{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T07:34:46Z","timestamp":1770363286483,"version":"3.49.0"},"reference-count":15,"publisher":"SAGE Publications","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2023,3,9]]},"abstract":"<jats:p>Aspect-based sentiment analysis (ABSA) is a challenging task of sentiment analysis that aims at extracting the discussed aspects and identifying the sentiment corresponding to each aspect. We can distinguish three main ABSA tasks: aspect term extraction, aspect category detection (ACD), and aspect sentiment classification. Most Arabic ABSA research has relied on rule-based or machine learning-based methods, with little attention to deep learning techniques. Moreover, most existing Arabic deep learning models are initialized using context-free word embedding models, which cannot handle polysemy. Therefore, this paper aims at overcoming the limitations mentioned above by exploiting the contextualized embeddings from pre-trained language models, specifically the BERT model. Besides, we combine BERT with a temporal convolutional network and a bidirectional gated recurrent unit network in order to enhance the extracted semantic and contextual features. The evaluation results show that the proposed method has outperformed the baseline and other models by achieving an F1-score of 84.58% for the Arabic ACD task. Furthermore, a set of methods are examined to handle the class imbalance in the used dataset. Data augmentation based on back-translation has shown its effectiveness through enhancing the first results by an overall improvement of more than 3% in terms of F1-score.<\/jats:p>","DOI":"10.3233\/jifs-221214","type":"journal-article","created":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T10:40:29Z","timestamp":1669977629000},"page":"4123-4136","source":"Crossref","is-referenced-by-count":14,"title":["Combining BERT with TCN-BiGRU for enhancing Arabic aspect category detection"],"prefix":"10.1177","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0964-3876","authenticated-orcid":false,"given":"Rajae","family":"Bensoltane","sequence":"first","affiliation":[{"name":"IRF-SIC Laboratory, Faculty of Science, Ibn Zohr University, FP-Agadir, Morocco"}]},{"given":"Taher","family":"Zaki","sequence":"additional","affiliation":[{"name":"IRF-SIC Laboratory, Faculty of Science, Ibn Zohr University, FP-Agadir, Morocco"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-221214_ref4","doi-asserted-by":"crossref","unstructured":"Baragash R. and Aldowah H. , Sentiment analysis in higher education: a systematic mapping review. in Journal of Physics: Conference Series, 2021, IOP Publishing.","DOI":"10.1088\/1742-6596\/1860\/1\/012002"},{"issue":"1","key":"10.3233\/JIFS-221214_ref5","first-page":"14","article-title":"A Novel Deep Learning ArCAR System for Arabic Text Recognition with Character-Level Representation","volume":"2","author":"Muaad","year":"2022","journal-title":"Computer Sciences & Mathematics Forum"},{"key":"10.3233\/JIFS-221214_ref6","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1016\/j.future.2020.05.034","article-title":"A review of sentiment analysis research in Arabic language","volume":"112","author":"Oueslati","year":"2020","journal-title":"Future Generation Computer Systems"},{"key":"10.3233\/JIFS-221214_ref12","doi-asserted-by":"crossref","first-page":"101224","DOI":"10.1016\/j.csl.2021.101224","article-title":"Enhancing Arabic aspect-based sentiment analysis using deep learning models","volume":"69","author":"Al-Dabet","year":"2021","journal-title":"Computer Speech & Language"},{"issue":"1","key":"10.3233\/JIFS-221214_ref13","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1007\/s13278-021-00794-4","article-title":"Towards Arabic aspect-based sentiment analysis: a transfer learning-based approach","volume":"12","author":"Bensoltane","year":"2021","journal-title":"Social Network Analysis and Mining"},{"key":"10.3233\/JIFS-221214_ref15","doi-asserted-by":"crossref","unstructured":"Zheng S. and Yang M. , A new method of improving BERT for text classification. in International Conference on Intelligent Science and Big Data Engineering, 2019, Springer.","DOI":"10.1007\/978-3-030-36204-1_37"},{"key":"10.3233\/JIFS-221214_ref16","doi-asserted-by":"crossref","first-page":"154290","DOI":"10.1109\/ACCESS.2019.2946594","article-title":"Target-dependent sentiment classification with BERT","volume":"7","author":"Gao","year":"2019","journal-title":"IEEE Access"},{"key":"10.3233\/JIFS-221214_ref17","doi-asserted-by":"crossref","first-page":"91537","DOI":"10.1109\/ACCESS.2021.3092261","article-title":"Classical Arabic named entity recognition using variant deep neural network architectures and BERT","volume":"9","author":"Alsaaran","year":"2021","journal-title":"IEEE Access"},{"key":"10.3233\/JIFS-221214_ref21","unstructured":"Vaswani A. , Shazeer N. , Parmar N. , Uszkoreit J. , Jones L. , Gomez A.N. , Kaiser \u0141. and Polosukhin I. , Attention is all you need. Advances in Neural Information Processing Systems 30 (2017)."},{"issue":"3","key":"10.3233\/JIFS-221214_ref25","first-page":"327","article-title":"Framework for Affective News Analysis of Arabic News: 2014 Gaza Attacks Case Study","volume":"23","author":"Al-Ayyoub","year":"2017","journal-title":"J UCS"},{"key":"10.3233\/JIFS-221214_ref28","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1016\/j.procs.2017.10.117","article-title":"AraVec: A set of Arabic Word Embedding Models for use in Arabic NLP","volume":"117","author":"Soliman","year":"2017","journal-title":"Procedia Computer Science"},{"key":"10.3233\/JIFS-221214_ref30","doi-asserted-by":"crossref","first-page":"37075","DOI":"10.1109\/ACCESS.2021.3062654","article-title":"Refined global word embeddings based on sentiment concept for sentiment analysis","volume":"9","author":"Wang","year":"2021","journal-title":"IEEE Access"},{"issue":"4","key":"10.3233\/JIFS-221214_ref31","doi-asserted-by":"crossref","first-page":"391","DOI":"10.17791\/jcs.2017.18.4.391","article-title":"A comparison of oversampling methods on imbalanced topic classification of Korean news articles","volume":"18","author":"Suh","year":"2017","journal-title":"Journal of Cognitive Science"},{"key":"10.3233\/JIFS-221214_ref32","doi-asserted-by":"crossref","first-page":"736","DOI":"10.1016\/j.procs.2019.09.229","article-title":"Dealing with data imbalance in text classification","volume":"159","author":"Padurariu","year":"2019","journal-title":"Procedia Computer Science"},{"issue":"8","key":"10.3233\/JIFS-221214_ref36","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-221214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T06:17:34Z","timestamp":1769667454000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-221214"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,9]]},"references-count":15,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.3233\/jifs-221214","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,9]]}}}