{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:44:23Z","timestamp":1777697063907,"version":"3.51.4"},"reference-count":46,"publisher":"SAGE Publications","issue":"6","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":["Intelligent Decision Technologies"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:p>\n                    The widespread dissemination of false information on digital platforms has become a critical concern, particularly for low-resource languages like Bengali. Addressing this issue, the present study introduces a Hybrid Tri-Encoder model that utilizes three transformer-based encoders DistilBERT, mBERT, and BanglaBERT,\u00a0to process different components of a news article: its headline, a hybrid-summarized form of the content, and the complete article itself. The summarized version is generated using a two-step hybrid summarization strategy that combines YAKE-based extractive summarization with mT5-based abstractive summarization. This ensures the preservation of key terms along with semantic coherence for better representation. The outputs from the three encoders are combined to create a unified feature representation, which is then passed through a dense classification layer to determine the authenticity of the article. To address the class imbalance in the dataset, we employed a weighted loss function during training. Furthermore, this study incorporates LIME (Local Interpretable Model-agnostic Explanations),\u00a0a technique that approximates the model's behavior locally,\u00a0to generate instance-level interpretability for predictions. The experimental results confirm that the proposed method effectively distinguishes between genuine and fake news. The integration of explainability enhances model reliability, offering a transparent and robust solution for fake news detection in Bengali\n                    <jats:bold>.<\/jats:bold>\n                  <\/jats:p>","DOI":"10.1177\/18724981251384403","type":"journal-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T17:27:54Z","timestamp":1763659674000},"page":"3984-4003","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Hybrid Tri-Encoder model for fake news detection in Bengali with LIME-based explainability"],"prefix":"10.1177","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3581-7428","authenticated-orcid":false,"given":"Karan Kumar","family":"Yadav","sequence":"first","affiliation":[{"name":"National Institute of Technology Hamirpur"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0941-9444","authenticated-orcid":false,"given":"Garima","family":"Thakur","sequence":"additional","affiliation":[{"name":"National Institute of Technology Hamirpur"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8105-4809","authenticated-orcid":false,"given":"Jyoti","family":"Srivastava","sequence":"additional","affiliation":[{"name":"National Institute of Technology Hamirpur"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2025,11,20]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"931","article-title":"REGAC: multi-class offensive content identification using graphical approach","volume":"52","author":"Chinivar S","year":"2025","unstructured":"Chinivar S, Roopa MS, Arunalatha JS, et\u00a0al. REGAC: multi-class offensive content identification using graphical approach. IAENG Int J Comput Sci 2025; 52: 931\u2013952.","journal-title":"IAENG Int J Comput Sci"},{"key":"e_1_3_2_3_2","first-page":"2862","volume-title":"Banfakenews: a dataset for detecting fake news in banglaLREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings","author":"Hossain MZ","unstructured":"Hossain MZ, Rahman MA, Islam MS, et\u00a0al. Banfakenews: a dataset for detecting fake news in bangla. In: LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings, 2020, pp.2862\u20132871."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2023.1320800"},{"key":"e_1_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Chowdhury AS Shahariar GM Aziz AT et\u00a0al. Tackling Fake News in Bengali: Unraveling the Impact of Summarization vs. Augmentation on Pre-trained Language Models https:\/\/arxiv.org\/pdf\/2307.06979 (2023 accessed 9 October 2025).","DOI":"10.1007\/s42979-025-04398-z"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66046-8_38"},{"key":"e_1_3_2_7_2","first-page":"959","volume-title":"Bangla fake news detection using machine learning, deep learning and transformer modelsProceedings of 2022 25th International Conference on Computer and Information Technology, ICCIT 2022","author":"Rasel RI","unstructured":"Rasel RI, Zihad AH, Sultana N, et\u00a0al. Bangla fake news detection using machine learning, deep learning and transformer models. In: Proceedings of 2022 25th International Conference on Computer and Information Technology, ICCIT 2022, 2022, pp.959\u2013964."},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT51525.2021.9580035"},{"key":"e_1_3_2_9_2","first-page":"97","article-title":"Breaking the curse of class imbalance: bangla text classification","volume":"21","author":"Rafi-Ur-Rashid M","year":"2022","unstructured":"Rafi-Ur-Rashid M, Mahbub M, Adnan MA. Breaking the curse of class imbalance: bangla text classification. Trans Asian Low-Resour Language Inform Process 2022; 21: 97.","journal-title":"Trans Asian Low-Resour Language Inform Process"},{"key":"e_1_3_2_10_2","unstructured":"Alam T Khan A Alam F. Bangla Text Classification using Transformers https:\/\/arxiv.org\/pdf\/2011.04446 (2020 accessed 6 October 2025)."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106087"},{"key":"e_1_3_2_12_2","first-page":"1135","volume-title":"Why should i trust you?\u2019 explaining the predictions of any classifierProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Ribeiro MT","unstructured":"Ribeiro MT, Singh S, Guestrin C. Why should i trust you?\u2019 explaining the predictions of any classifier. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016 13-17-August-2016, pp.1135\u20131144."},{"key":"e_1_3_2_13_2","first-page":"281","volume-title":"Bengali fake news detection2020 IEEE 10th International Conference on Intelligent Systems, IS 2020 \u2013 Proceedings","author":"Islam F","unstructured":"Islam F, Alam MM, Shahadat Hossain SM, et\u00a0al. Bengali fake news detection. In: 2020 IEEE 10th International Conference on Intelligent Systems, IS 2020 \u2013 Proceedings, 2020, pp.281\u2013287."},{"key":"e_1_3_2_14_2","first-page":"1428","volume-title":"Semi-Supervised based bangla fake review detection: a comparative analysisProceedings of 8th International Conference on Inventive Computation Technologies, ICICT 2025","author":"Absar N","unstructured":"Absar N, Mahmud T, Hanip A, et\u00a0al. Semi-Supervised based bangla fake review detection: a comparative analysis. In: Proceedings of 8th International Conference on Inventive Computation Technologies, ICICT 2025, 2025, pp.1428\u20131433."},{"key":"e_1_3_2_15_2","first-page":"100007","article-title":"Fake news detection: a hybrid CNN-RNN based deep learning approach","volume":"1","author":"Nasir JA","year":"2021","unstructured":"Nasir JA, Khan OS, Varlamis I. Fake news detection: a hybrid CNN-RNN based deep learning approach. Int J Inform Manag Data Insights 2021; 1: 100007.","journal-title":"Int J Inform Manag Data Insights"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107614"},{"key":"e_1_3_2_17_2","volume-title":"Are You Misinformed? A Study of COVID-Related Fake News in Bengali on FacebookProceedings of ACM Conference (Conference\u201917)","volume":"1","author":"Pranto PB","unstructured":"Pranto PB, Navid SZ-U-H, Dey P, et\u00a0al. Are You Misinformed? A Study of COVID-Related Fake News in Bengali on Facebook. In: Proceedings of ACM Conference (Conference\u201917); 1, https:\/\/arxiv.org\/pdf\/2203.11669 (2022, accessed 6 October 2025)."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110642"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106877"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16669-z"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/NCIM59001.2023.10212799"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.measen.2022.100495"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114171"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119017"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2019.12.005"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2025.102469"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2025.3568872"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.techfore.2023.122746"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.osnem.2023.100249"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2023.108866"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.108344"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-17301-w"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-023-00788-y"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-022-07215-4"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06450-4"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11782-3"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3216892"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106688"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCUBEA54992.2022.10011096"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT51525.2021.9579777"},{"key":"e_1_3_2_41_2","first-page":"1318","volume-title":"BanglaBERT: language model pretraining and benchmarks for low-resource language understanding evaluation in banglaFindings of the Association for Computational Linguistics: NAACL 2022 - Findings","author":"Bhattacharjee A","unstructured":"Bhattacharjee A, Hasan T, Uddin Ahmad W, et\u00a0al. BanglaBERT: language model pretraining and benchmarks for low-resource language understanding evaluation in bangla. In: Findings of the Association for Computational Linguistics: NAACL 2022 - Findings, 2021, pp.1318\u20131327."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3572051"},{"key":"e_1_3_2_43_2","unstructured":"Shibu HM Datta S Miah M et\u00a0al. From Scarcity to Capability: Empowering Fake News Detection in Low-Resource Languages with LLMs https:\/\/arxiv.org\/pdf\/2501.09604 (2025 accessed 7 October 2025)."},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3457860"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2025.3571024"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.3390\/app12178398"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-2445-3_51"}],"container-title":["Intelligent Decision Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/18724981251384403","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/18724981251384403","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/18724981251384403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:21:45Z","timestamp":1777454505000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/18724981251384403"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":46,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1177\/18724981251384403"],"URL":"https:\/\/doi.org\/10.1177\/18724981251384403","relation":{},"ISSN":["1872-4981","1875-8843"],"issn-type":[{"value":"1872-4981","type":"print"},{"value":"1875-8843","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}