{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T20:44:10Z","timestamp":1771015450005,"version":"3.50.1"},"reference-count":29,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2025,2,10]],"date-time":"2025-02-10T00:00:00Z","timestamp":1739145600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Deanship of Research and Graduate Studies at King Khalid University, KSA","award":["GRP\/50\/45"],"award-info":[{"award-number":["GRP\/50\/45"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>The COVID-19 pandemic has generated a vast corpus of online conversations regarding vaccines, predominantly on social media platforms like X (formerly known as Twitter). However, analyzing sentiment in Arabic text is challenging due to the diverse dialects and lack of readily available sentiment analysis resources for the Arabic language. This paper proposes an explainable Deep Learning (DL) approach designed for sentiment analysis of Arabic tweets related to COVID-19 vaccinations. The proposed approach utilizes a Bidirectional Long Short-Term Memory (BiLSTM) network with Multi-Self-Attention (MSA) mechanism for capturing contextual impacts over long spans within the tweets, while having the sequential nature of Arabic text constructively learned by the BiLSTM model. Moreover, the XLNet embeddings are utilized to feed contextual information into the model. Subsequently, two essential Explainable Artificial Intelligence (XAI) methods, namely Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP), have been employed for gaining further insights into the features\u2019 contributions to the overall model performance and accordingly achieving reasonable interpretation of the model\u2019s output. Obtained experimental results indicate that the combined XLNet with BiLSTM model outperforms other implemented state-of-the-art methods, achieving an accuracy of 93.2% and an F-measure of 92% for average sentiment classification. The integration of LIME and SHAP techniques not only enhanced the model\u2019s interpretability, but also provided detailed insights into the factors that influence the classification of emotions. These findings underscore the model\u2019s effectiveness and reliability for sentiment analysis in low-resource languages such as Arabic.<\/jats:p>","DOI":"10.3390\/bdcc9020037","type":"journal-article","created":{"date-parts":[[2025,2,10]],"date-time":"2025-02-10T09:29:26Z","timestamp":1739179766000},"page":"37","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Explainable Deep Learning for COVID-19 Vaccine Sentiment in Arabic Tweets Using Multi-Self-Attention BiLSTM with XLNet"],"prefix":"10.3390","volume":"9","author":[{"given":"Asmaa Hashem","family":"Sweidan","sequence":"first","affiliation":[{"name":"Faculty of Computers and Artificial Intelligence, Fayoum University, Fayoum 63514, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6553-4159","authenticated-orcid":false,"given":"Nashwa","family":"El-Bendary","sequence":"additional","affiliation":[{"name":"College of Computing and Information Technology, Arab Academy for Science, Technology, and Maritime Transport (AASTMT), Aswan 81516, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3067-7173","authenticated-orcid":false,"given":"Shereen A.","family":"Taie","sequence":"additional","affiliation":[{"name":"Faculty of Computers and Artificial Intelligence, Fayoum University, Fayoum 63514, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6387-642X","authenticated-orcid":false,"given":"Amira M.","family":"Idrees","sequence":"additional","affiliation":[{"name":"College of Business, King Khalid University, Abha 61421, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Esraa","family":"Elhariri","sequence":"additional","affiliation":[{"name":"Faculty of Computers and Artificial Intelligence, Fayoum University, Fayoum 63514, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,2,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1007\/s13278-022-00946-0","article-title":"Automatically detecting and understanding the perception of COVID-19 vaccination: A middle east case study","volume":"12","author":"Aljedaani","year":"2022","journal-title":"Soc. Netw. Anal. Min."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e1507","DOI":"10.7717\/peerj-cs.1507","article-title":"ASAVACT: Arabic sentiment analysis for vaccine-related COVID-19 tweets using deep learning","volume":"9","author":"Alhumoud","year":"2023","journal-title":"PeerJ Comput. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"20552076231205714","DOI":"10.1177\/20552076231205714","article-title":"The spread of COVID-19 vaccine information in Arabic on YouTube: A network exposure study","volume":"9","author":"Zeid","year":"2023","journal-title":"Digit. Health"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"51755","DOI":"10.1007\/s11042-023-17437-9","article-title":"CBMAFM: CNN-BiLSTM Multi-Attention Fusion Mechanism for Sentiment Classification","volume":"83","author":"Wankhade","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref_5","first-page":"255","article-title":"Sentiment Analysis with an Integrated Model of BERT and Bi-LSTM Based on Multi-Head Attention Mechanism","volume":"50","author":"Wang","year":"2023","journal-title":"Int. J. Comput. Sci."},{"key":"ref_6","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J.G., Salakhutdinov, R., and Le, Q.V. (2019, January 8\u201314). XLNet: Generalized Autoregressive Pretraining for Language Understanding. Proceedings of the Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD\u201916), San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_9","unstructured":"Shrikumar, A., Greenside, P., Shcherbina, A., and Kundaje, A. (2017). Not Just a Black Box: Learning Important Features Through Propagating Activation Differences. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Aljameel, S.S., Alabbad, D.A., Alzahrani, N.A., Alqarni, S.M., Alamoudi, F.A., Babili, L.M., Aljaafary, S.K., and Alshamrani, F.M. (2021). A Sentiment Analysis Approach to Predict an Individual\u2019s Awareness of the Precautionary Procedures to Prevent COVID-19 Outbreaks in Saudi Arabia. Int. J. Environ. Res. Public Health, 18.","DOI":"10.3390\/ijerph18010218"},{"key":"ref_11","unstructured":"Calzolari, N., B\u00e9chet, F., Blache, P., Choukri, K., Cieri, C., Declerck, T., Goggi, S., Isahara, H., Maegaard, B., and Mariani, J. (2022, January 20\u201325). ArCovidVac: Analyzing Arabic Tweets About COVID-19 Vaccination. Proceedings of the Thirteenth Language Resources and Evaluation Conference, Marseille, France."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Alhazmi, H. (2022). Arabic Twitter conversation dataset about the COVID-19 vaccine. Data, 7.","DOI":"10.3390\/data7110152"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"M\u00fcller, M., Salath\u00e9, M., and Kummervold, P. (2023). COVID-Twitter-BERT: A natural language processing model to analyse COVID-19 content on Twitter. Front. Artif. Intell., 6.","DOI":"10.3389\/frai.2023.1023281"},{"key":"ref_14","unstructured":"Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019, January 2\u20137). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, MN, USA."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1186\/s13677-024-00644-6","article-title":"Stacked-CNN-BiLSTM-COVID: An effective stacked ensemble deep learning framework for sentiment analysis of Arabic COVID-19 tweets","volume":"13","author":"Abdelhady","year":"2024","journal-title":"J. Cloud Comput."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"55367","DOI":"10.1109\/ACCESS.2024.3389655","article-title":"Detecting reported side effects of COVID-19 vaccines from Arabic twitter (X) data","volume":"12","author":"Alhumayani","year":"2024","journal-title":"IEEE Access"},{"key":"ref_17","first-page":"1216","article-title":"Bidirectional Encoder Representations from Transformers for the COVID-19 vaccine stance classification","volume":"Volume 3159","author":"Mehta","year":"2021","journal-title":"Proceedings of the Working Notes of FIRE 2021\u2014Forum for Information Retrieval Evaluation"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Basu, M., Poddar, S., Ghosh, S., and Ghosh, K. (2021, January 13\u201317). Overview of the FIRE 2021 track: Information Retrieval from Microblogs during Disasters (IRMiDis). Proceedings of the FIRE\u201921: Proceedings of the 13th Annual Meeting of the Forum for Information Retrieval Evaluation, Virtual.","DOI":"10.1145\/3503162.3503174"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Kumar, A., Singh, J.P., and Singh, A.K. (2023). Explainable BERT-LSTM Stacking for Sentiment Analysis of COVID-19 Vaccination. IEEE Trans. Comput. Soc. Syst., 1\u201311.","DOI":"10.1109\/TCSS.2023.3329664"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.patrec.2024.01.001","article-title":"A multi-aspect framework for explainable sentiment analysis","volume":"178","author":"Prakash","year":"2024","journal-title":"Pattern Recognit. Lett."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Sweidan, A.H., El-Bendary, N., and Elhariri, E. (2024). Autoregressive Feature Extraction with Topic Modeling for Aspect-based Sentiment Analysis of Arabic as a Low-resource Language. ACM Transactions on Asian and Low-Resource Language Information Processing, Association for Computing Machinery.","DOI":"10.1145\/3638050"},{"key":"ref_22","unstructured":"Hamed, I., Vu, N.T., and Abdennadher, S. (2020, January 11\u201316). Arzen: A speech corpus for code-switched egyptian arabic-english. Proceedings of the Twelfth Language Resources and Evaluation Conference, Marseille, France."},{"key":"ref_23","unstructured":"Bouamor, H., Habash, N., and Oflazer, K. (2014, January 26\u201331). A Multidialectal Parallel Corpus of Arabic. Proceedings of the LREC, 2014, Reykjavik, Iceland."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Taghva, K., Elkhoury, R., and Coombs, J. (2005, January 4\u20136). Arabic stemming without a root dictionary. Proceedings of the International Conference on Information Technology: Coding and Computing (ITCC\u201905)-Volume II, Las Vegas, NV, USA.","DOI":"10.1109\/ITCC.2005.90"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"101805","DOI":"10.1016\/j.inffus.2023.101805","article-title":"Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence","volume":"99","author":"Ali","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"963","DOI":"10.1007\/s43681-022-00217-w","article-title":"Explainable AI lacks regulative reasons: Why AI and human decision-making are not equally opaque","volume":"3","author":"Peters","year":"2023","journal-title":"AI Ethics"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"30164","DOI":"10.1109\/ACCESS.2024.3368377","article-title":"Explainable AI for Intrusion Detection Systems: LIME and SHAP Applicability on Multi-Layer Perceptron","volume":"12","author":"Gaspar","year":"2024","journal-title":"IEEE Access"},{"key":"ref_28","unstructured":"Alhazmi, H. (2024, July 20). Arabic Twitter Conversation Dataset about COVID-19 Vaccine. Available online: https:\/\/data.mendeley.com\/datasets\/zmwfnsms9n\/1."},{"key":"ref_29","unstructured":"Mubarak, H., Hassan, S., Chowdhury, S.A., and Alam, F. (2024, July 20). ArCovidVac: Arabic COVID-19 Vaccine Sentiment Dataset. Available online: https:\/\/huggingface.co\/datasets\/arbml\/ArCovidVac."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/2\/37\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:30:31Z","timestamp":1760027431000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/2\/37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,10]]},"references-count":29,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["bdcc9020037"],"URL":"https:\/\/doi.org\/10.3390\/bdcc9020037","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,10]]}}}