{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T15:16:31Z","timestamp":1778598991256,"version":"3.51.4"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T00:00:00Z","timestamp":1778544000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T00:00:00Z","timestamp":1778544000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Scientific Research Fund of the Ministry of Higher Education and Scientific Research, Jordan","award":["Soci\/2\/1\/2016"],"award-info":[{"award-number":["Soci\/2\/1\/2016"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s10772-026-10265-w","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T14:49:54Z","timestamp":1778597394000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A morphologically annotated dataset and comprehensive evaluation of morphological analyzers for Orani Arabic (MADOran)"],"prefix":"10.1007","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4975-6709","authenticated-orcid":false,"given":"Majdi","family":"Sawalha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3359-6052","authenticated-orcid":false,"given":"Faisal","family":"Alshargi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0594-3230","authenticated-orcid":false,"given":"Sane","family":"Yagi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3933-2082","authenticated-orcid":false,"given":"Ouafaa","family":"Kacha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9692-3242","authenticated-orcid":false,"given":"Abdallah T.","family":"AlShdaifat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad A.","family":"Qudah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7583-2440","authenticated-orcid":false,"given":"Najla","family":"Alnaqbi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3062-4511","authenticated-orcid":false,"given":"Bayan","family":"AbuShawar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,12]]},"reference":[{"key":"10265_CR1","doi-asserted-by":"publisher","unstructured":"Abdaoui, A., Berrimi, M., Oussalah, M., & Moussaoui, A. (2022). DziriBERT: A pre-trained language model for the Algerian dialect (arXiv:2109.12346). arXiv. https:\/\/doi.org\/10.48550\/arXiv.2109.12346","DOI":"10.48550\/arXiv.2109.12346"},{"key":"10265_CR2","doi-asserted-by":"publisher","unstructured":"Abdelali, A., Hassan, S., Mubarak, H., Darwish, K., & Samih, Y. (2021). Pre-training BERT on Arabic tweets: Practical considerations. (arXiv:2102.10684). arXiv. https:\/\/doi.org\/10.48550\/arXiv.2102.10684","DOI":"10.48550\/arXiv.2102.10684"},{"key":"10265_CR3","unstructured":"Adouane, W., Touileb, S., & Bernardy, J. P. (2020). Identifying sentiments in Algerian code-switched user-generated comments. In N. Calzolari, F. B\u00e9chet, P. Blache, K. Choukri, C. Cieri, T. Declerck, S. Goggi, H. Isahara, B. Maegaard, J. Mariani, H. Mazo, A. Moreno, J. Odijk, & S. Piperidis (Eds.), Proceedings of the twelfth language resources and evaluation conference (pp. 2698\u20132705). European Language Resources Association. https:\/\/aclanthology.org\/2020.lrec-1.328\/"},{"key":"10265_CR5","doi-asserted-by":"crossref","unstructured":"Al-Shargi, F., Kaplan, A., Eskander, R., Habash, N., & Rambow, O. (2016). Morphologically annotated corpora and morphological analyzers for Moroccan and Sanaani Yemeni Arabic. In Proceedings of the tenth international conference on language resources and evaluation (LREC 2016).","DOI":"10.63317\/2hchewb29iga"},{"key":"10265_CR4","doi-asserted-by":"publisher","unstructured":"Alshargi, F., Dibas, S., Alkhereyf, S., Faraj, R., Abdulkareem, B., Yagi, S., Kacha, O., Habash, N., & Rambow, O. (2019). Morphologically annotated corpora for seven Arabic dialects: Taizi, Sanaani, Najdi, Jordanian, Syrian, Iraqi and Moroccan. In W. El-Hajj, L. H. Belguith, F. Bougares, W. Magdy, I. Zitouni, N. Tomeh, M. El-Haj, & W. Zaghouani (Eds.), Proceedings of the fourth Arabic natural language processing workshop (pp. 137\u2013147). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/W19-4615","DOI":"10.18653\/v1\/W19-4615"},{"key":"10265_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/s41870-024-01926-7","author":"B Babaali","year":"2024","unstructured":"Babaali, B., Salem, M., & Alharbe, N. R. (2024). Breaking language barriers with ChatGPT: Enhancing low-resource machine translation between Algerian Arabic and MSA. International Journal of Information Technology. https:\/\/doi.org\/10.1007\/s41870-024-01926-7","journal-title":"International Journal of Information Technology"},{"key":"10265_CR7","doi-asserted-by":"publisher","unstructured":"Baert, G., Gahbiche, S., Gadek, G., & Pauchet, A. (2020). Arabizi language models for sentiment analysis. In D. Scott, N. Bel, & C. Zong (Eds.), Proceedings of the 28th international conference on computational l inguistics (pp. 592\u2013603). International Committee on Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.51","DOI":"10.18653\/v1\/2020.coling-main.51"},{"key":"10265_CR8","doi-asserted-by":"publisher","unstructured":"Belbachir, F. (2023). Foul at SemEval-2023 task 12: MARBERT language model and lexical filtering for sentiments analysis of tweets in Algerian Arabic. In A. Kr. Ojha, A. S. Do\u011fru\u00f6z, G. Da San Martino, H. Tayyar Madabushi, R. Kumar, & E. Sartori (Eds.), Proceedings of the 17th international workshop on semantic evaluation (SemEval-2023) (pp. 389\u2013396). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2023.semeval-1.52","DOI":"10.18653\/v1\/2023.semeval-1.52"},{"key":"10265_CR9","doi-asserted-by":"publisher","unstructured":"Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzm\u00e1n, F., Grave, E., Ott, M., Zettlemoyer, L., & Stoyanov, V. (2020). Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th annual M meeting of the association for computational linguistics (pp. 8440\u20138451). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.747","DOI":"10.18653\/v1\/2020.acl-main.747"},{"issue":"3","key":"10265_CR10","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1007\/s10579-016-9347-6","volume":"51","author":"M Djellab","year":"2017","unstructured":"Djellab, M., Amrouche, A., Bouridane, A., & Mehallegue, N. (2017). Algerian modern colloquial Arabic speech corpus (AMCASC): Regional accents recognition within complex socio-linguistic environments. Language Resources and Evaluation, 51(3), 613\u2013641. https:\/\/doi.org\/10.1007\/s10579-016-9347-6","journal-title":"Language Resources and Evaluation"},{"key":"10265_CR14","unstructured":"Guellil, I., & Faical, A. (2017). Bilingual lexicon for Algerian Arabic dialect treatment in social media. In WiNLP: Women & underrepresented minorities in natural language processing (Co-Located with ACL 2017)."},{"key":"10265_CR13","doi-asserted-by":"publisher","unstructured":"Guellil, I., Azouaou, F. (2016). Arabic dialect identification with an unsupervised learning (based on a lexicon). Application case: ALGERIAN dialect. In 2016 IEEE International conference on computational science and engineering (CSE) and IEEE International conference on embedded and ubiquitous computing (EUC) and 15th International symposium on distributed computing and applications for business engineering (DCABES), (pp. 724\u2013731). https:\/\/doi.org\/10.1109\/CSE-EUC-DCABES.2016.268","DOI":"10.1109\/CSE-EUC-DCABES.2016.268"},{"key":"10265_CR12","doi-asserted-by":"publisher","unstructured":"Guellil, I., Adeel, A., Azouaou, F., & Hussain, A. (2018). SentiALG: Automated corpus annotation for Algerian sentiment analysis. In J. Ren, A. Hussain, J. Zheng, C.-L. Liu, B. Luo, H. Zhao, & X. Zhao (Eds.), Advances in brain inspired cognitive systems (pp. 557\u2013567). Springer. https:\/\/doi.org\/10.1007\/978-3-030-00563-4_54","DOI":"10.1007\/978-3-030-00563-4_54"},{"issue":"2","key":"10265_CR11","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1007\/s42979-021-00510-1","volume":"2","author":"I Guellil","year":"2021","unstructured":"Guellil, I., Adeel, A., Azouaou, F., Benali, F., Hachani, A. E., Dashtipour, K., Gogate, M., Ieracitano, C., Kashani, R., & Hussain, A. (2021). A semi-supervised approach for sentiment analysis of Arab(ic\u2009+\u2009izi) messages: Application to the Algerian dialect. SN Computer Science, 2(2), 118. https:\/\/doi.org\/10.1007\/s42979-021-00510-1","journal-title":"SN Computer Science"},{"issue":"15","key":"10265_CR15","first-page":"219","volume":"XV","author":"J Guerrero","year":"2015","unstructured":"Guerrero, J. (2015). Preliminary notes on the current Arabic dialect of Oran (Western Algeria). Romano-Arabica, XV(15), 219\u2013233.","journal-title":"Romano-Arabica"},{"key":"10265_CR17","doi-asserted-by":"publisher","unstructured":"Harrat, S., Meftouh, K., & Smaili, K. (2019). Script independent morphological segmentation for Arabic maghrebi dialects: An application to machine translation. Computaci\u00f3n y Sistemas, 23(3). https:\/\/doi.org\/10.13053\/cys-23-3-3267","DOI":"10.13053\/cys-23-3-3267"},{"key":"10265_CR16","doi-asserted-by":"crossref","unstructured":"Harrat, S., Meftouh, K., Abbas, M., & Sma\u00efli, K. (2014, September 14). Building resources for Algerian Arabic dialects. In 15th annual conference of the international communication association interspeech. https:\/\/inria.hal.science\/hal-01066989","DOI":"10.21437\/Interspeech.2014-481"},{"key":"10265_CR18","unstructured":"Inoue, G., Alhafni, B., Baimukan, N., Bouamor, H., & Habash, N. (2021). The interplay of variant, size, and task type in Arabic pre-trained language models. In N. Habash, H. Bouamor, H. Hajj, W. Magdy, W. Zaghouani, F. Bougares, N. Tomeh, I. Abu Farha, & S. Touileb (Eds.), Proceedings of the sixth Arabic natural language processing workshop (pp. 92\u2013104). Association for Computational Linguistics. https:\/\/aclanthology.org\/2021.wanlp-1.10\/"},{"issue":"3","key":"10265_CR19","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1007\/s10579-016-9370-7","volume":"51","author":"M Jarrar","year":"2017","unstructured":"Jarrar, M., Habash, N., Alrimawi, F., Akra, D., & Zalmout, N. (2017). Curras: An annotated corpus for the Palestinian Arabic dialect. Language Resources and Evaluation, 51(3), 745\u2013775. https:\/\/doi.org\/10.1007\/s10579-016-9370-7","journal-title":"Language Resources and Evaluation"},{"key":"10265_CR20","doi-asserted-by":"crossref","unstructured":"Khalifa, S., Habash, N., Eryani, F., Obeid, O., Abdulrahim, D., & Al Kaabi, M. (2018). A morphologically annotated corpus of Emirati Arabic. In Proceedings of the eleventh international conference on language resources and evaluation (LREC 2018). https:\/\/aclanthology.org\/L18-1607","DOI":"10.63317\/4ujvhk7xskc6"},{"key":"10265_CR21","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1016\/j.procs.2018.10.489","volume":"142","author":"L Lulu","year":"2018","unstructured":"Lulu, L., & Elnagar, A. (2018). Automatic Arabic dialect classification using deep learning models. Procedia Computer Science. Arabic Computational Linguistics, 142, 262\u2013269. https:\/\/doi.org\/10.1016\/j.procs.2018.10.489","journal-title":"Arabic Computational Linguistics"},{"key":"10265_CR22","unstructured":"Moudjari, L., Akli-Astouati, K., & Benamara, F. (2020). An Algerian corpus and an annotation platform for opinion and emotion analysis. In N. Calzolari, F. B\u00e9chet, P. Blache, K. Choukri, C. Cieri, T. Declerck, S. Goggi, H. Isahara, B. Maegaard, J. Mariani, H. Mazo, A. Moreno, J. Odijk, & S. Piperidis (Eds.), Proceedings of the twelfth language resources and evaluation conference (pp. 1202\u20131210). European Language Resources Association. https:\/\/aclanthology.org\/2020.lrec-1.151\/"},{"key":"10265_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2025.112104","author":"M Sawalha","year":"2025","unstructured":"Sawalha, M., Al-Shargi, F., Yagi, S., Kasha, W., AlShdaifat, A. T., Qudah, M. A., & Alnaqbi, N. (2025). MADOran: A morphologically annotated dataset of Oran. Data in Brief, 63, 112104. https:\/\/doi.org\/10.1016\/j.dib.2025.112104"},{"issue":"6","key":"10265_CR24","doi-asserted-by":"publisher","first-page":"e6788","DOI":"10.1002\/cpe.6788","volume":"34","author":"R Torjmen","year":"2022","unstructured":"Torjmen, R., & Haddar, K. (2022). Translation system from tunisian dialect to modern standard Arabic. Concurrency and Computation: Practice and Experience, 34(6), e6788. https:\/\/doi.org\/10.1002\/cpe.6788","journal-title":"Concurrency and Computation: Practice and Experience"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-026-10265-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-026-10265-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-026-10265-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T14:50:00Z","timestamp":1778597400000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-026-10265-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,12]]},"references-count":24,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10265"],"URL":"https:\/\/doi.org\/10.1007\/s10772-026-10265-w","relation":{"references":[{"id-type":"doi","id":"10.1016\/j.dib.2025.112104","asserted-by":"subject"}]},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,12]]},"assertion":[{"value":"18 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"43"}}