honorifics incorrectly, mixing dialects in unnatural ways, and misunderstanding the context. These results highlight the need to include sociolinguistic principles in AI training to improve its understanding of culture and context. Furthermore, the results of the current study can help AI developers and policymakers in the MENA region.

   Highlights

  • The paper identifies specific pragmatic failures encountered by AI systems when processing Arabic, highlighting issues such as misinterpretation of context, cultural nuances, and idiomatic expressions that affect communication effectiveness.
  • Through a detailed analysis of various communication scenarios, the study demonstrates how AI's inability to grasp social cues and contextual subtleties leads to misunderstandings, thereby impacting user experience and trust in AI applications.
  • The paper offers actionable recommendations for enhancing AI's performance in Arabic, including the integrating culturally relevant training datasets, improving natural language processing algorithms, and emphasizing the importance of human-in-the-loop systems to mitigate pragmatic errors.

 

Keywords:

Artificial Intelligence (AI); Contextual Language Understanding; AI and Cultural Adaptation; Discourse Completion Test (DCT)

References

[1] Jakesch, M., Hancock, J.T., Naaman, M., 2023. Human heuristics for AI-generated language are flawed. Proceedings of the National Academy of Sciences. 120(11), 2208839120. DOI: https://doi.org/10.1073/pnas.2208839120

[2] Warschauer, M., Tseng, W., Yim, S., et al., 2023. The affordances and contradictions of AI-generated text for writers of English as a second or foreign language. Journal of Second Language Writing. 62, 1–20. DOI: https://doi.org/10.1016/j.jslw.2023.101071

[3] Zou, L., 2024. Creative computing in language understanding: A novel approach to pragmatic analysis [PhD Thesis]. University of Leicester: Leicester, UK.

[4] Hossain, K.I., 2024. Reviewing the role of culture in English language learning: Challenges and opportunities for educators. Social Sciences and Humanities Open. 9, 100781. DOI: https://doi.org/10.1016/j.ssaho.2023.100781

[5] Nazeer, I., Khan, N.M., Nawaz, A., et al., 2024. An experimental analysis of pragmatic competence in human-ChatGPT conversations. Pakistan Journal of Humanities and Social Sciences. 12(1), 424–435. DOI: http://dx.doi.org/10.52131/pjhss.2024.v12i1.2061

[6] Alos, J., 2015. Explicating the implicit: an empirical investigation into pragmatic competence in translator training. The Interpreter and Translator Trainer. 9(3), 287–305. DOI: https://doi.org/10.1080/1750399X.2015.1100398

[7] Taguchi, N., 2009. Pragmatic competence in Japanese as a second language: An introduction. Pragmatic Competence. 5, 1–18. DOI: https://doi.org/10.1515/9783110218558.1

[8] Brown, P., Levinson, S.C., 1987. Politeness: Some Universals in Language Usage. Cambridge University Press: Cambridge, UK.

[9] Hovy, E.H., 1990. Pragmatics and natural language generation. Artificial Intelligence. 43(2), 153–197. DOI: https://doi.org/10.1016/0004-3702(90)90084-D

[10] Algouzi, S., Alzubi, A.A.F., 2023. The study of AI-mediated communication and sociocultural language-related variables: Gmail reply suggestions. Applied Artificial Intelligence. 37(1), 2175114. DOI: https://doi.org/10.1080/08839514.2023.2175114

[11] Qiu, H., Zhao, T., Li, A., et al., 2023. A benchmark for understanding dialogue safety in mental health support. arXiv preprint. arXiv: 2307.16457v1. DOI: https://doi.org/10.48550/arXiv.2307.16457

[12] Cao, Y., Zhou, L., Lee, S., et al., 2023. Assessing cross-cultural alignment between ChatGPT and human societies: An empirical study. arXiv preprint. arXiv: 2303.17466. DOI: https://doi.org/10.48550/arXiv.2303.17466

[13] Paulikova, K., 2025. Navigating interaction with AI chatbots: Sociolinguistic and pragmatic aspects of chatbot use by Slovak and Hungarian speakers. Journal of Siberian Federal University. Humanities & Social Sciences. 18(1), 70–80.

[14] Green, A., 2009. Designing and evaluating human-robot communication: Informing design through analysis of user interaction [PhD Thesis]. KTH Royal Institute of Technology Stockholm, Sweden.

[15] Nam, Y., Chung, H., Hong, U., 2023. Language artificial intelligences' communicative performance quantified through the Gricean conversation theory. Cyberpsychology, Behavior, and Social Networking. 26(12), 919–923. DOI: https://doi.org/10.1089/cyber.2022.0356

[16] Guzman, A.L., Lewis, S.C., 2020. Artificial intelligence and communication: A human-machine communication research agenda. New Media and Society. 22(1), 70–86. DOI: https://doi.org/10.1177/1461444819858691

[17] Kim, H.-Y., 2014. Analysis of variance (ANOVA) comparing means of more than two groups. Restorative Dentistry and Endodontics. 39(1), 74–77. DOI: https://doi.org/10.5395/rde.2014.39.1.74

[18] Kim, T.K., 2017. Understanding one-way ANOVA using conceptual figures. Korean Journal of Anesthesiology. 70(1), 22–26. DOI: https://doi.org/10.4097/kjae.2017.70.1.22

[19] Moffett, J.W., Fennell, P., Harmeling, C.M., et al., 2024. The Taguchi approach to large-scale experimental designs: A powerful and efficient tool for advancing marketing theory and practice. Journal of the Academy of Marketing Science. 53, 949–954. DOI: http://dx.doi.org/10.1007/s11747-024-01059-0

[20] Taguchi, N., Crawford, W., Wetzel, D.Z., 2013. What linguistic features are indicative of writing quality? A case of argumentative essays in a college composition program. TESOL Quarterly. 47(2), 420–430.

[21] Devlin, J., Chang, M.-W., Lee, K., et al., 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv: 1810.04805. DOI: https://doi.org/10.48550/arXiv.1810.04805

[22] Habash, N.Y., 2010. Introduction to Arabic natural language processing (Synthesis lectures on human language technologies). Machine Translation 24, 285–289. DOI: https://doi.org/10.1007/s10590-011-9087-8

[23] Zhang, Y., Sun, S., Galley, M., et al., 2020. DialoGPT: Large-scale generative pre-training for conversational response generation. arXiv preprint arXiv: 1911.00536. DOI: https://doi.org/10.48550/arXiv.1911.00536

[24] Blodgett, S.L., Barocas, S., Daume III, H., et al., 2005. Language (technology) is power: A critical survey of "bias" in NLP. arXiv preprint. arXiv: 2005.14050v2. DOI: https://doi.org/10.48550/arXiv.2005.14050

[25] Alshraah, S.M., Harun, H., Kariem, A.A., 2023. Pragmalinguistic competence of directness request level: A case of Saudi EFL learners. International Journal of Society, Culture & Language. 1–16. DOI: https://doi.org/10.22034/ijscl.2023.2009932.3139

Downloads

How to Cite

Alshraah, S. M., Aldaghri, A. A., & Oraif, I. M. (2025). AI’s Struggle with Arabic: A Study on Pragmatic Failures in Contextual Communication. Forum for Linguistic Studies, 7(11), 1537–1549. https://doi.org/10.30564/fls.v7i11.9252

Issue

Vol. 7 , Iss. 11 (November 2025)

Article Type

Article

License

Copyright © 2025 Shadi Majed Alshraah, Ashwaq Abdulrahman Aldaghri, Iman Mohammad Oraif

Creative Commons License

This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.