{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:35:13Z","timestamp":1783694113236,"version":"3.55.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T00:00:00Z","timestamp":1705968000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T00:00:00Z","timestamp":1705968000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Data Sci Anal"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s41060-023-00498-2","type":"journal-article","created":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T06:02:06Z","timestamp":1705989726000},"page":"917-929","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["DarijaBERT: a step forward in NLP for the written Moroccan dialect"],"prefix":"10.1007","volume":"20","author":[{"given":"Kamel","family":"Gaanoun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdou Mohamed","family":"Naira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anass","family":"Allak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Imade","family":"Benelallam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,23]]},"reference":[{"key":"498_CR1","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: 31st NIPS, pp. 6000\u20136010 (2017)"},{"key":"498_CR2","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), pp. 4171\u20134186 (2019). https:\/\/doi.org\/10.18653\/v1\/n19-1423","DOI":"10.18653\/v1\/n19-1423"},{"key":"498_CR3","doi-asserted-by":"publisher","unstructured":"Martin, L., Muller, B., Ortiz\u00a0Su\u00e1rez, P.J., Dupont, Y., Romary, L., de\u00a0la Clergerie, \u00c9., Seddah, D., Sagot, B.: CamemBERT: a tasty French language model. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online, pp. 7203\u20137219 (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.645","DOI":"10.18653\/v1\/2020.acl-main.645"},{"key":"498_CR4","unstructured":"Ca\u00f1ete, J., Chaperon, G., Fuentes, R., Ho, J.-H., Kang, H., P\u00e9rez, J.: Spanish pre-trained bert model and evaluation data. In: PML4DC at ICLR 2020 (2020)"},{"key":"498_CR5","doi-asserted-by":"publisher","unstructured":"Elgezouli, M., Elmadani, K.N., Saeed, M.: Sudabert: pre-trained encoder representation for Sudanese Arabic dialect. In: 2020 ICCCEEE, pp. 1\u20134 (2021). https:\/\/doi.org\/10.1109\/ICCCEEE49695.2021.9429651","DOI":"10.1109\/ICCCEEE49695.2021.9429651"},{"key":"498_CR6","doi-asserted-by":"crossref","unstructured":"Messaoudi, A., Cheikhrouhou, A., Haddad, H., Ferchichi, N., BenHajhmida, M., Korched, A., Naski, M., Ghriss, F., Kerkeni, A.: Tunbert: Pretrained contextualized text representation for Tunisian dialect. In: Intelligent Systems and Pattern Recognition, Cham, pp. 278\u2013290 (2022)","DOI":"10.1007\/978-3-031-08277-1_23"},{"key":"498_CR7","unstructured":"Abdaoui, A., Berrimi, M., Oussalah, M., Moussaoui, A.: Dziribert: pre-trained language model for the Algerian dialect. arXiv preprint arXiv:2109.12346 (2021)"},{"key":"498_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13369-022-06588-w","volume":"47","author":"A Slim","year":"2022","unstructured":"Slim, A., Melouah, A., Faghihi, U., Sahib, K.: Improving neural machine translation for low resource Algerian dialect by transductive transfer learning strategy. Arab. J. Sci. Eng. 47, 1\u20138 (2022)","journal-title":"Arab. J. Sci. Eng."},{"key":"498_CR9","unstructured":"Meftouh, K., Harrat, S., Jamoussi, S., Abbas, M., Smaili, K.: Machine translation experiments on PADIC: a parallel Arabic DIalect corpus. In: Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation, Shanghai, China, pp. 26\u201334 (2015). https:\/\/aclanthology.org\/Y15-1004"},{"key":"498_CR10","unstructured":"Antoun, W., Baly, F., Hajj, H.: AraBERT: transformer-based model for Arabic language understanding. In: Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, Marseille, France, pp. 9\u201315 (2020)"},{"key":"498_CR11","doi-asserted-by":"crossref","unstructured":"Safaya, A., Abdullatif, M., Yuret, D.: KUISAIL at SemEval-2020 : BERT-CNN for offensive speech identification in social media. In: 40th SemEval, pp. 2054\u20132059. ICCL, Barcelona (online) (2020)","DOI":"10.18653\/v1\/2020.semeval-1.271"},{"key":"498_CR12","doi-asserted-by":"publisher","unstructured":"Abdul-Mageed, M., Elmadany, A., Nagoudi, E.M.B.: ARBERT & MARBERT: Deep bidirectional transformers for Arabic. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Online, pp. 7088\u20137105 (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.551","DOI":"10.18653\/v1\/2021.acl-long.551"},{"key":"498_CR13","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.: Unsupervised cross-lingual representation learning at scale. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online, pp. 8440\u20138451 (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.747","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"498_CR14","unstructured":"Inoue, G., Alhafni, B., Baimukan, N., Bouamor, H., Habash, N.: The interplay of variant, size, and task type in Arabic pre-trained language models. In: Workshop on Arabic Natural Language Processing (2021)"},{"key":"498_CR15","unstructured":"Abdelali, A., Hassan, S., Mubarak, H., Darwish, K., Samih, Y.: Pre-training bert on Arabic tweets: practical considerations. arXiv preprint arXiv:2102.10684 (2021)"},{"key":"498_CR16","unstructured":"El-Khair, I.A.: 1.5b words Arabic corpus. preprint arXiv:1611.04033 (2016)"},{"key":"498_CR17","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: Xlnet: generalized autoregressive pretraining for language understanding. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"498_CR18","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., Stoyanov, V.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"498_CR19","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020 (2020)"},{"key":"498_CR20","doi-asserted-by":"crossref","unstructured":"Schuster, M., Nakajima, K.: Japanese and Korean voice search. In: 2012 IEEE ICASSP, pp. 5149\u20135152 (2012). IEEE","DOI":"10.1109\/ICASSP.2012.6289079"},{"issue":"4","key":"498_CR21","doi-asserted-by":"publisher","first-page":"483","DOI":"10.14746\/ssllt.2012.2.4.3","volume":"2","author":"RM Bianchi","year":"2012","unstructured":"Bianchi, R.M.: Glocal Arabic online: the case of 3arabizi. SSLLT 2(4), 483\u2013503 (2012)","journal-title":"SSLLT"},{"issue":"2","key":"498_CR22","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1162\/desi.2008.24.2.39","volume":"24","author":"MA Yaghan","year":"2008","unstructured":"Yaghan, M.A.: \u201cArabizi\u2019\u2019: a contemporary style of Arabic slang. Design Issues 24(2), 39\u201352 (2008)","journal-title":"Design Issues"},{"issue":"9","key":"498_CR23","doi-asserted-by":"publisher","first-page":"155","DOI":"10.3390\/socsci7090155","volume":"7","author":"H Alghamdi","year":"2018","unstructured":"Alghamdi, H., Petraki, E.: Arabizi in Saudi Arabia: a deviant form of language or simply a form of expression? Soc. Sci. 7(9), 155 (2018)","journal-title":"Soc. Sci."},{"key":"498_CR24","unstructured":"Aboelezz, M.: \u2019we are young. we are trendy. buy our product!\u2019: The use of Latinized Arabic in printed edited magazines in Egypt. UAJSS (9), 47\u201372 (2012)"},{"issue":"1","key":"498_CR25","first-page":"917","volume":"9","author":"D Palfreyman","year":"2003","unstructured":"Palfreyman, D., Khalil, M.A.: \u201cA funky language for teenz to use\u2019\u2019: representing gulf Arabic in instant messaging. J. Comput. Med. Commun. 9(1), 917 (2003)","journal-title":"J. Comput. Med. Commun."},{"issue":"3","key":"498_CR26","first-page":"44","volume":"4","author":"L Mostafa","year":"2012","unstructured":"Mostafa, L.: A survey of automated tools for translating Arab chat alphabet into Arabic language. Am. Acad. Sch. Res. J. 4(3), 44\u201350 (2012)","journal-title":"Am. Acad. Sch. Res. J."},{"key":"498_CR27","doi-asserted-by":"crossref","unstructured":"Elmahdy, M., Gruhn, R., Abdennadher, S., Minker, W.: Rapid phonetic transcription using everyday life natural chat alphabet orthography for dialectal Arabic speech recognition. In: 2011 IEEE ICASSP, pp. 4936\u20134939 (2011). IEEE","DOI":"10.1109\/ICASSP.2011.5947463"},{"key":"498_CR28","unstructured":"Habash, N., Eryani, F., Khalifa, S., Rambow, O., Abdulrahim, D., Erdmann, A., Faraj, R., Zaghouani, W., Bouamor, H., Zalmout, N., : Unified guidelines and resources for arabic dialect orthography. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) (2018)"},{"key":"498_CR29","unstructured":"Abu\u00a0Farha, I., Magdy, W.: From Arabic sentiment analysis to sarcasm detection: the ArSarcasm dataset. In: 4th OSACT, Marseille, France, pp. 32\u201339 (2020)"},{"key":"498_CR30","unstructured":"Bouamor, H., Habash, N., Salameh, M., Zaghouani, W., Rambow, O., Abdulrahim, D., Obeid, O., Khalifa, S., Eryani, F., Erdmann, A.,: The madar arabic dialect corpus and lexicon. In: LREC (2018)"},{"key":"498_CR31","unstructured":"Abdul-Mageed, M., Zhang, C., Bouamor, H., Habash, N.: NADI 2020: The first Nuanced Arabic dialect identification shared task. In: Proceedings of the Fifth WANLP, pp. 97\u2013110 (2020)"},{"key":"498_CR32","unstructured":"Abdelali, A., Mubarak, H., Samih, Y., Hassan, S., Darwish, K.: Qadi: Arabic dialect identification in the wild. In: Workshop on Arabic Natural Language Processing (2021)"},{"key":"498_CR33","unstructured":"Zaghouani, W., Charfi, A.: Arap-tweet: a large multi-dialect Twitter corpus for gender, age and language variety identification. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan (2018)"},{"key":"498_CR34","unstructured":"Al-Shargi, F., Kaplan, A., Eskander, R., Habash, N., Rambow, O.: Morphologically annotated corpora and morphological analyzers for Moroccan and Sanaani Yemeni Arabic. In: 10th LREC 2016 (2016)"},{"key":"498_CR35","first-page":"62","volume":"3","author":"K Darwish","year":"2018","unstructured":"Darwish, K., Abdelali, A., Mubarak, H., Samih, Y., Attia, M.: Diacritization of Moroccan and Tunisian Arabic dialects: A CRF approach. OSACT 3, 62 (2018)","journal-title":"OSACT"},{"key":"498_CR36","unstructured":"Samih, Y., Maier, W.: An Arabic-Moroccan Darija code-switched corpus. In: Proceedings of LREC\u201916, pp. 4170\u20134175 (2016)"},{"key":"498_CR37","unstructured":"Voss, C., Tratz, S., Laoudi, J., Briesch, D.: Finding Romanized Arabic dialect in code-mixed tweets. In: Proceedings of LREC\u201914, pp. 2249\u20132253 (2014)"},{"key":"498_CR38","unstructured":"Laoudi, J., Bonial, C., Donatelli, L., Tratz, S., Voss, C.: Towards a computational lexicon for Moroccan darija: Words, idioms, and constructions. In: Proceedings of LAW-MWE-CxG-2018, pp. 74\u201385 (2018)"},{"key":"498_CR39","doi-asserted-by":"crossref","unstructured":"Maghfour, M., Elouardighi, A.: Standard and dialectal Arabic text classification for sentiment analysis. In: ICMDE, pp. 282\u2013291 (2018). Springer","DOI":"10.1007\/978-3-030-00856-7_18"},{"issue":"10","key":"498_CR40","first-page":"363","volume":"11","author":"S Mihi","year":"2020","unstructured":"Mihi, S., Ait, B., El, I., Arezki, S., Laachfoubi, N.: Mstd: Moroccan sentiment twitter dataset. Int. J. Adv. Comput. Sci. Appl 11(10), 363\u2013372 (2020)","journal-title":"Int. J. Adv. Comput. Sci. Appl"},{"key":"498_CR41","unstructured":"Refaee, E., Rieser, V.: An Arabic twitter corpus for subjectivity and sentiment analysis. In: LREC, pp. 2268\u20132273 (2014)"},{"issue":"4","key":"498_CR42","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1177\/0165551519849516","volume":"46","author":"A Oussous","year":"2020","unstructured":"Oussous, A., Benjelloun, F.-Z., Lahcen, A.A., Belfkih, S.: Asa: A framework for Arabic sentiment analysis. J. Inf. Sci. 46(4), 544\u2013559 (2020)","journal-title":"J. Inf. Sci."},{"key":"498_CR43","unstructured":"El\u00a0Abdouli, A., Hassouni, L., Anoun, H.: Sentiment analysis of Moroccan tweets using naive bayes algorithm. IJCSIS 15(12) (2017)"},{"key":"498_CR44","doi-asserted-by":"crossref","unstructured":"Habbat, N., Anoun, H., Hassouni, L.: Topic modeling and sentiment analysis with LDA and NMF on Moroccan tweets. In: The Proceedings of the Third ICSCA, pp. 147\u2013161 (2020). Springer","DOI":"10.1007\/978-3-030-66840-2_12"},{"key":"498_CR45","doi-asserted-by":"crossref","unstructured":"Abdellaoui, H., Zrigui, M.: Using tweets and emojis to build tead: an Arabic dataset for sentiment analysis. Computaci\u2019on y Sistemas 22(3) (2018)","DOI":"10.13053\/cys-22-3-3031"},{"key":"498_CR46","unstructured":"Boujou, E., Chataoui, H., Mekki, A.E., Benjelloun, S., Chairi, I., Berrada, I.: An open access nlp dataset for arabic dialects: data collection, labeling, and model construction. preprint arXiv:2102.11000 (2021)"}],"container-title":["International Journal of Data Science and Analytics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-023-00498-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41060-023-00498-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-023-00498-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T18:37:15Z","timestamp":1757097435000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41060-023-00498-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,23]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["498"],"URL":"https:\/\/doi.org\/10.1007\/s41060-023-00498-2","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2560653\/v1","asserted-by":"object"}]},"ISSN":["2364-415X","2364-4168"],"issn-type":[{"value":"2364-415X","type":"print"},{"value":"2364-4168","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,23]]},"assertion":[{"value":"7 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 December 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors state that they have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}