Beyond Keywords: Leveraging Generative LLMs and Label Aggregation to Classify Economic Policy Uncertainty in News Articles

Beyond Keywords: Leveraging Generative LLMs and Label Aggregation to Classify Economic Policy Uncertainty in News Articles | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Beyond Keywords: Leveraging Generative LLMs and Label Aggregation to Classify Economic Policy Uncertainty in News Articles Paul This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9162777/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract This research describes the adaptation of large language models (LLMs) for economic monitoring in the public sector to automatically determine whether an article discusses economic policy uncertainty (EPU) and to identify its specific type. Previous studies either rely on keywords, which often result in a high number of false positives, or use machine learning (ML) approaches that require a large amount of high-quality human-labeled data, which is costly and time-consuming to obtain. In this study, we propose approaches based on weak supervision, using generative LLMs to create synthetic labels through prompting, making the approach both cost-effective and scalable. In addition, we propose methods for multi-label and hierarchical classification of articles related to EPU. Artificial Intelligence and Machine Learning Citizen Feedback Machine Learning Topic Modeling Language Models Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-9162777","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":608480002,"identity":"2dbeb3b7-3841-46b3-8090-62652855fb78","order_by":0,"name":"Paul","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/UlEQVRIie3PoW4CMRjA8V5Iivl2ugRSXuFbyC6Ie5ieqUJMLYiJwxyGB5jbK0xNNzThTB+AC4g7g0IgScYIPZYMwSjgJvoXTdr0l34lxOf7h9HmaFRuhjHQZmq32P85Fg4SgtaPb0byEFRN2HXCmZTth2za4+x4jd0wGBkgA6qSrLV++tg+M4K5Lkk5dBGD1iyTrD2IiokdDI1EIoyDBBMUyFZHMoeazIGQJHOQBqASqO1gJip2v2TvIJQmqRK6RxlEi9MrqYNAQwepkpyCfFl07Lda9i9KzC6T7ns1/vrex9Ad689ivYt5mOuq2r5eJmdBvag7gM/n8/n+6AANdk6VkZ9MVQAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0003-0177-1096","institution":"Trust","correspondingAuthor":true,"prefix":"","firstName":"","middleName":"","lastName":"Paul","suffix":""}],"badges":[],"createdAt":"2026-03-18 20:16:02","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":true,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":true},"doi":"10.21203/rs.3.rs-9162777/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9162777/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105023859,"identity":"2eec4713-22e2-41dd-9f3a-9f9184ebb5ce","added_by":"auto","created_at":"2026-03-20 03:55:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":333103,"visible":true,"origin":"","legend":"","description":"","filename":"BeyondKeywordsLeveragingGenerativeLLMsandLabelAggregationtoClassifyEconomicPolicyUncertaintyinNewsArticles1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9162777/v1_covered_35a2e6b2-2f0b-42f0-b254-ba2877a27618.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eBeyond Keywords: Leveraging Generative LLMs and Label Aggregation to Classify Economic Policy Uncertainty in News Articles\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"University College Cork","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Citizen Feedback, Machine Learning, Topic Modeling, Language Models","lastPublishedDoi":"10.21203/rs.3.rs-9162777/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9162777/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis research describes the adaptation of large language models (LLMs) for economic monitoring in the public sector to automatically determine whether an article discusses economic policy uncertainty (EPU) and to identify its specific type. Previous studies either rely on keywords, which often result in a high number of false positives, or use machine learning (ML) approaches that require a large amount of high-quality human-labeled data, which is costly and time-consuming to obtain. In this study, we propose approaches based on weak supervision, using generative LLMs to create synthetic labels through prompting, making the approach both cost-effective and scalable. In addition, we propose methods for multi-label and hierarchical classification of articles related to EPU.\u003c/p\u003e","manuscriptTitle":"Beyond Keywords: Leveraging Generative LLMs and Label Aggregation to Classify Economic Policy Uncertainty in News Articles","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-20 03:55:15","doi":"10.21203/rs.3.rs-9162777/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"1a80097f-dbf0-48f3-92a2-de3485d1e7b5","owner":[],"postedDate":"March 20th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":64749796,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-03-20T03:55:15+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-20 03:55:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9162777","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9162777","identity":"rs-9162777","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}