{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T18:19:32Z","timestamp":1787941172781,"version":"build-2784847793"},"reference-count":38,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","award":["2025NSFSC0812"],"award-info":[{"award-number":["2025NSFSC0812"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Public health communication increasingly depends on networked interactions in which attitudes and behavioral intentions emerge through repeated peer exchange and institutional contact, yet trust remains weakly represented in many computational diffusion and graph-learning frameworks, particularly when privacy shocks abruptly reshape credibility. We present a proof-of-concept, mechanism-grounded framework that treats trust as a bounded, directed, and diffusible state on a temporal heterogeneous graph and couples that state to learned influence pathways and budget-constrained intervention optimization. Users, physicians, and privacy-shock events are represented in a timestamped graph; trust changes through event-level directed transfer, relation- and content-dependent modulation, explicitly scoped shock exposure, and parametric recovery. A temporal graph transformer encodes event histories, and influence-aware pooling gates pathway aggregation by source trust before intention prediction and joint node-target and content assignment. Evaluation is conducted entirely in reproducible, mechanism-consistent simulations spanning shock-free, global-shock, and community-targeted-shock regimes. Within these controlled settings, the framework achieved higher predictive performance than the evaluated static, sequential, classical-diffusion, and temporal or heterogeneous baselines, and its optimized policies produced greater simulated intention lift than the evaluated heuristics at the reported operating points. Because the simulator shares structural assumptions with the model, these findings demonstrate internal feasibility rather than established real-world superiority. Empirical calibration, real or semi-real interaction topologies, structurally mismatched policy evaluation, and complete configuration-by-budget uncertainty analyses remain necessary before operational use.<\/jats:p>","DOI":"10.1371\/journal.pone.0356143","type":"journal-article","created":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T17:52:46Z","timestamp":1787939566000},"page":"e0356143","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Modeling and optimizing trust-mediated influence in temporal heterogeneous networks"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0754-2269","authenticated-orcid":true,"given":"Fengliang","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,28]]},"reference":[{"issue":"12","key":"pone.0356143.ref001","doi-asserted-by":"crossref","first-page":"2051","DOI":"10.2105\/AJPH.94.12.2051","article-title":"Communication at the core of effective public health","volume":"94","author":"JM Bernhardt","year":"2004","journal-title":"Am J Public Health"},{"key":"pone.0356143.ref002","unstructured":"Bello I, Pham H, Le QV, Norouzi M, Bengio S. Neural combinatorial optimization with reinforcement learning. In: ICLR Workshop. 2017."},{"issue":"2","key":"pone.0356143.ref003","doi-asserted-by":"crossref","first-page":"790","DOI":"10.1109\/JBHI.2022.3185673","article-title":"Handling privacy-sensitive medical data with federated learning: challenges and future directions","volume":"27","author":"O Aouedi","year":"2023","journal-title":"IEEE J Biomed Health Inform"},{"issue":"12","key":"pone.0356143.ref004","doi-asserted-by":"crossref","first-page":"2053","DOI":"10.2105\/AJPH.94.12.2053","article-title":"The contributions of health communication to eliminating health disparities","volume":"94","author":"VS Freimuth","year":"2004","journal-title":"Am J Public Health"},{"key":"pone.0356143.ref005","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1080\/10810730.2025.2466098","article-title":"Public Health Communication and Trust: Opportunities for Understanding","volume":"30","author":"JS Schuh","year":"2025","journal-title":"J Health Commun"},{"key":"pone.0356143.ref006","first-page":"57","author":"P Domingos","year":"2001"},{"key":"pone.0356143.ref007","doi-asserted-by":"crossref","unstructured":"Tang Y, Xiao X, Shi Y. Influence maximization: near-optimal time complexity meets practical efficiency. In: Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data. 2014;75\u201386.","DOI":"10.1145\/2588555.2593670"},{"key":"pone.0356143.ref008","unstructured":"Rossi E, Chamberlain BP, Frasca F, Eynard D, Monti F, Bronstein MM. Temporal graph networks for deep learning on dynamic graphs. In: ICML Workshop on Graph Representation Learning. 2020."},{"key":"pone.0356143.ref009","first-page":"199","author":"W Chen","year":"2009"},{"issue":"9","key":"pone.0356143.ref010","doi-asserted-by":"crossref","first-page":"2729","DOI":"10.1080\/00207721.2025.2557528","article-title":"Reinforcement learning-based dynamic event-triggered prescribed performance control for nonlinear systems with input delay","volume":"57","author":"H Xu","year":"2025","journal-title":"International Journal of Systems Science"},{"key":"pone.0356143.ref011","doi-asserted-by":"crossref","unstructured":"Sankar A, Wu Y, Gou L, Zhang W, Yang HJ i. Dysat: Deep neural representation learning on dynamic graphs via self-attention. In: Proceedings of the ACM International Conference on Web Search and Data Mining (WSDM). 2020;519\u201327.","DOI":"10.1145\/3336191.3371845"},{"issue":"11","key":"pone.0356143.ref012","doi-asserted-by":"crossref","first-page":"107761","DOI":"10.1016\/j.jfranklin.2025.107761","article-title":"A novel event-triggered mechanism-based optimal safe control for nonlinear multi-player systems using adaptive dynamic programming","volume":"362","author":"S Liu","year":"2025","journal-title":"Journal of the Franklin Institute"},{"key":"pone.0356143.ref013","first-page":"137","author":"D Kempe","year":"2003"},{"key":"pone.0356143.ref014","first-page":"88","author":"W Chen","year":"2010"},{"issue":"1","key":"pone.0356143.ref015","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1109\/JIOT.2025.3626164","article-title":"Distributed adaptive optimized sliding-mode time-varying formation control with prescribed-time performance constraints for nonlinear heterogeneous multiagent systems","volume":"13","author":"B Zhu","year":"2026","journal-title":"IEEE Internet Things J"},{"key":"pone.0356143.ref016","unstructured":"Trivedi R, Farajtabar M, Biswal P, Zha H. Dyrep: Learning representations over dynamic graphs. In: 2019."},{"key":"pone.0356143.ref017","first-page":"1","article-title":"Dynamic event-triggered fuzzy adaptive hierarchical sliding mode optimal control for unknown nonlinear systems","author":"M Liu","year":"2025","journal-title":"International J Fuzzy Systems"},{"key":"pone.0356143.ref018","first-page":"1269","article-title":"Predicting dynamic embedding trajectory in temporal interaction networks","volume":"2019","author":"S Kumar","year":"2019","journal-title":"KDD"},{"key":"pone.0356143.ref019","unstructured":"Tang J, Tang Y, Yuan J. Maximizing temporal influence spread. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2016;2479\u201385."},{"issue":"04","key":"pone.0356143.ref020","doi-asserted-by":"crossref","first-page":"5363","DOI":"10.1609\/aaai.v34i04.5984","article-title":"EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs","volume":"34","author":"A Pareja","year":"2020","journal-title":"AAAI"},{"key":"pone.0356143.ref021","unstructured":"Wang Y, Chen W. Community-based greedy algorithm for influence maximization. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2010. 1323\u20138."},{"issue":"9","key":"pone.0356143.ref022","article-title":"A formal model for multiagent Q-learning on graphs","volume":"68","author":"J Liu","year":"2025","journal-title":"Sci China Inf Sci"},{"issue":"1","key":"pone.0356143.ref023","doi-asserted-by":"crossref","DOI":"10.1145\/1232722.1232727","article-title":"The dynamics of viral marketing","volume":"1","author":"J Leskovec","year":"2007","journal-title":"ACM Transactions on the Web"},{"key":"pone.0356143.ref024","unstructured":"Mei H, Eisner JM. The neural hawkes process: A neurally self-modulating multivariate point process. In: Advances in Neural Information Processing Systems. 2017;6754\u201364."},{"issue":"2","key":"pone.0356143.ref025","doi-asserted-by":"crossref","first-page":"2210","DOI":"10.1109\/TCSS.2023.3272331","article-title":"ToupleGDD: A fine-designed solution of influence maximization by deep reinforcement learning","volume":"11","author":"T Chen","year":"2024","journal-title":"IEEE Trans Comput Soc Syst"},{"issue":"3","key":"pone.0356143.ref026","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.physrep.2012.03.001","article-title":"Temporal networks","volume":"519","author":"P Holme","year":"2012","journal-title":"Physics Reports"},{"key":"pone.0356143.ref027","first-page":"118039","article-title":"Temporal influence modeling with dynamic graph attention","volume":"635","author":"L Wang","year":"2023","journal-title":"Information Sciences"},{"key":"pone.0356143.ref028","doi-asserted-by":"crossref","unstructured":"Saito K, Nakano R, Kimura M. Prediction of information diffusion probabilities for independent cascade model. In: International Conference on Knowledge-Based and Intelligent Information and Engineering Systems. 2009;67\u201375.","DOI":"10.1007\/978-3-540-85567-5_9"},{"issue":"3","key":"pone.0356143.ref029","doi-asserted-by":"crossref","first-page":"1288","DOI":"10.1109\/TCSS.2022.3164667","article-title":"PIANO: influence maximization meets deep reinforcement learning","volume":"10","author":"H Li","year":"2023","journal-title":"IEEE Trans Comput Soc Syst"},{"issue":"6","key":"pone.0356143.ref030","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1631\/FITEE.2300548","article-title":"Transformer in reinforcement learning for decision-making: a survey","volume":"25","author":"W Yuan","year":"2024","journal-title":"Front Inform Technol Electron Eng"},{"key":"pone.0356143.ref031","first-page":"665","author":"C Budak","year":"2011"},{"key":"pone.0356143.ref032","doi-asserted-by":"crossref","first-page":"79143","DOI":"10.1109\/ACCESS.2021.3082932","article-title":"Foundations and Modeling of Dynamic Networks Using Dynamic Graph Neural Networks: A Survey","volume":"9","author":"J Skarding","year":"2021","journal-title":"IEEE Access"},{"issue":"12","key":"pone.0356143.ref033","doi-asserted-by":"crossref","first-page":"10589","DOI":"10.1109\/TNNLS.2022.3169488","article-title":"Synchronous Spatiotemporal Graph Transformer: A New Framework for Traffic Data Prediction","volume":"34","author":"T Wang","year":"2023","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"6090","key":"pone.0356143.ref034","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1126\/science.1217330","article-title":"Network interventions","volume":"337","author":"TW Valente","year":"2012","journal-title":"Science"},{"key":"pone.0356143.ref035","first-page":"7234","article-title":"Neural diffusion models for dynamic social influence","volume":"33","author":"W Tang","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"pone.0356143.ref036","doi-asserted-by":"crossref","first-page":"026107","DOI":"10.1103\/PhysRevE.85.026107","article-title":"Temporal node centrality in complex networks","volume":"85","author":"H Kim","year":"2012","journal-title":"Phys Rev E Stat Nonlin Soft Matter Phys"},{"issue":"1","key":"pone.0356143.ref037","first-page":"19","article-title":"Credibility-weighted graph analytics for behavioral intention forecasting under disrupted information ecosystems","volume":"3","author":"MJ Holloway","year":"2025","journal-title":"Journal of AI Analytics and Applications"},{"issue":"1","key":"pone.0356143.ref038","doi-asserted-by":"crossref","first-page":"24","DOI":"10.63646\/jaiaa.2024.020102","article-title":"A deep graph learning approach to community-level health adoption prediction with dynamic credibility states and shock-driven pathway reweighting","volume":"2","author":"MJ Holloway","year":"2024","journal-title":"Journal of AI Analytics and Applications"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0356143","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T17:52:51Z","timestamp":1787939571000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0356143"}},"subtitle":[],"editor":[{"given":"Yang (Jack)","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,28]]},"references-count":38,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,28]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0356143","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,28]]}}}