{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T20:20:06Z","timestamp":1773433206589,"version":"3.50.1"},"reference-count":61,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,9,11]],"date-time":"2021-09-11T00:00:00Z","timestamp":1631318400000},"content-version":"vor","delay-in-days":253,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61877050"],"award-info":[{"award-number":["61877050"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>Sentiment analysis is an essential process which is important to many natural language applications. In this paper, we apply two models for Arabic sentiment analysis to the ASTD and ATDFS datasets, in both 2\u2010class and multiclass forms. Model MC1 is a 2\u2010layer CNN with global average pooling, followed by a dense layer. MC2 is a 2\u2010layer CNN with max pooling, followed by a BiGRU and a dense layer. On the difficult ASTD 4\u2010class task, we achieve 73.17%, compared to 65.58% reported by Attia et al., 2018. For the easier 2\u2010class task, we achieve 90.06% with MC1 compared to 85.58% reported by Kwaik et al., 2019. We carry out experiments on various data splits, to match those used by other researchers. We also pay close attention to Arabic preprocessing and include novel steps not reported in other works. In an ablation study, we investigate the effect of two steps in particular, the processing of emoticons and the use of a custom stoplist. On the 4\u2010class task, these can make a difference of up to 4.27% and 5.48%, respectively. On the 2\u2010class task, the maximum improvements are 2.95% and 3.87%.<\/jats:p>","DOI":"10.1155\/2021\/5538791","type":"journal-article","created":{"date-parts":[[2021,9,11]],"date-time":"2021-09-11T22:50:07Z","timestamp":1631400607000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Improving Arabic Sentiment Analysis Using CNN\u2010Based Architectures and Text Preprocessing"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3106-669X","authenticated-orcid":false,"given":"Mustafa","family":"Mhamed","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5549-5691","authenticated-orcid":false,"given":"Richard","family":"Sutcliffe","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0572-641X","authenticated-orcid":false,"given":"Xia","family":"Sun","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0706-2103","authenticated-orcid":false,"given":"Jun","family":"Feng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7182-9639","authenticated-orcid":false,"given":"Eiad","family":"Almekhlafi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0906-9605","authenticated-orcid":false,"given":"Ephrem Afele","family":"Retta","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2021,9,11]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.05.034"},{"key":"e_1_2_9_2_2","unstructured":"Web Languages Top ten languages used in the web\u2013March 31 2020 2020 https:\/\/www.internetworldstats.com\/stats7.htm."},{"key":"e_1_2_9_3_2","doi-asserted-by":"publisher","DOI":"10.14257\/ijgdc.2018.11.9.09"},{"key":"e_1_2_9_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-019-0596-4"},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00039"},{"key":"e_1_2_9_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3049734"},{"key":"e_1_2_9_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.10.489"},{"key":"e_1_2_9_8_2","unstructured":"ASTD 2015 Arabic Sentiment Tweets Dataset https:\/\/github.com\/mahmoudnabil\/ASTD."},{"key":"e_1_2_9_9_2","unstructured":"AttiaM. SamihY. ElkahkyA. andKallmeyerL. Multilingual multi-class sentiment classification using convolutional neural networks Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) May 2018 Miyazaki Japan."},{"key":"e_1_2_9_10_2","doi-asserted-by":"crossref","unstructured":"KimY. Convolutional neural networks for sentence classification 2014 http:\/\/arxiv.org\/abs\/1408.5882.","DOI":"10.3115\/v1\/D14-1181"},{"key":"e_1_2_9_11_2","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/1329281"},{"key":"e_1_2_9_12_2","unstructured":"DahouA. XiongS. ZhouJ. HaddoudM. H. andDuanP. Word embeddings and convolutional neural network for Arabic sentiment classification Proceedings of Coling 2016 the 26th International Conference on Computational Linguistics: Technical Papers December 2016 Osaka Japan 2418\u20132427."},{"key":"e_1_2_9_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.10.466"},{"key":"e_1_2_9_14_2","doi-asserted-by":"crossref","unstructured":"SoufanA. Deep learning for sentiment analysis of Arabic text Proceedings of the 2019 Arabic 6th Annual International Conference Research Track March 2019 Rabat Morocco 1\u20138 https:\/\/doi.org\/10.1145\/3333165.3333185 2-s2.0-85071938300.","DOI":"10.1145\/3333165.3333185"},{"key":"e_1_2_9_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102435"},{"key":"e_1_2_9_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106435"},{"key":"e_1_2_9_17_2","unstructured":"ZhouC. SunC. LiuZ. andLauF. A c-lstm neural network for text classification 2015 http:\/\/arxiv.org\/abs\/1511.08630."},{"key":"e_1_2_9_18_2","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/2537689"},{"key":"e_1_2_9_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3278605"},{"key":"e_1_2_9_20_2","doi-asserted-by":"publisher","DOI":"10.17694\/bajece.419538"},{"key":"e_1_2_9_21_2","first-page":"101","article-title":"Lda-based topic modelling in text sentiment classification: an empirical analysis","volume":"7","author":"Onan A.","year":"2016","journal-title":"International Journal of Linguistics and Computational Applications"},{"key":"e_1_2_9_22_2","doi-asserted-by":"crossref","unstructured":"KwaikK. A. SaadM. ChatzikyriakidisS. andDobnikS. Lstm-cnn deep learning model for sentiment analysis of dialectal Arabic Proceedings of the 2019 7th International Conference on Arabic Language Processing October 2019 Nancy France Springer 108\u2013121.","DOI":"10.1007\/978-3-030-32959-4_8"},{"key":"e_1_2_9_23_2","doi-asserted-by":"publisher","DOI":"10.1002\/cae.22179"},{"key":"e_1_2_9_24_2","doi-asserted-by":"publisher","DOI":"10.1002\/cae.22253"},{"key":"e_1_2_9_25_2","doi-asserted-by":"crossref","unstructured":"BalyR. BadaroG. El-KhouryG.et al. A characterization study of Arabic twitter data with a benchmarking for state-of-the-art opinion mining models Proceedings of the 2017 Third Arabic Natural Language Processing Workshop April 2017 Valencia Spain 110\u2013118 https:\/\/doi.org\/10.18653\/v1\/W17-1314.","DOI":"10.18653\/v1\/W17-1314"},{"key":"e_1_2_9_26_2","unstructured":"KwaikK. A.andChatzikyriakidisS. An Arabic tweets sentiment analysis dataset (atsad) using distant supervision and self training Proceedings of the 2020 4th Workshop on Open-Source Arabic Corpora and Processing Tools with a Shared Task on Offensive Language Detection May 2020 Marseille France 1\u20138."},{"key":"e_1_2_9_27_2","unstructured":"ZaidanO. F.andCallison-BurchC. The Arabic online commentary dataset: an annotated dataset of informal Arabic with high dialectal content Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies June 2011 Portland OR USA 37\u201341."},{"key":"e_1_2_9_28_2","doi-asserted-by":"crossref","unstructured":"NabilM. Alaa El-Dien AlyM. andAtiyaA. ASTD: Arabic sentiment tweets dataset Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing September 2015 Lisbon Portugal https:\/\/doi.org\/10.18653\/v1\/D15-1299.","DOI":"10.18653\/v1\/D15-1299"},{"key":"e_1_2_9_29_2","unstructured":"ATDFS Large Arabic twitter data for sentiment analysis 2019 https:\/\/www.kaggle.com\/adelalharbi\/rogue-content-and-arabic-spammers-on-twitter."},{"key":"e_1_2_9_30_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4787"},{"key":"e_1_2_9_31_2","volume-title":"Iraqi Dialect versus Standard Arabic","author":"Khoshaba M. P.","year":"2006"},{"key":"e_1_2_9_32_2","unstructured":"AlyM.andAtiyaA. Labr: a large scale Arabic book reviews dataset 2 Proceedings of the 2013 51st Annual Meeting of the Association for Computational Linguistics August 2013 Sofia Bulgaria 494\u2013498."},{"key":"e_1_2_9_33_2","doi-asserted-by":"crossref","unstructured":"RosenthalS. FarraN. andNakovP. Semeval-2017 task 4: sentiment analysis in twitter Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017) August 2017 Vancouver Canada 502\u2013518.","DOI":"10.18653\/v1\/S17-2088"},{"key":"e_1_2_9_34_2","unstructured":"KwaikK. A. SaadM. ChatzikyriakidisS. andDobnikS. Shami: a corpus of levantine Arabic dialects Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) May 2018 Miyazaki Japan."},{"key":"e_1_2_9_35_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9030483"},{"key":"e_1_2_9_36_2","unstructured":"SocherR. PerelyginA. andJeanY. Recursive deep models for semantic compositionality over a sentiment treebank Proceedings of the 2013 Conference On Empirical Methods In Natural Language Processing (EMNLP) October 2013 Seattle WA USA."},{"key":"e_1_2_9_37_2","doi-asserted-by":"publisher","DOI":"10.15516\/cje.v18i1.1471"},{"key":"e_1_2_9_38_2","unstructured":"RossiR. G. MarcaciniR. M. andRezendeS. O. Benchmarking text collections for classification and clustering tasks 2013."},{"key":"e_1_2_9_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.03.045"},{"key":"e_1_2_9_40_2","doi-asserted-by":"publisher","DOI":"10.1108\/K-10-2016-0300"},{"key":"e_1_2_9_41_2","doi-asserted-by":"crossref","unstructured":"IyyerM. ManjunathaV. Boyd-GraberJ. andDaum\u00e9H. Deep unordered composition rivals syntactic methods for text classification 1 Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing July 2015 Beijing China 1681\u20131691.","DOI":"10.3115\/v1\/P15-1162"},{"key":"e_1_2_9_42_2","unstructured":"LinY. LeiH. WuJ. andLiX. An empirical study on sentiment classification of Chinese review using word embedding 2015 http:\/\/arxiv.org\/abs\/1511.01665."},{"key":"e_1_2_9_43_2","volume-title":"Sanders-Twitter Sentiment Corpus","author":"Sanders N. J.","year":"2011"},{"key":"e_1_2_9_44_2","unstructured":"WojatzkiM. RuppertE. HolschneiderS. ZeschT. andBiemannC. Germeval 2017: shared task on aspect-based sentiment in social media customer feedback 2017."},{"key":"e_1_2_9_45_2","doi-asserted-by":"publisher","DOI":"10.1177\/0165551516677911"},{"key":"e_1_2_9_46_2","doi-asserted-by":"publisher","DOI":"10.1002\/cae.22252"},{"key":"e_1_2_9_47_2","unstructured":"OrabyS. HarrisonV. ReedL. HernandezE. RiloffE. andWalkerM. Creating and characterizing a diverse corpus of sarcasm in dialogue 2017 http:\/\/arxiv.org\/abs\/1709.05404."},{"key":"e_1_2_9_48_2","unstructured":"MisraR. News headlines dataset for sarcasm detection 2018 https:\/\/www.kaggle.com\/rmisra\/newsheadlines-dataset-for-sarcasm-detection."},{"key":"e_1_2_9_49_2","doi-asserted-by":"crossref","unstructured":"BifetA.andFrankE. Sentiment knowledge discovery in twitter streaming data Proceedings of the 2010 International Conference on Discovery Science October 2010 Canberra Australia Springer 1\u201315 https:\/\/doi.org\/10.1007\/978-3-642-16184-1_1 2-s2.0-78650162978.","DOI":"10.1007\/978-3-642-16184-1_1"},{"key":"e_1_2_9_50_2","doi-asserted-by":"crossref","unstructured":"WanY.andGaoQ. An ensemble sentiment classification system of twitter data for airline services analysis Proceedings of the 2015 IEEE International Conference on Data Mining Workshop (ICDMW) November 2015 Atlantic City NJ USA IEEE 1318\u20131325 https:\/\/doi.org\/10.1109\/ICDMW.2015.7 2-s2.0-84964765892.","DOI":"10.1109\/ICDMW.2015.7"},{"key":"e_1_2_9_51_2","doi-asserted-by":"crossref","unstructured":"ChenL. C. BarronJ. T. PapandreouG. MurphyK. andYuilleA. L. Semantic image segmentation with task-specific edge detection using cnns and a discriminatively trained domain transform Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition June 2016 Las Vegas NV USA 4545\u20134554.","DOI":"10.1109\/CVPR.2016.492"},{"key":"e_1_2_9_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/bf00994018"},{"key":"e_1_2_9_53_2","doi-asserted-by":"crossref","unstructured":"AbdullaN. A. AhmedN. A. ShehabM. A. andAl-AyyoubM. Arabic sentiment analysis: lexicon-based and corpus-based Proceedings of the 2013 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT) December 2013 Amman Jordan IEEE 1\u20136 https:\/\/doi.org\/10.1109\/AEECT.2013.6716448 2-s2.0-84894191370.","DOI":"10.1109\/AEECT.2013.6716448"},{"key":"e_1_2_9_54_2","doi-asserted-by":"crossref","unstructured":"AlomariK. M. ElSherifH. M. andShaalanK. Arabic tweets sentimental analysis using machine learning Proceedings of the 2017 International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems June 2017 Arras France Springer 602\u2013610 https:\/\/doi.org\/10.1007\/978-3-319-60042-0_66 2-s2.0-85026409866.","DOI":"10.1007\/978-3-319-60042-0_66"},{"key":"e_1_2_9_55_2","doi-asserted-by":"crossref","unstructured":"AltowayanA. A.andTaoL. Word embeddings for Arabic sentiment analysis Proceedings of the 2016 IEEE International Conference on Big Data (Big Data) December 2016 Washington DC USA IEEE 3820\u20133825 https:\/\/doi.org\/10.1109\/BigData.2016.7841054 2-s2.0-85015256141.","DOI":"10.1109\/BigData.2016.7841054"},{"key":"e_1_2_9_56_2","unstructured":"ZhangY.andWallaceB. A sensitivity analysis of (and practitioners\u2019 guide to) convolutional neural networks for sentence classification 2015 http:\/\/arxiv.org\/abs\/1510.03820."},{"key":"e_1_2_9_57_2","volume-title":"Deep Learning with Keras","author":"Gulli A.","year":"2017"},{"key":"e_1_2_9_58_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.10.094"},{"key":"e_1_2_9_59_2","doi-asserted-by":"publisher","DOI":"10.3390\/fi11110229"},{"key":"e_1_2_9_60_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.10.117"},{"key":"e_1_2_9_61_2","unstructured":"MikolovT. SutskeverI. ChenK. CorradoG. S. andDeanJ. Distributed representations of words and phrases and their compositionality Proceedings of the 26th International Conference on Neural Information Processing Systems December 2013 Sydney Australia 3111\u20133119."}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/5538791.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/5538791.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/5538791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T11:20:19Z","timestamp":1722943219000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/5538791"}},"subtitle":[],"editor":[{"given":"Daniele","family":"Bibbo","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":61,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/5538791"],"URL":"https:\/\/doi.org\/10.1155\/2021\/5538791","archive":["Portico"],"relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"value":"1687-5265","type":"print"},{"value":"1687-5273","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2021-02-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-05-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"5538791"}}