{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T00:29:49Z","timestamp":1777854589015,"version":"3.51.4"},"reference-count":58,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T00:00:00Z","timestamp":1697846400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T00:00:00Z","timestamp":1697846400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Information Science"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:p>Arabic sentiment analysis has become an important research field in recent years. Initially, work focused on Modern Standard Arabic (MSA), which is the most widely used form. Since then, work has been carried out on several different dialects, including Egyptian, Levantine and Moroccan. Moreover, a number of data sets have been created to support such work. However, up until now, no work has been carried out on Sudanese Arabic, a dialect which has 32\u2009million speakers. In this article, two new public data sets are introduced, the two-class Sudanese Sentiment Data set (SudSenti2) and the three-class Sudanese Sentiment Data set (SudSenti3). In the preparation phase, we establish a Sudanese stopword list. Furthermore, a convolutional neural network (CNN) architecture, Sentiment Convolutional MMA (SCM), is proposed, comprising five CNN layers together with a novel Mean Max Average (MMA) pooling layer, to extract the best features. This SCM model is applied to SudSenti2 and SudSenti3 and shown to be superior to the baseline models, with accuracies of 92.25% and 85.23% (Experiments 1 and 2). The performance of MMA is compared with Max, Avg and Min and shown to be better on SudSenti2, the Saudi Sentiment Data set and the MSA Hotel Arabic Review Data set by 1.00%, 0.83% and 0.74%, respectively (Experiment 3). Next, we conduct an ablation study to determine the contribution to performance of text normalisation and the Sudanese stopword list (Experiment 4). For normalisation, this makes a difference of 0.43% on two-class and 0.45% on three-class. For the custom stoplist, the differences are 0.82% and 0.72%, respectively. Finally, the model is compared with other deep learning classifiers, including transformer-based language models for Arabic, and shown to be comparable for SudSenti2 (Experiment 5).<\/jats:p>","DOI":"10.1177\/01655515231188341","type":"journal-article","created":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T02:11:59Z","timestamp":1697940719000},"page":"285-306","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":12,"title":["A deep CNN architecture with novel pooling layer applied to two Sudanese Arabic sentiment data sets"],"prefix":"10.1177","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3106-669X","authenticated-orcid":false,"given":"Mustafa","family":"Mhamed","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Northwest University, China; College of Information and Electrical Engineering, China Agricultural University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5549-5691","authenticated-orcid":false,"given":"Richard","family":"Sutcliffe","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Northwest University, China; School of Computer Science and Electronic Engineering, University of Essex, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Husam","family":"Quteineh","sequence":"additional","affiliation":[{"name":"Business and Local Government Data Research Centre, School of CSEE, University of Essex, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xia","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Northwest University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7182-9639","authenticated-orcid":false,"given":"Eiad","family":"Almekhlafi","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Northwest University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ephrem Afele","family":"Retta","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Northwest University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Northwest University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2023,10,21]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55394-8_2"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2632188.2632207"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101274"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-19578-0_15"},{"key":"e_1_3_3_6_2","volume-title":"Dialectal Arabic processing using deep learning","author":"Samih Y.","year":"2017","unstructured":"Samih Y. Dialectal Arabic processing using deep learning. PhD thesis, HeinrichHeine-Universit\u00e4t, D\u00fcsseldorf, 2017."},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2021.107777"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1002\/asi.21301"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00563-4_60"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1075\/cilt.33"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.05.034"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1177\/0165551519865488"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00239"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1177\/01655515211006594"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96292-4"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.10.489"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/AICCSA.2018.8612804"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCISci.2019.8716394"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISACS48493.2019.9068897"},{"key":"e_1_3_3_20_2","doi-asserted-by":"crossref","unstructured":"Mulki H Haddad H Gridach M et al Empirical evaluation of leveraging named entities for Arabic sentiment analysis. arXiv preprintarXiv:1904.10195 2019.","DOI":"10.34028\/iajit\/17\/2\/11"},{"key":"e_1_3_3_21_2","unstructured":"Abdel-Salam R. WANLP 2021 shared-task: towards irony and sentiment detection in Arabic tweets using multiheaded-LSTM-CNN-GRU and MaRBERT. In: Proceedings of the Sixth Arabic natural language processing workshop pp. 306\u2013311 2021. https:\/\/aclanthology.org\/2021.wanlp-1.37\/"},{"key":"e_1_3_3_22_2","unstructured":"Abdul-Mageed M Elmadany A Nagoudi EMB. ARBERT & MARBERT: deep bidirectional transformers for Arabic. arXiv preprintarXiv:2101.01785 2020."},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/5538791"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.05.028"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3386723.3387899"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1177\/0165551516683908"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-0877-1_10"},{"key":"e_1_3_3_29_2","unstructured":"Zaidan O Callison-Burch C. The Arabic online commentary dataset: an annotated dataset of informal Arabic with high dialectal content. In: Proceedings of the 49th annual meeting of the Association for Computational Linguistics: human language technologies Portland OR 19\u201324 June 2011 pp. 37\u201341. New York: ACM."},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1002\/asi.21598"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/AEECT.2013.6716448"},{"key":"e_1_3_3_32_2","unstructured":"Aly M Atiya A. LABR: a large scale Arabic book reviews dataset. In: Proceedings of the 51st annual meeting of the Association for Computational Linguistics vol. 2: Short Papers 2013 pp. 494\u2013498. https:\/\/aclanthology.org\/P13-2088\/"},{"key":"e_1_3_3_33_2","unstructured":"Moudjari L Akli-Astouati K Benamara F. An Algerian corpus and an annotation platform for opinion and emotion analysis. In: Proceedings of The 12th language resources and evaluation conference pp. 1202\u20131210 2020. https:\/\/aclanthology.org\/2020.lrec-1.151\/"},{"key":"e_1_3_3_34_2","unstructured":"Mikolov T Chen K Corrado G et al Efficient estimation of word representations in vector space. arXiv preprintarXiv:1301.3781 2013."},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32959-4_9"},{"key":"e_1_3_3_36_2","first-page":"729","volume-title":"Proceedings of the future technologies conference","author":"Y\u0131lmaz T","year":"2019","unstructured":"Y\u0131lmaz T, Ergil A, \u0130lgen B. Deep learning-based document modeling for personality detection from Turkish texts. In: Arai K, Bhatia R, Kapoor S (eds) Proceedings of the future technologies conference. Cham: Springer, 2019, pp. 729\u2013736."},{"key":"e_1_3_3_37_2","first-page":"35","volume-title":"Second international conference on Arabic computational linguistics, ACLING","author":"Sayadi K","year":"2016","unstructured":"Sayadi K, Liwicki M, Ingold R, et al Tunisian dialect and modern standard Arabic dataset for sentiment analysis: Tunisian election context. In: Second international conference on Arabic computational linguistics, ACLING, Konya, Turkey, 3rd-9th April 2016, pp. 35\u201353."},{"key":"e_1_3_3_38_2","doi-asserted-by":"crossref","unstructured":"Medhaffar S Bougares F Esteve Y et al Sentiment analysis of Tunisian dialects: linguistic resources and experiments. In: Third Arabic natural language processing workshop (WANLP) 2017 pp. 55\u201361. https:\/\/aclanthology.org\/W17-1307\/","DOI":"10.18653\/v1\/W17-1307"},{"key":"e_1_3_3_39_2","unstructured":"Farha A Zaghouani W Magdy W. Overview of the WANLP 2021 shared task on sarcasm and sentiment detection in Arabic. In: Proceedings of the sixth Arabic natural language processing workshop 2021 pp. 296\u2013305. https:\/\/aclanthology.org\/2021.wanlp-1.36\/"},{"key":"e_1_3_3_40_2","doi-asserted-by":"crossref","unstructured":"Nabil M Aly M Atiya A. ASTD: Arabic sentiment tweets dataset. In: Proceedings of the 2015 conference on empirical methods in natural language processing 2015 pp. 2515\u20132519. https:\/\/aclanthology.org\/D15-1299\/","DOI":"10.18653\/v1\/D15-1299"},{"key":"e_1_3_3_41_2","doi-asserted-by":"crossref","unstructured":"Salameh M Mohammad S Kiritchenko S. Sentiment after translation: a case-study on Arabic social media posts. In: Proceedings of the 2015 conference of the North American chapter of the association for computational linguistics: human language technologies 2015 pp. 767\u2013777. https:\/\/aclanthology.org\/N15-1078\/","DOI":"10.3115\/v1\/N15-1078"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.3390\/fi11110229"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67056-0_3"},{"key":"e_1_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2021.e06191"},{"issue":"2","key":"e_1_3_3_45_2","first-page":"38","article-title":"Improving Arabic text categorization using normalization and stemming techniques","volume":"135","author":"Sallam RM","year":"2016","unstructured":"Sallam RM, Mousa HM, Hussein M. Improving Arabic text categorization using normalization and stemming techniques. Int J Comput Appl 2016; 135(2): 38\u201343.","journal-title":"Int J Comput Appl"},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.10.117"},{"key":"e_1_3_3_47_2","unstructured":"Mikolov T Sutskever I Chen K et al Distributed representations of words and phrases and their compositionality. arXiv preprintarXiv:1310.4546 2013."},{"key":"e_1_3_3_48_2","first-page":"1185","article-title":"Sparse feature learning for deep belief networks","volume":"20","author":"Ranzato M","year":"2007","unstructured":"Ranzato M, Boureau Y-L, LeCun Y, et al Sparse feature learning for deep belief networks. Adv Neur In 2007; 20: 1185\u20131192.","journal-title":"Adv Neur In"},{"key":"e_1_3_3_49_2","first-page":"396","article-title":"Handwritten digit recognition with a back-propagation network","volume":"2","author":"LeCun Y","year":"1990","unstructured":"LeCun Y, Boser B, Denker J, et al Handwritten digit recognition with a back-propagation network. Adv Neur In 1990; 2: 396\u2013404.","journal-title":"Adv Neur In"},{"key":"e_1_3_3_50_2","unstructured":"Socher R Huang E Pennin J et al Dynamic pooling and unfolding recursive autoencoders for paraphrase detection. Adv Neur In 2011; 24. https:\/\/papers.nips.cc\/paper_files\/paper\/2011\/hash\/3335881e06d4d23091389226225e17c7-Abstract.html"},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1142\/S0219649220400183"},{"key":"e_1_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.5539\/mas.v13n5p88"},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jiph.2016.09.007"},{"key":"e_1_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.7603\/s40601-016-0016-9"},{"key":"e_1_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.12.018"},{"key":"e_1_3_3_56_2","unstructured":"Britz D. Recurrent neural networks tutorial part 1 \u2013introduction to RNNS. online]. http:\/\/www.wildml.com\/2015\/09\/recurrent-neuralnetworkstutorial-part-1-introduction-to-rnns\/ (2015 accessed 2 May 2019)."},{"key":"e_1_3_3_57_2","unstructured":"Zhang Y Wallace B. A sensitivity analysis of (and practitioners\u2019 guide to) convolutional neural networks for sentence classification. arXiv preprintarXiv:1510.03820 2015."},{"key":"e_1_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32959-4"},{"key":"e_1_3_3_59_2","unstructured":"Abdelali A Durrani N Dalvi F et al Interpreting Arabic transformer models. arXiv preprintarXiv:2201.07434 2022."}],"container-title":["Journal of Information Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/01655515231188341","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/01655515231188341","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/01655515231188341","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T23:10:12Z","timestamp":1777504212000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/01655515231188341"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,21]]},"references-count":58,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1177\/01655515231188341"],"URL":"https:\/\/doi.org\/10.1177\/01655515231188341","relation":{},"ISSN":["0165-5515","1741-6485"],"issn-type":[{"value":"0165-5515","type":"print"},{"value":"1741-6485","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,21]]}}}