[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125943-en":3,"doc-seo-125943-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},125943,137451207643,"Noah","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","LingML - Linguistic-Informed Machine Learning for Enhanced Fake News Detection","Social media spreads information at an unprecedented pace, making reliable distinction between misinformation and fake news a critical societal need. Existing machine learning approaches often face limited accuracy, weak interpretability, and poor generalizability. LingML introduces linguistics as input to enhance fake news detection using an experimental setup on a widely used pandemic dataset. Results show strong effectiveness with low error frequency using linguistic input alone, high explainability, and improved performance when combined with large-scale NLP models, achieving a 1.8% average error rate.","LingML: Linguistic-Informed Machine Learning for Enhanced Fake News Detection  \nJasraj Singh, Fang Liu, Member, IEEE, Hong Xu, Bee Chin Ng, and Wei Zhang, Member, IEEE  \narXiv :2405 .04165v1 [ cs .CL] 7 May 2024  \nAbstract—Nowadays, Information spreads at an unprecedented pace in social media and discerning truth from misinformation and fake news has become an acute societal challenge. Machine learning (ML) models have been employed to identify fake news but are far from perfect with challenging problems like limited accuracy, interpretability, and generalizability. In this paper, we enhance ML-based solutions with linguistics input and we propose LingML, linguistic-informed ML, for fake news detection. We conducted an experimental study with a popular dataset on fake news during the pandemic. The experiment results show that our proposed solution is highly effective. There are fewer than two errors out of every ten attempts with only linguistic input used in ML and the knowledge is highly explainable. When linguistics input is integrated with advanced large-scale ML models for natural language processing, our solution outperforms existing ones with 1.8% average error rate. LingML creates a new path with linguistics to push the frontier of effective and efficient fake news detection. It also sheds light on real-world multi-disciplinary applications requiring both MLand domain expertise to achieve optimal performance.  \nI. INTRODUCTION  \nTHE advent of the digital age has ushered in connectivity  \nand information sharing primarily through social media platforms. Such interconnectedness indeed has transformed the way we communicate and brought us various benefits, but it has also given rise to the spread of misinformation and fake news [1] . In major events like the recent pandemic, social media became a breeding ground of unverified claims, conspiracy theories, etc., which offset its contribution to disseminating timely and useful news. With events carrying high stakes and uncertainties like the pandemic, people to some extent are more susceptible to misleading narratives. The consequences  \nThis work was supported in part by the School of Social Sciences at Nanyang Technological University, A*STAR under its MTC Programmatic (Award M23L9b0052), SIT’s Ignition Grant (STEM) (Grant ID: IG (S) 2/2023 – 792), and the Ministry of Education, Singapore, under the Academic Research Tier 1 Grant (Grant ID: GMS 693) . (Corresponding author: Fang Liu)  \nJasraj Singh is with the Nanyang Technological University (NTU), Singapore, and the University College London (UCL), United Kingdom (e-mail: [jasraj001@e.ntu.edu.sg](jasraj001@e.ntu.edu.sg) [and jasraj.singh.23@ucl.ac.uk](and jasraj.singh.23@ucl.ac.uk)).  \nFang Liu is with the School of Science and Technology, Singapore University of Social Sciences, Singapore 599494 (e-mail: [liufang@suss.edu.sg](liufang@suss.edu.sg)).  \nHong Xu is with the School of Social Sciences at Nanyang Technological University, Singapore 639798 (e-mail: [xuhong@ntu.edu.sg](xuhong@ntu.edu.sg)).  \nBee Chin Ng is with the School of Humanities at Nanyang Technological University, Singapore 639798 ([e-mail: mbcng@ntu.edu.sg](e-mail: mbcng@ntu.edu.sg)).  \nWei Zhang is with the Information and Communications Technology Cluster, Singapore Institute of Technology, Singapore 138683 (e-mail: [wei.zhang@singaporetech.edu.sg](wei.zhang@singaporetech.edu.sg)).  \nManuscript received January 1, 2024; revised January 1, 2024 .  \ncan be profound, e.g., shaping public opinion and eroding trust, if the spread of fake news is not well controlled.  \nPreventing the negative consequences requires fake news detection and to do this effectively and efficiently is highly challenging. With the huge volume of information that is created every day and circulated online with ever-increasing social media activities, it is nearly impossible to manually sift through all the news and identify the fake ones fast enough. There is an urgent demand to de","cbCaioEQ4IV9VLZE","https://ap.wps.com/l/cbCaioEQ4IV9VLZE","pdf",1897074,4,1,7,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"What problem does LingML address in social media?\",\"answer\":\"LingML targets the difficulty of detecting misinformation and fake news as information spreads rapidly on social platforms.\"},{\"question\":\"Why are existing ML and LLM fake news detectors insufficient?\",\"answer\":\"They often suffer from limited accuracy, poor interpretability (black-box behavior), and insufficient generalizability due to overfitting and shifting social language.\"},{\"question\":\"How does LingML improve fake news detection and what results are reported?\",\"answer\":\"LingML integrates linguistics input into machine learning, providing higher explainability and improved effectiveness, including a reported 1.8% average error rate when combined with large-scale NLP models.\"}]","LingML - Linguistic-Informed Machine Learning for Enhanced Fake News Detection | PDF",1785902154,18,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"lingml-linguistic-informed-machine-learning-for-enhanced-fake-news-detection","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/document/lingml-linguistic-informed-machine-learning-for-enhanced-fake-news-detection/125943/",{"url":53,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does LingML address in social media?","Question",{"text":76,"@type":77},"LingML targets the difficulty of detecting misinformation and fake news as information spreads rapidly on social platforms.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Why are existing ML and LLM fake news detectors insufficient?",{"text":81,"@type":77},"They often suffer from limited accuracy, poor interpretability (black-box behavior), and insufficient generalizability due to overfitting and shifting social language.",{"name":83,"@type":74,"acceptedAnswer":84},"How does LingML improve fake news detection and what results are reported?",{"text":85,"@type":77},"LingML integrates linguistics input into machine learning, providing higher explainability and improved effectiveness, including a reported 1.8% average error rate when combined with large-scale NLP models.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]