{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T08:11:20Z","timestamp":1781597480815,"version":"3.54.5"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"26","license":[{"start":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T00:00:00Z","timestamp":1755129600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T00:00:00Z","timestamp":1755129600000},"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":["Neural Comput & Applic"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s00521-025-11501-1","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T19:22:54Z","timestamp":1755199374000},"page":"22029-22055","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Swarm intelligence for handling out-of-vocabulary in Arabic Dialect Identification with different representations"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1572-3055","authenticated-orcid":false,"given":"Mahmoud","family":"Sobhy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed H.","family":"AbuElAtta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed A.","family":"El-Sawy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamada","family":"Nayel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,14]]},"reference":[{"key":"11501_CR1","doi-asserted-by":"publisher","unstructured":"Cho K, Merri\u00ebnboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation. In: Moschitti, A., Pang, B., Daelemans, W. (eds.) Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp. 1724\u20131734. Association for Computational Linguistics, Doha, Qatar. https:\/\/doi.org\/10.3115\/v1\/D14-1179","DOI":"10.3115\/v1\/D14-1179"},{"key":"11501_CR2","doi-asserted-by":"crossref","unstructured":"Lochter JV, Pires PR, Bossolani C, Yamakami A, Almeida TA (2018) Evaluating the impact of corpora used to train distributed text representation models for noisy and short texts. In: 2018 International joint conference on neural networks (IJCNN), 1\u20138","DOI":"10.1109\/IJCNN.2018.8489355"},{"key":"11501_CR3","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1007\/978-3-030-61377-8_29","volume-title":"Intelligent system","author":"JV Lochter","year":"2020","unstructured":"Lochter JV, Silva RM, Almeida TA (2020) Deep learning models for representing out-of-vocabulary words. In: Cerri R, Prati RC (eds) Intelligent system. Springer, Cham, pp 418\u2013434"},{"key":"11501_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108911","volume":"251","author":"JV Lochter","year":"2022","unstructured":"Lochter JV, Silva RM, Almeida TA (2022) Multi-level out-of-vocabulary words handling approach. Knowl-Based Syst 251:108911. https:\/\/doi.org\/10.1016\/j.knosys.2022.108911","journal-title":"Knowl-Based Syst"},{"key":"11501_CR5","doi-asserted-by":"publisher","unstructured":"Garneau N, Leboeuf J-S, Lamontagne L (2018) Predicting and interpreting embeddings for out of vocabulary words in downstream tasks. In: Linzen, T., Chrupa\u0142a, G., Alishahi, A. (eds.) Proceedings of the 2018 EMNLP workshop BlackboxNLP: analyzing and interpreting neural networks for NLP, pp. 331\u2013333. Association for Computational Linguistics, Brussels, Belgium. https:\/\/doi.org\/10.18653\/v1\/W18-5439","DOI":"10.18653\/v1\/W18-5439"},{"key":"11501_CR6","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski P, Grave E, Joulin A, Mikolov T (2017) Enriching word vectors with subword information. Trans Assoc Comput Linguist 5:135\u2013146. https:\/\/doi.org\/10.1162\/tacl_a_00051","journal-title":"Trans Assoc Comput Linguist"},{"key":"11501_CR7","doi-asserted-by":"publisher","unstructured":"Sundermeyer M, Schl\u00fcter R, Ney H (2012) LSTM neural networks for language modeling. In Proc. Interspeech. https:\/\/doi.org\/10.21437\/Interspeech.2012-65","DOI":"10.21437\/Interspeech.2012-65"},{"key":"11501_CR8","doi-asserted-by":"crossref","unstructured":"Abdul-Mageed M, Zhang C, Elmadany A, Bouamor H, Habash N (2021) Nadi 2021: the second nuanced arabic dialect identification shared task.","DOI":"10.18653\/v1\/2022.wanlp-1.9"},{"key":"11501_CR9","doi-asserted-by":"crossref","unstructured":"Abdul-Mageed M, Zhang C, Elmadany A, Bouamor H, Habash N (2022) Nadi 2022: the third nuanced arabic dialect identification shared task","DOI":"10.18653\/v1\/2022.wanlp-1.9"},{"key":"11501_CR10","doi-asserted-by":"crossref","unstructured":"Abdul-Mageed M, Elmadany A, Nagoudi EMB (2020) Arbert & marbert: deep bidirectional transformers for arabic","DOI":"10.18653\/v1\/2021.acl-long.551"},{"issue":"3","key":"11501_CR11","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1017\/S0047404507070315","volume":"36","author":"N Boussofara-Omar","year":"2007","unstructured":"Boussofara-Omar N (2007) Niloofar haeri, sacred language, ordinary people: dilemmas of culture and politics in Egypt. Lang Soc 36(3):466\u2013469. https:\/\/doi.org\/10.1017\/S0047404507070315","journal-title":"Lang Soc"},{"key":"11501_CR12","unstructured":"Aliwy A, Taher H, AboAltaheen Z (2020) Arabic dialects identification for all Arabic countries. In: Proceedings of the fifth Arabic natural language processing workshop, 302\u2013307"},{"key":"11501_CR13","doi-asserted-by":"publisher","DOI":"10.1515\/9781474457361","volume-title":"Arabic sociolinguistics: topics in diglossia, gender, identity, and politics","author":"R Bassiouney","year":"2020","unstructured":"Bassiouney R (2020) Arabic sociolinguistics: topics in diglossia, gender, identity, and politics. Georgetown University Press, Washington"},{"key":"11501_CR14","first-page":"99","volume":"4","author":"M Tilmatine","year":"1999","unstructured":"Tilmatine M (1999) Substrat et convergences: le berb\u00e8re et l\u2019 arabe nord-africain. EDNA Estudios de dialectolog\u00eda norteafricana y andalus\u00ed 4:99\u2013119","journal-title":"EDNA Estudios de dialectolog\u00eda norteafricana y andalus\u00ed"},{"key":"11501_CR15","doi-asserted-by":"crossref","unstructured":"Abdul-Mageed M, Elmadany A, Zhang C, Nagoudi EMB, Bouamor H, Habash N (2023) NADI 2023: the fourth nuanced Arabic dialect identification shared task","DOI":"10.18653\/v1\/2023.arabicnlp-1.62"},{"key":"11501_CR16","doi-asserted-by":"crossref","unstructured":"Abdul-Mageed M, Keleg A, Elmadany A, Zhang C, Hamed I, Magdy W, Bouamor H, Habash N (2024) NADI 2024: the fifth nuanced Arabic dialect identification shared task","DOI":"10.18653\/v1\/2024.arabicnlp-1.79"},{"key":"11501_CR17","unstructured":"Antoun W, Baly F, Hajj H (2020) Arabert: transformer-based model for Arabic language understanding"},{"key":"11501_CR18","unstructured":"Talafha B, Ali M, Za\u2019ter ME, Seelawi H, Tuffaha I, Samir M, Farhan W, Al-Natsheh HT (2020) Multi-dialect Arabic bert for country-level dialect identification"},{"key":"11501_CR19","unstructured":"Gaanoun K, Benelallam I (2020) Arabic dialect identification: An arabic-bert model with data augmentation and ensembling strategy. In: Proceedings of the fifth Arabic natural language processing workshop, pp. 275\u2013281"},{"key":"11501_CR20","unstructured":"Abbassi A, Mechti S, Belguith LH, Faiz R (2017) Author profiling for arabic tweets based on n-grams. In: LPKM"},{"key":"11501_CR21","doi-asserted-by":"publisher","unstructured":"AbuElAtta AH, Sobhy M, El-Sawy AA, Nayel H (2023) Arabic regional dialect identification (ardi) using pair of continuous bag-of-words and data augmentation. Int J Adv Comput Sci Appl 14(11) https:\/\/doi.org\/10.14569\/IJACSA.2023.0141125","DOI":"10.14569\/IJACSA.2023.0141125"},{"key":"11501_CR22","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s10791-017-9319-5","volume":"21","author":"X Yang","year":"2016","unstructured":"Yang X, Macdonald C, Ounis I (2016) Using word embeddings in twitter election classification. Inf Retriev J 21:183\u2013207","journal-title":"Inf Retriev J"},{"key":"11501_CR23","doi-asserted-by":"publisher","unstructured":"Khodak M, Saunshi N, Liang Y, Ma T, Stewart B, Arora S (2018) A la carte embedding: Cheap but effective induction of semantic feature vectors. In: Gurevych, I., Miyao, Y. (eds.) Proceedings of the 56th annual meeting of the association for computational linguistics (Volume 1: Long Papers), pp. 12\u201322. Association for Computational Linguistics, Melbourne, Australia. https:\/\/doi.org\/10.18653\/v1\/P18-1002","DOI":"10.18653\/v1\/P18-1002"},{"key":"11501_CR24","doi-asserted-by":"publisher","unstructured":"Hu Z, Chen T, Chang K-W, Sun Y (2019) Few-shot representation learning for out-of-vocabulary words. In: Korhonen, A., Traum, D., M\u00e0rquez, L. (eds.) Proceedings of the 57th annual meeting of the association for computational linguistics, pp. 4102\u20134112. Association for Computational Linguistics, Florence, Italy. https:\/\/doi.org\/10.18653\/v1\/P19-1402","DOI":"10.18653\/v1\/P19-1402"},{"key":"11501_CR25","doi-asserted-by":"crossref","unstructured":"Garneau N, Leboeuf J-S, Lamontagne L (2019) Contextual generation of word embeddings for out of vocabulary words in downstream tasks. In: Canadian Conference on AI","DOI":"10.1007\/978-3-030-18305-9_60"},{"key":"11501_CR26","unstructured":"Zhuang L, Wayne L, Ya S, Jun Z (2021) A robustly optimized BERT pre-training approach with post-training. In: Li, S., Sun, M., Liu, Y., Wu, H., Liu, K., Che, W., He, S., Rao, G. (eds.) Proceedings of the 20th Chinese national conference on computational linguistics, pp. 1218\u20131227. Chinese Information Processing Society of China, Huhhot, China"},{"key":"11501_CR27","unstructured":"Sanh V, Debut L, Chaumond J, Wolf T (2020) DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter"},{"key":"11501_CR28","unstructured":"Abu\u00a0Farha I, Magdy W (2020) From Arabic sentiment analysis to sarcasm detection: The ArSarcasm dataset. In: Al-Khalifa, H., Magdy, W., Darwish, K., Elsayed, T., Mubarak, H. (eds.) Proceedings of the 4th workshop on open-source Arabic corpora and processing tools, with a shared task on offensive language detection, pp. 32\u201339. European Language Resource Association, Marseille, France"},{"key":"11501_CR29","doi-asserted-by":"crossref","unstructured":"Rosenthal S, Farra N, Nakov P (2019) Semeval-2017 task 4: sentiment analysis in twitter","DOI":"10.18653\/v1\/S17-2088"},{"key":"11501_CR30","doi-asserted-by":"crossref","unstructured":"Nabil M, Aly M, Atiya A (2015) Astd: Arabic sentiment tweets dataset. In: Proceedings of the 2015 conference on empirical methods in natural language processing, pp. 2515\u20132519","DOI":"10.18653\/v1\/D15-1299"},{"key":"11501_CR31","unstructured":"Abu\u00a0Farha I, Zaghouani W, Magdy W (2021) Overview of the WANLP 2021 shared task on sarcasm and sentiment detection in Arabic. In: Habash, N., Bouamor, H., Hajj, H., Magdy, W., Zaghouani, W., Bougares, F., Tomeh, N., Abu\u00a0Farha, I., Touileb, S. (eds.) Proceedings of the sixth Arabic natural language processing workshop, pp. 296\u2013305. Association for Computational Linguistics, Kyiv, Ukraine (Virtual). https:\/\/aclanthology.org\/2021.wanlp-1.36\/"},{"issue":"3","key":"11501_CR32","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/s11528-014-0750-9","volume":"58","author":"CA Depaolo","year":"2014","unstructured":"Depaolo CA, Wilkinson K (2014) Get your head into the clouds: using word clouds for analyzing qualitative assessment data. TechTrends 58(3):38\u201344 (Copyright - Association for Educational Communications and Technology 2014)","journal-title":"TechTrends"},{"key":"11501_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-021-00492-0","volume":"8","author":"C Shorten","year":"2021","unstructured":"Shorten C, Khoshgoftaar TM, Furht B (2021) Text data augmentation for deep learning. J Big Data 8:1\u201334","journal-title":"J Big Data"},{"key":"11501_CR34","unstructured":"El-Haj M (2020) Habibi-a multi dialect multi national Arabic song lyrics corpus"},{"key":"11501_CR35","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space"},{"key":"11501_CR36","unstructured":"Rehurek R, Sojka P (2011) Gensim \u2013 statistical semantics in python"},{"key":"11501_CR37","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski P, Grave E, Joulin A, Mikolov T (2017) Enriching word vectors with subword information. Trans Assoc Comput Linguist 5:135\u2013146. https:\/\/doi.org\/10.1162\/tacl_a_00051","journal-title":"Trans Assoc Comput Linguist"},{"key":"11501_CR38","doi-asserted-by":"crossref","unstructured":"Suleiman D, Awajan A (2018) Comparative study of word embeddings models and their usage in arabic language applications. In: 2018 International Arab Conference on Information Technology (ACIT), pp. 1\u20137. IEEE","DOI":"10.1109\/ACIT.2018.8672674"},{"key":"11501_CR39","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/978-3-319-11857-4_10","volume-title":"Adv Swarm Intell","author":"X Meng","year":"2014","unstructured":"Meng X, Liu Y, Gao X, Zhang H (2014) A new bio-inspired algorithm: Chicken swarm optimization. In: Tan Y, Shi Y, Coello CAC (eds) Adv Swarm Intell. Springer, Cham, pp 86\u201394"},{"key":"11501_CR40","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.advengsoft.2013.12.007","volume":"69","author":"S Mirjalili","year":"2014","unstructured":"Mirjalili S, Mirjalili SM, Lewis A (2014) Grey wolf optimizer. Adv Eng Softw 69:46\u201361. https:\/\/doi.org\/10.1016\/j.advengsoft.2013.12.007","journal-title":"Adv Eng Softw"},{"key":"11501_CR41","unstructured":"Salami NA (2009) Ant colony optimization algorithm. https:\/\/api.semanticscholar.org\/CorpusID:11754556"},{"key":"11501_CR42","doi-asserted-by":"publisher","unstructured":"Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of ICNN\u201995 - international conference on neural networks, 4:1942\u201319484. https:\/\/doi.org\/10.1109\/ICNN.1995.488968","DOI":"10.1109\/ICNN.1995.488968"},{"key":"11501_CR43","doi-asserted-by":"crossref","unstructured":"Dalianis H, Dalianis H (2018) Evaluation metrics and evaluation. Clinical Text Mining: secondary use of electronic patient records, 45\u201353","DOI":"10.1007\/978-3-319-78503-5_6"},{"issue":"11","key":"11501_CR44","first-page":"33","volume":"4","author":"A Sarkar","year":"2015","unstructured":"Sarkar A, Chatterjee S, Das W, Datta D (2015) Text classification using support vector machine. Int J Eng Sci Invent 4(11):33\u201337","journal-title":"Int J Eng Sci Invent"},{"issue":"1","key":"11501_CR45","doi-asserted-by":"publisher","first-page":"1503","DOI":"10.1016\/j.eswa.2011.08.040","volume":"39","author":"S Jiang","year":"2012","unstructured":"Jiang S, Pang G, Wu M, Kuang L (2012) An improved k-nearest-neighbor algorithm for text categorization. Expert Syst Appl 39(1):1503\u20131509","journal-title":"Expert Syst Appl"},{"key":"11501_CR46","doi-asserted-by":"crossref","unstructured":"Harrag F, El-Qawasmeh E, Pichappan P (2009) Improving arabic text categorization using decision trees. In: 2009 First international conference on networked digital technologies, pp. 110\u2013115. IEEE","DOI":"10.1109\/NDT.2009.5272214"},{"issue":"6","key":"11501_CR47","doi-asserted-by":"publisher","first-page":"2733","DOI":"10.1016\/j.jksuci.2022.03.012","volume":"34","author":"N Jalal","year":"2022","unstructured":"Jalal N, Mehmood A, Choi GS, Ashraf I (2022) A novel improved random forest for text classification using feature ranking and optimal number of trees. J King Saud Univ-Comput Inf Sci 34(6):2733\u20132742","journal-title":"J King Saud Univ-Comput Inf Sci"},{"key":"11501_CR48","first-page":"1","volume":"2021","author":"H Alla","year":"2021","unstructured":"Alla H, Moumoun L, Balouki Y (2021) A multilayer perceptron neural network with selective-data training for flight arrival delay prediction. Sci Progr 2021:1\u201312","journal-title":"Sci Progr"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11501-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-025-11501-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11501-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T03:22:18Z","timestamp":1757388138000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-025-11501-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,14]]},"references-count":48,"journal-issue":{"issue":"26","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["11501"],"URL":"https:\/\/doi.org\/10.1007\/s00521-025-11501-1","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,14]]},"assertion":[{"value":"30 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 August 2025","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 author declares that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}