Deep Temporal Graph Learning for Cascade Popularity Prediction in Social Networks

Deep Temporal Graph Learning for Cascade Popularity Prediction in Social Networks | 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 Deep Temporal Graph Learning for Cascade Popularity Prediction in Social Networks Elaf Adel Abbas, Raaid Alubady, Aqeel Sahi, Mohammed Diykh, Shahab Abdulla This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6942213/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 Information propagation in social networks often exhibits cascade behavior, where initial posts trigger chain reactions of shares and interactions. Accurately predicting cascade popularity is crucial for applications such as misinformation control and viral marketing. In this paper, we propose a hybrid architecture that combines Graph Neural Networks (GNNs) with Transformer encoders to capture both local network topology and long-range temporal dependencies in cascade evolution. Our model employs a Self-Attention Transformer layer to model temporal dynamics and processes graph-structured cascade data through message passing mechanisms (GCN/GAT). We evaluate our approach on two real-world datasets: Twitter and Digg, which provide rich temporal and structural information for cascade analysis. The prediction target is cascade popularity at multiple time horizons (6, 12, 18, and 24 hours), assessed using rank correlation (Spearman) and regression metrics (MSE, MAE, R²). Compared to established baselines including GCN, GAT, and traditional node embedding methods (DeepWalk and Node2Vec with MLP), our GNN + Transformer model consistently achieves higher correlation and lower prediction error across all evaluation metrics. The performance improvements are particularly pronounced for long-term forecasts; for instance, our model significantly reduces MSE at the 24-hour prediction horizon compared to all baseline methods. These results demonstrate that the integrated Transformer component effectively captures long-range cascade dynamics that are not adequately modeled by conventional graph-based approaches. Graph neural networks Transformer networks Cascade prediction Social networks Temporal modeling Full Text Additional Declarations No competing interests reported. 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-6942213","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":495716407,"identity":"b7aebcc7-ff00-4436-8ff0-4b5598c6b99b","order_by":0,"name":"Elaf Adel Abbas","email":"","orcid":"","institution":"University of Karbala","correspondingAuthor":false,"prefix":"","firstName":"Elaf","middleName":"Adel","lastName":"Abbas","suffix":""},{"id":495716409,"identity":"22eb36c4-6519-489a-914d-1bfa0f5d0f50","order_by":1,"name":"Raaid Alubady","email":"","orcid":"","institution":"Alayen Iraqi University","correspondingAuthor":false,"prefix":"","firstName":"Raaid","middleName":"","lastName":"Alubady","suffix":""},{"id":495716410,"identity":"7d0e69d1-4232-49a3-9779-7303177e4c9f","order_by":2,"name":"Aqeel Sahi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCElEQVRIiWNgGAWjYBACNhDxgKGOwYCZ+QADgwFY0ACvFn4QkcBwGKiFLYE4LZINYC0HgMp44CrxazE4nnzwAVCLvDk7zzfpgoI62Qb25m0SDDWHcWs58yzZIIGhznBnM+826RkGh40beI6VSTAcw6PlRo6ZRAIDM+OGw0AtPAYHEhskgCIMbLi12N/I//4DqMV+w2GeZ0AtdYkN8m+AWv7htYUN6H3mRKAWNqAWZqAtPGYSjG14/WIskWBwOHnDYTZjax6gX9p40ootEvvScWs5nvzww4eKOtsN5w8/vM3zp062n/3wxhsfvlnj1AKKFJSIYGyDCeLXggQYG/CqHgWjYBSMgpEIAJrOUlsZgso+AAAAAElFTkSuQmCC","orcid":"","institution":"University of Southern Queensland","correspondingAuthor":true,"prefix":"","firstName":"Aqeel","middleName":"","lastName":"Sahi","suffix":""},{"id":495716411,"identity":"38bd8b52-66e6-494a-8a09-cdbaf97cba12","order_by":3,"name":"Mohammed Diykh","email":"","orcid":"","institution":"Al-Shatrah University","correspondingAuthor":false,"prefix":"","firstName":"Mohammed","middleName":"","lastName":"Diykh","suffix":""},{"id":495716412,"identity":"d4b30323-5e1b-4334-8c9f-0305d38e2065","order_by":4,"name":"Shahab Abdulla","email":"","orcid":"","institution":"UniSQ College, University of Southern Queensland","correspondingAuthor":false,"prefix":"","firstName":"Shahab","middleName":"","lastName":"Abdulla","suffix":""}],"badges":[],"createdAt":"2025-06-21 02:38:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6942213/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6942213/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":88714959,"identity":"bae3570e-866a-4627-9bb1-d9cc54e64109","added_by":"auto","created_at":"2025-08-10 09:31:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1040454,"visible":true,"origin":"","legend":"","description":"","filename":"paperGNN.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6942213/v1_covered_f741e1d7-4ee9-404f-b3eb-9914f730cfe6.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Deep Temporal Graph Learning for Cascade Popularity Prediction in Social Networks","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","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":"Graph neural networks, Transformer networks, Cascade prediction, Social networks, Temporal modeling","lastPublishedDoi":"10.21203/rs.3.rs-6942213/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6942213/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eInformation propagation in social networks often exhibits cascade behavior, where initial posts trigger chain reactions of shares and interactions. Accurately predicting cascade popularity is crucial for applications such as misinformation control and viral marketing. In this paper, we propose a hybrid architecture that combines Graph Neural Networks (GNNs) with Transformer encoders to capture both local network topology and long-range temporal dependencies in cascade evolution. Our model employs a Self-Attention Transformer layer to model temporal dynamics and processes graph-structured cascade data through message passing mechanisms (GCN/GAT). We evaluate our approach on two real-world datasets: Twitter and Digg, which provide rich temporal and structural information for cascade analysis. The prediction target is cascade popularity at multiple time horizons (6, 12, 18, and 24 hours), assessed using rank correlation (Spearman) and regression metrics (MSE, MAE, R\u0026sup2;). Compared to established baselines including GCN, GAT, and traditional node embedding methods (DeepWalk and Node2Vec with MLP), our GNN\u0026thinsp;+\u0026thinsp;Transformer model consistently achieves higher correlation and lower prediction error across all evaluation metrics. The performance improvements are particularly pronounced for long-term forecasts; for instance, our model significantly reduces MSE at the 24-hour prediction horizon compared to all baseline methods. These results demonstrate that the integrated Transformer component effectively captures long-range cascade dynamics that are not adequately modeled by conventional graph-based approaches.\u003c/p\u003e","manuscriptTitle":"Deep Temporal Graph Learning for Cascade Popularity Prediction in Social Networks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-08 03:01:56","doi":"10.21203/rs.3.rs-6942213/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":"c21d3092-a23f-4718-b899-aedf34fe8438","owner":[],"postedDate":"August 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-08-10T09:23:27+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-08 03:01:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6942213","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6942213","identity":"rs-6942213","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}