{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T22:17:23Z","timestamp":1768342643199,"version":"3.49.0"},"reference-count":36,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T00:00:00Z","timestamp":1745798400000},"content-version":"vor","delay-in-days":117,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,17]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Detecting fake news early is challenging due to the absence of labeled articles for emerging events in training data. To address this, we propose a Disentangled Event-Agnostic Representation (DEAR) learning approach. Our method begins with a BERT-based adaptive multi-grained semantic encoder that captures hierarchical and comprehensive textual representations of the input news content. To effectively separate latent authenticity-related and event-specific knowledge within the news content, we employ a disentanglement architecture. To further enhance the decoupling effect, we introduce a cross-perturbation mechanism that perturbs authenticity-related representation with the event-specific one, and vice versa, deriving a robust and discerning authenticity-related signal. Additionally, we implement a refinement learning scheme to minimize potential interactions between two decoupled representations, ensuring that the authenticity signal remains strong and unaffected by event-specific details. Experimental results demonstrate that our approach effectively mitigates the impact of event-specific influence, outperforming state-of-the-art methods. In particular, it achieves a 6.0% improvement in accuracy on the PHEME dataset over MDDA, a similar approach that decouples latent content and style knowledge, in scenarios involving articles from unseen events different from the topics of the training set.<\/jats:p>","DOI":"10.1162\/tacl_a_00743","type":"journal-article","created":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T19:04:44Z","timestamp":1745867084000},"page":"343-356","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":2,"title":["DEAR: Disentangled Event-Agnostic Representation Learning for Early Fake News Detection"],"prefix":"10.1162","volume":"13","author":[{"given":"Xiao","family":"Pu","sequence":"first","affiliation":[{"name":"Chongqing University of Posts and Telecommunications, China. puxiao@cqupt.edu.cn"}]},{"given":"Hao","family":"Wu","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications, China. wuhao_stu_cqupt@outlook.com"}]},{"given":"Xiuli","family":"Bi","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications, China. bixl@cqupt.edu.cn"}]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications, China. wuyu@cqupt.edu.cn"}]},{"given":"Xinbo","family":"Gao","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications, China. gaoxb@cqupt.edu.cn"}]}],"member":"281","published-online":{"date-parts":[[2025,4,17]]},"reference":[{"key":"2025042815043988000_bib1","first-page":"18","article-title":"E-BART: Jointly predicting and explaining truthfulness","volume-title":"Proceedings of the 2021 Truth and Trust Online Conference","author":"Brand","year":"2021"},{"key":"2025042815043988000_bib2","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1007\/978-3-030-04503-6_4","article-title":"Call attention to rumors: Deep attention based recurrent neural networks for early rumor detection","volume-title":"Proceedings of the Trends and Applications in Knowledge Discovery and Data Mining","author":"Chen","year":"2018"},{"key":"2025042815043988000_bib3","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1007\/978-3-030-73696-5_16","article-title":"A heuristic-driven ensemble framework for COVID-19 fake news detection","volume-title":"Proceedings of the Combating Online Hostile Posts in Regional Languages during Emergency Situation","author":"Das","year":"2021"},{"key":"2025042815043988000_bib4","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Devlin","year":"2019"},{"key":"2025042815043988000_bib5","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1109\/ICDMW53433.2021.00110","article-title":"Cross-lingual COVID-19 fake news detection","volume-title":"Proceedings of the 2021 International Conference on Data Mining Workshops","author":"Jiangshu","year":"2021"},{"key":"2025042815043988000_bib6","doi-asserted-by":"publisher","first-page":"2672","DOI":"10.1145\/342262","article-title":"Generative adversarial nets","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems","author":"Goodfellow","year":"2014"},{"key":"2025042815043988000_bib7","doi-asserted-by":"publisher","first-page":"22105","DOI":"10.1609\/aaai.v38i20.30214","article-title":"Bad actor, good advisor: Exploring the role of large language models in fake news detection","volume-title":"Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence","author":"Beizhe","year":"2024"},{"key":"2025042815043988000_bib8","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1609\/icwsm.v18i1.31341","article-title":"A multi-modal prompt learning framework for early detection of fake news","volume-title":"Proceedings of the Eighteenth International AAAI Conference on Web and Social Media","author":"Weiqi","year":"2024"},{"key":"2025042815043988000_bib9","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/ICCV.2017.167","article-title":"Arbitrary style transfer in real-time with adaptive instance normalization","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Huang","year":"2017"},{"issue":"5","key":"2025042815043988000_bib10","doi-asserted-by":"publisher","first-page":"103029","DOI":"10.1016\/J.IPM.2022.103029","article-title":"Fake news detection via knowledgeable prompt learning","volume":"59","author":"Jiang","year":"2022","journal-title":"Information Processing & Management"},{"key":"2025042815043988000_bib11","doi-asserted-by":"publisher","first-page":"2972","DOI":"10.1609\/aaai.v30i1.10382","article-title":"News verification by exploiting conflicting social viewpoints in microblogs","volume-title":"Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence","author":"Jin","year":"2016"},{"key":"2025042815043988000_bib12","doi-asserted-by":"publisher","first-page":"1746","DOI":"10.3115\/v1\/D14-1181","article-title":"Convolutional neural networks for sentence classification","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing","author":"Kim","year":"2014"},{"key":"2025042815043988000_bib13","first-page":"3402","article-title":"All-in-one: Multi-task learning for rumour verification","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics","author":"Kochkina","year":"2018"},{"key":"2025042815043988000_bib14","doi-asserted-by":"publisher","first-page":"3627","DOI":"10.1109\/ICDE60146.2024.00279","article-title":"Dual-teacher de-biasing distillation framework for multi-domain fake news detection","volume-title":"Proceedings of the 40th IEEE International Conference on Data Engineering","author":"Li","year":"2024"},{"key":"2025042815043988000_bib15","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1109\/BigData52589.2021.9671592","article-title":"Multi-source domain adaptation with weak supervision for early fake news detection","volume-title":"Proceedings of the 2021 IEEE International Conference on Big Data","author":"Li","year":"2021"},{"key":"2025042815043988000_bib16","doi-asserted-by":"publisher","first-page":"2543","DOI":"10.18653\/v1\/2022.findings-naacl.194","article-title":"Detect rumors in microblog posts for low-resource domains via adversarial contrastive learning","volume-title":"Proceedings of the Findings of the Association for Computational Linguistics","author":"Lin","year":"2022"},{"key":"2025042815043988000_bib17","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1109\/TIFS.2023.3326368","article-title":"Robust domain misinformation detection via multi-modal feature alignment","volume":"19","author":"Liu","year":"2024","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"2025042815043988000_bib18","article-title":"Roberta: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019","journal-title":"CoRR"},{"key":"2025042815043988000_bib19","first-page":"3818","article-title":"Detecting rumors from microblogs with recurrent neural networks","volume-title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","author":"Ma","year":"2016"},{"key":"2025042815043988000_bib20","doi-asserted-by":"publisher","first-page":"3632","DOI":"10.1145\/3485447.3512258","article-title":"Domain adaptive fake news detection via reinforcement learning","volume-title":"Proceedings of the ACM Web Conference 2022","author":"Mosallanezhad","year":"2022"},{"key":"2025042815043988000_bib21","doi-asserted-by":"publisher","first-page":"1732","DOI":"10.1145\/3627673.3679519","article-title":"Let silence speak: Enhancing fake news detection with generated comments from large language models","volume-title":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","author":"Nan","year":"2024"},{"key":"2025042815043988000_bib22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IC3SIS54991.2022.9885398","article-title":"A multi-model intelligent approach for rumor detection in social networks","volume-title":"Proceedings of the 2022 International Conference on Computing, Communication, Security and Intelligent Systems","author":"Santhosh","year":"2022"},{"key":"2025042815043988000_bib23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IWQoS54832.2022.9812879","article-title":"A privacy-aware distributed knowledge graph approach to qois-driven COVID-19 misinformation detection","volume-title":"Proceedings of the 30th IEEE\/ACM International Symposium on Quality of Service","author":"Shang","year":"2022"},{"key":"2025042815043988000_bib24","doi-asserted-by":"publisher","first-page":"3623","DOI":"10.1145\/3485447.3512257","article-title":"A duo-generative approach to explainable multimodal COVID-19 misinformation detection","volume-title":"Proceedings of the ACM Web Conference 2022","author":"Shang","year":"2022"},{"key":"2025042815043988000_bib25","article-title":"Gradient matching for domain generalization","volume-title":"Proceedings of the Tenth International Conference on Learning Representations","author":"Shi","year":"2022"},{"key":"2025042815043988000_bib26","article-title":"Fakenewsnet: A data repository with news content, social context and dynamic information for studying fake news on social media","volume":"abs\/1809.01286","author":"Shu","year":"2018","journal-title":"Big Data"},{"key":"2025042815043988000_bib27","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1609\/icwsm.v14i1.7329","article-title":"Hierarchical propagation networks for fake news detection: Investigation and exploitation","volume-title":"Proceedings of the Fourteenth International AAAI Conference on Web and Social Media","author":"Shu","year":"2020"},{"key":"2025042815043988000_bib28","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1145\/3289600.3290994","article-title":"Beyond news contents: The role of social context for fake news detection","volume-title":"Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining","author":"Shu","year":"2019"},{"key":"2025042815043988000_bib29","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1609\/aaai.v35i1.16134","article-title":"Embracing domain differences in fake news: Cross-domain fake news detection using multi-modal data","volume-title":"Proceedings of the AAAI conference on artificial intelligence","author":"Silva","year":"2021"},{"issue":"11","key":"2025042815043988000_bib30","doi-asserted-by":"publisher","first-page":"7283","DOI":"10.1109\/TKDE.2024.3392788","article-title":"Unsupervised domain-agnostic fake news detection using multi-modal weak signals","volume":"36","author":"Silva","year":"2024","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"2025042815043988000_bib31","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1145\/3219819.3219903","article-title":"EANN: Event adversarial neural networks for multi-modal fake news detection","volume-title":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","author":"Wang","year":"2018"},{"key":"2025042815043988000_bib32","doi-asserted-by":"publisher","first-page":"3367","DOI":"10.1145\/3637528.3671977","article-title":"Fake news in sheep\u2019s clothing: Robust fake news detection against llm-empowered style attacks","volume-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Jiaying","year":"2024"},{"issue":"11","key":"2025042815043988000_bib33","doi-asserted-by":"publisher","first-page":"5591","DOI":"10.1109\/TKDE.2023.3341640","article-title":"Adversarial contrastive learning for evidence-aware fake news detection with graph neural networks","volume":"36","author":"Junfei","year":"2024","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"2025042815043988000_bib34","doi-asserted-by":"publisher","first-page":"2423","DOI":"10.1145\/3511808.3557263","article-title":"Contrastive domain adaptation for early misinformation detection: A case study on COVID-19","volume-title":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","author":"Yue","year":"2022"},{"key":"2025042815043988000_bib35","doi-asserted-by":"publisher","first-page":"5223","DOI":"10.18653\/v1\/2023.acl-long.286","article-title":"Metaadapt: Domain adaptive few-shot misinformation detection via meta learning","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics","author":"Yue","year":"2023"},{"key":"2025042815043988000_bib36","doi-asserted-by":"publisher","first-page":"4441","DOI":"10.1109\/TMM.2020.3042055","article-title":"Multimodal disentangled domain adaption for social media event rumor detection","volume":"23","author":"Zhang","year":"2021","journal-title":"IEEE Transactions on Multimedia"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00743\/2514602\/tacl_a_00743.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00743\/2514602\/tacl_a_00743.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T19:04:47Z","timestamp":1745867087000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00743\/128940\/DEAR-Disentangled-Event-Agnostic-Representation"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00743","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025]]},"published":{"date-parts":[[2025]]}}}