ENHANCING WRITING COMPREHENSION IN L2 ARABIC LEARNERS THROUGH AI-BASED TRANSLANGUAGING CHATBOTS
Article Sidebar
Main Article Content
Abstract
The ability to speak a foreign language today is a skill that should be possessed by everyone, especially students, among whom are Arabic language skills. Nowadays, there are a lot of media and learning facilities that can be used to improve language skills. One of them is using AI chatbots, so this research is done to find out how effective these artificial intelligence chatbots are in improving the Arabic writing skills of L2 students. Second language acquisition poses a significant challenge when utilizing artificial intelligence chatbots for learning. Proficiency limitations in the second language can impede effective communication with chatbots. However, this challenge can be addressed through the practice of translanguaging in chatbot interactions. This study adopts a quantitative approach using pre-experimental methods to assess the efficacy of an artificial intelligence chatbot for enhancing Arabic writing comprehension within a translanguaging framework. The primary objective is to improve writing comprehension among Arabic learners as a second language (L2). The research involves 45 participants from Arabic language classes within the Department of Quranic Studies and Exegesis (IQT) at STAI Al-Anwar Sarang, Rembang. Statistical analyses and Bayesian inference are performed using JASP 0.18.1.0 software. Both classical and Bayesian analyses are employed to validate test results, augment probability and sustainability, while maintaining a focused analysis of the impact of chatbot-assisted learning within the translation framework. The results indicate a significant positive impact of utilizing AI chatbot-based Arabic writing comprehension among L2 learners. The researchers foresee the necessity for further exploration in the realms of translanguaging frameworks and their application in AI-assisted language learning
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Abdulkader, Z., & Al-Irhayim, Y. (2022). A Review of Arabic Intelligent Chatbots: Developments and Challenges. Al-Rafidain Engineering Journal (AREJ), 27(2), 178–189. https://doi.org/10.33899/rengj.2022.132550.1148
Al-Abdullatif, A. M., & Alsubaie, M. A. (2022). Using digital learning platforms for teaching Arabic literacy: A post-pandemic mobile learning scenario in Saudi Arabia. Sustainability, 14(19), 11868.
Ashoori, M., & Weisz, J. D. (2019). In AI We Trust? Factors That Influence Trustworthiness of AI-infused Decision-Making Processes. https://doi.org/10.48550/ARXIV.1912.02675
Brundage, M., Avin, S., Wang, J., Belfield, H., Krueger, G., Hadfield, G., Khlaaf, H., Yang, J., Toner, H., & Fong, R. (2020). Toward trustworthy AI development: Mechanisms for supporting verifiable claims. arXiv Preprint arXiv:2004.07213. https://doi.org/10.48550/arXiv.2004.07213
Canals, L. (2022). The role of the language of interaction and translanguaging on attention to interactional feedback in virtual exchanges. System, 105, 102721.
Chan, C. K. Y. (2023). A comprehensive AI policy education framework for university teaching and learning. International Journal of Educational Technology in Higher Education, 20(1), 38. https://doi.org/10.48550/arXiv.2305.00280
DeCapua, S. E. (2022). (Not) Lost in Translation: Multilingual Students, Translation, and Translanguaging in First-Year Writing. In Global and Transformative Approaches Toward Linguistic Diversity (pp. 206–222). IGI Global.
Elashhab, S. (2020). The impact of translanguaging on the EFL competence development of Arabic speaking learners. The Asian EFL Journal, 27(3.1), 393–413.
Faulkenberry, T. J., Ly, A., & Wagenmakers, E.-J. (2020). Bayesian Inference in Numerical Cognition: A Tutorial Using JASP. Journal of Numerical Cognition, 6(2), 231–259. https://doi.org/10.5964/jnc.v6i2.288
Fuad, A., & Al-Yahya, M. (2022). Recent Developments in Arabic Conversational AI: A Literature Review. IEEE Access, 10, 23842–23859. https://doi.org/10.1109/ACCESS.2022.3155521
Goodman, B., & Tastanbek, S. (2021). Making the shift from a codeswitching to a translanguaging lens in English language teacher education. TESOL Quarterly, 55(1), 29–53.
Goss-Sampson, M., van Doorn, J., & Wagenmakers, E. J. (2020, May 19). Bayesian inference in JASP: A guide for students [Monograph]. University of Greenwich; Jeffrey’s Amazing Statistics Program (JASP). https://doi.org/10.17605/OSF.IO/CKNXM
Hajir, B., Rasman, R., & McInerney, W. (2022). Digital translanguaging and Arabic-English transliteration (Arabizi): Insights from Syria and Lebanon. Cambridge Educational Reseach E-Journal, 9
Hatherley, J. J. (2020). Limits of trust in medical AI. Journal of Medical Ethics, 46(7), 478–481. http://dx.doi.org/10.1136/medethics-2019-105935
Iftanti, E. (2016). Improving students’ writing skills through writing journal articles. IAIN Tulungagung Research Collections, 8(1), 1–22. https://dx.doi.org/10.21274/ls.2016.8.1.1-22
Kolhar, M., & Alameen, A. (2021). Artificial Intelligence Based Language Translation Platform. Intelligent Automation & Soft Computing, 28(1). http://dx.doi.org/10.32604/iasc.2021.014995
Kruschke, J. K. (2021). Bayesian Analysis Reporting Guidelines. Nature Human Behaviour, 5(10), Article 10. https://doi.org/10.1038/s41562-021-01177-7
Liang, W., & Dai, H. (2023). Bayesian inference. In Quantum Chemistry in the Age of Machine Learning (pp. 233–250). Elsevier. https://doi.org/10.1016/B978-0-323-90049-2.00005-6
Maier, M., Bartoš, F., Quintana, D., Dablander, F., van den Bergh, D., Marsman, M., Ly, A., & Wagenmakers, E.-J. (2022). Model-averaged Bayesian T-tests.
Miao, F., Holmes, W., Huang, R., & Zhang, H. (2021). AI and education: A guidance for policymakers. UNESCO Publishing. https://doi.org/10.54675/PCSP7350
Michel-Villarreal, R., Vilalta-Perdomo, E., Salinas-Navarro, D. E., Thierry-Aguilera, R., & Gerardou, F. S. (2023). Challenges and Opportunities of Generative AI for Higher Education as Explained by ChatGPT. Education Sciences, 13(9), 856. https://doi.org/10.3390/educsci13090856
Perkins, M. (2023). Academic integrity considerations of AI Large Language Models in the post-pandemic era: ChatGPT and beyond. Journal of University Teaching and Learning Practice, British University, Vietnam, 20(2). https://doi.org/10.53761/1.20.02.07
Putri Supriadi, S. R. R., Haedi, S. U., & Chusni, M. M. (2022). Inovasi pembelajaran berbasis teknologi Artificial Intelligence dalam Pendidikan di era industry 4.0 dan society 5.0. Jurnal Penelitian Sains Dan Pendidikan (JPSP), 2(2), 192–198. https://doi.org/10.23971/jpsp.v2i2.4036
Renz, A., & Vladova, G. (2021). Reinvigorating the discourse on human-centered artificial intelligence in educational technologies. Technology Innovation Management Review, 11(5).
Rumaisa, F., Puspitarani, Y., Rosita, A., Zakiah, A., & Violina, S. (2021). Penerapan Natural Language Processing (NLP) di bidang pendidikan. Jurnal Inovasi Masyarakat, 1(3), 232–235. https://doi.org/10.33197/jim.vol1.iss3.2021.799
SAPUTRI, D. S. C. (2021). PENGEMBANGAN MODEL PEMBELAJARAN BAHASA INGGRIS BERBASIS AUGMENTED REALITY
Aisah, S., Anas, A., Gunawan, G., & Lestari, V. (2022). Peningkatan Kapasitas Ibu dengan Kondisi Marginal Pendidikan dalam Upaya Mendidik Generasi Alpha di Era Modernitas Informasi. Risalah, Jurnal Pendidikan dan Studi Islam, 8(4), 1486-1498