{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T18:20:37Z","timestamp":1787768437633,"version":"build-2784847793"},"reference-count":40,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>The rapid spread of misinformation in Arabic news headlines poses a growing challenge to digital media integrity, given the scarcity of Arabic-specific automated detection tools relative to English-centric systems. Headlines are brief and context-limited, yet their lexical and stylistic patterns encode strong cues of veracity or deception, making headline-only detection practically urgent and linguistically tractable. This study investigates automatic fake-news detection using Arabic headlines, leveraging five heterogeneous corpora and their unified combination. English sets were incorporated via neural machine translation with light post-normalization that preserves stylistic cues, yielding a heterogeneous cross-domain corpus. A systematic analysis of linguistic and stylistic indicators reveals stable asymmetries between fake and real headlines that recur across domains. We evaluate approaches from classical TF-IDF baselines to Arabic-specialized transformers, and propose a late-fusion strategy coupling transformer representations with discriminative engineered features. Transformers consistently outperform classical baselines, confirming that subword representations effectively capture semantic and stylistic regularities in short Arabic texts. Late fusion yields statistically significant improvements only on datasets with prominent numeric or temporal cues; on the unified corpus, McNemar\u2019s exact test confirms that fusion gains are non-significant, indicating that subword encoders already internalize the surface-level cues captured by the engineered features. Even where accuracy differences are marginal, interpretable features enhance explainability.<\/jats:p>","DOI":"10.1371\/journal.pone.0356823","type":"journal-article","created":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T17:51:19Z","timestamp":1787766679000},"page":"e0356823","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Linguistic markers of deception in Arabic news headlines: A cross-corpus study of stylistic and numeric features"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4486-3110","authenticated-orcid":true,"given":"Eman Salamah","family":"Albtoush","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2972-3523","authenticated-orcid":true,"given":"Keng Hoon","family":"Gan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saif Addeen A.","family":"Alrababah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,26]]},"reference":[{"key":"pone.0356823.ref001","unstructured":"Julian G. What are the most spoken languages in the world. In: Ethnologue: languages of the world, vol. 31; 2020. 38 p."},{"key":"pone.0356823.ref002","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/07434618.2025.2519413","article-title":"Development of an Arabic core vocabulary list for children utilizing augmentative and alternative communication","author":"MM Alkhaldi","year":"2025","journal-title":"Augment Altern Commun"},{"issue":"1","key":"pone.0356823.ref003","first-page":"44","article-title":"Innovative word formation and pluralization processes in Arabic: a systematic review","volume":"8","author":"R Al-Jarf","year":"2026","journal-title":"JHSSS"},{"key":"pone.0356823.ref004","first-page":"66","article-title":"Lexical and lexical-semantic comparisons of classical Arabic and dialects","volume":"11","author":"H Abouzahr","year":"2025","journal-title":"IJAL"},{"key":"pone.0356823.ref005","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.2693","article-title":"Fake news detection: state-of-the-art review and advances with attention to Arabic language aspects","volume":"11","author":"ES Albtoush","year":"2025","journal-title":"PeerJ Comput Sci"},{"key":"pone.0356823.ref006","volume-title":"Novel weapons: the invasion of fake news and the evolution of political news ecosystems","author":"S Strasser","year":"2022"},{"issue":"1","key":"pone.0356823.ref007","doi-asserted-by":"crossref","first-page":"30463","DOI":"10.1038\/s41598-024-82111-5","article-title":"Novel approach for Arabic fake news classification using embedding from large language features with CNN-LSTM ensemble model and explainable AI","volume":"14","author":"O Ibrahim Aboulola","year":"2024","journal-title":"Sci Rep"},{"key":"pone.0356823.ref008","volume-title":"King salman rumor","author":"FCP Sawab","year":"2025"},{"key":"pone.0356823.ref009","volume-title":"WhatsApp did not recently change its privacy settings","author":"Misbar Fact-Checking Platform","year":"2021"},{"key":"pone.0356823.ref010","unstructured":"Fullfact H, editor. The WHO has not declared the Covid-19 pandemic over. fullfact Fact checker; 2023. Available from: https:\/\/fullfact.org\/health\/who-covid-pandemic-over\/"},{"issue":"1","key":"pone.0356823.ref011","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1057\/s41599-025-05215-x","article-title":"Hyperbole in Arabic YouTube: a pragmalinguistic study of artificial intelligence discourse","volume":"12","author":"RS Alsharif","year":"2025","journal-title":"Humanit Soc Sci Commun"},{"key":"pone.0356823.ref012","doi-asserted-by":"crossref","first-page":"162009","DOI":"10.1109\/ACCESS.2025.3606114","article-title":"Evaluation of machine learning and deep learning models for fake news detection in Arabic headlines","volume":"13","author":"ES Albtoush","year":"2025","journal-title":"IEEE Access"},{"key":"pone.0356823.ref013","volume-title":"Arabic terms belonging to the root","author":"Contributors W. wiki","year":"2025"},{"issue":"1","key":"pone.0356823.ref014","doi-asserted-by":"crossref","first-page":"836","DOI":"10.11591\/ijece.v15i1.pp836-845","article-title":"Arabic fake news detection using hybrid contextual features","volume":"15","author":"HM Turki","year":"2025","journal-title":"IJECE"},{"issue":"1","key":"pone.0356823.ref015","article-title":"Arabic fake news detection techniques: a review","volume":"18","author":"MA Abbas","year":"2026","journal-title":"J Intell Syst Internet Things"},{"issue":"1","key":"pone.0356823.ref016","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1007\/s13278-024-01370-2","article-title":"Fake-news detection: a survey of evaluation Arabic datasets","volume":"14","author":"M Abbas Yousef","year":"2024","journal-title":"Soc Netw Anal Min"},{"key":"pone.0356823.ref017","doi-asserted-by":"crossref","first-page":"108141","DOI":"10.1016\/j.dib.2022.108141","article-title":"AFND: Arabic fake news dataset for the detection and classification of articles credibility","volume":"42","author":"A Khalil","year":"2022","journal-title":"Data Brief"},{"key":"pone.0356823.ref018","doi-asserted-by":"crossref","unstructured":"Khouja J. Stance prediction and claim verification: an Arabic perspective. arXiv:200510410 [Preprint]. 2020.","DOI":"10.18653\/v1\/2020.fever-1.2"},{"issue":"8","key":"pone.0356823.ref019","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/s44443-025-00192-2","article-title":"A new stemming model based on data generation to enhance Arabic information retrieval","volume":"37","author":"SM Yaseen","year":"2025","journal-title":"J King Saud Univ Comput Inf Sci"},{"issue":"12","key":"pone.0356823.ref020","doi-asserted-by":"crossref","first-page":"576","DOI":"10.3390\/info13120576","article-title":"A comparative study of machine learning and deep learning techniques for fake news detection","volume":"13","author":"J Alghamdi","year":"2022","journal-title":"Information"},{"key":"pone.0356823.ref021","doi-asserted-by":"crossref","first-page":"156695","DOI":"10.1109\/ACCESS.2020.3019735","article-title":"Fake news stance detection using deep learning architecture (CNN-LSTM)","volume":"8","author":"M Umer","year":"2020","journal-title":"IEEE Access"},{"key":"pone.0356823.ref022","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.future.2020.11.022","article-title":"An ensemble machine learning approach through effective feature extraction to classify fake news","volume":"117","author":"S Hakak","year":"2021","journal-title":"Future Gener Comput Syst"},{"key":"pone.0356823.ref023","doi-asserted-by":"crossref","unstructured":"Pake TU, Pachareney U. Fine-tuning strategies for transformers. 2025 4th International Conference on Sentiment Analysis and Deep Learning (ICSADL). IEEE; 2025. p. 670\u20135.","DOI":"10.1109\/ICSADL65848.2025.10933255"},{"issue":"1","key":"pone.0356823.ref024","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1038\/s41562-024-02067-4","article-title":"Sharing without clicking on news in social media","volume":"9","author":"SS Sundar","year":"2025","journal-title":"Nat Hum Behav"},{"key":"pone.0356823.ref025","unstructured":"Saadany H, Mohamed E, Orasan C. Fake or real? A study of Arabic satirical fake news. arXiv:201100452 [Preprint]. 2020."},{"issue":"18","key":"pone.0356823.ref026","doi-asserted-by":"crossref","first-page":"16019","DOI":"10.1007\/s00521-022-07206-4","article-title":"Arabic fake news detection based on deep contextualized embedding models","volume":"34","author":"AB Nassif","year":"2022","journal-title":"Neural Comput Appl"},{"key":"pone.0356823.ref027","article-title":"Predictive modeling for Arabic fake news detection: leveraging language model embeddings and stacked ensemble","author":"M Umer","year":"2024","journal-title":"ACM Trans Asian Low-Resour Lang Inf Process"},{"issue":"1","key":"pone.0356823.ref028","doi-asserted-by":"crossref","first-page":"5516945","DOI":"10.1155\/2021\/5516945","article-title":"Arabic fake news detection: comparative study of neural networks and transformer\u2010based approaches","volume":"2021","author":"M Al-Yahya","year":"2021","journal-title":"Complexity"},{"key":"pone.0356823.ref029","doi-asserted-by":"crossref","first-page":"128078","DOI":"10.1016\/j.neucom.2024.128078","article-title":"Linguistic feature fusion for Arabic fake news detection and named entity recognition using reinforcement learning and swarm optimization","volume":"598","author":"A Dahou","year":"2024","journal-title":"Neurocomputing"},{"issue":"18","key":"pone.0356823.ref030","doi-asserted-by":"crossref","first-page":"2941","DOI":"10.3390\/math12182941","article-title":"Pre-trained language model ensemble for Arabic fake news detection","volume":"12","author":"L Al-Zahrani","year":"2024","journal-title":"Mathematics"},{"issue":"4","key":"pone.0356823.ref031","doi-asserted-by":"crossref","first-page":"3951","DOI":"10.11591\/ijece.v12i4.pp3951-3959","article-title":"Fake news detection for Arabic headlines-articles news data using deep learning","volume":"12","author":"H Najadat","year":"2022","journal-title":"IJECE"},{"key":"pone.0356823.ref032","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1016\/j.procs.2022.03.088","article-title":"Building an optimal dataset for arabic fake news detection","volume":"201","author":"MA Bsoul","year":"2022","journal-title":"Procedia Comput Sci"},{"issue":"8","key":"pone.0356823.ref033","doi-asserted-by":"crossref","first-page":"10453","DOI":"10.1007\/s13369-021-06449-y","article-title":"Arabic fake news detection based on textual analysis","volume":"47","author":"H Himdi","year":"2022","journal-title":"Arab J Sci Eng"},{"issue":"3","key":"pone.0356823.ref034","doi-asserted-by":"crossref","DOI":"10.52866\/ijcsm.2024.05.03.049","article-title":"Approach for detecting Arabic fake news using deep learning","volume":"5","author":"K Shaker","year":"2024","journal-title":"Iraqi J Comput Sci Math"},{"key":"pone.0356823.ref035","doi-asserted-by":"crossref","unstructured":"AlZaid A, Alkhayyal MK, Dajam TA, Khan MB. Towards an explainable framework for Arabic fake news detection: a systematic review. 2026 IEEE 15th International Conference on Communication Systems and Network Technologies (CSNT). IEEE; 2026. p. 1521\u20136.","DOI":"10.1109\/CSNT69054.2026.11502406"},{"key":"pone.0356823.ref036","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.2432","article-title":"VERA-ARAB: unveiling the Arabic tweets credibility by constructing balanced news dataset for veracity analysis","volume":"10","author":"MA Mostafa","year":"2024","journal-title":"PeerJ Comput Sci"},{"key":"pone.0356823.ref037","doi-asserted-by":"crossref","unstructured":"Wang WY. \u201cLiar, Liar Pants on Fire\u201d: a new benchmark dataset for fake news detection. arXiv:170500648 [Preprint]. 2017. https:\/\/doi.org\/10.48550\/arXiv.1705.00648","DOI":"10.18653\/v1\/P17-2067"},{"issue":"4","key":"pone.0356823.ref038","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1109\/TCSS.2021.3068519","article-title":"WELFake: Word embedding over linguistic features for fake news detection","volume":"8","author":"PK Verma","year":"2021","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"pone.0356823.ref039","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ. Bleu: a method for automatic evaluation of machine translation. Proceedings of the 40th annual meeting of the Association for Computational Linguistics; 2002. p. 311\u20138.","DOI":"10.3115\/1073083.1073135"},{"issue":"9","key":"pone.0356823.ref040","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"He Haibo","year":"2009","journal-title":"IEEE Trans Knowl Data Eng"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0356823","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T17:51:26Z","timestamp":1787766686000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0356823"}},"subtitle":[],"editor":[{"given":"Dhamyaa Abbas","family":"Nasrawi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,26]]},"references-count":40,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,26]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0356823","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,26]]}}}