[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127423-en":3,"doc-seo-127423-105":30,"detail-sidebar-cat-0-en-105":96},{"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":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},127423,962085564807,"Aurelia","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Modeling Digital Repression - A Machine Learning Analysis of Shutdowns as Governance Signals","This study advances Digital Government research by applying machine learning to analyze internet shutdowns as structured signals of digital repression. Using a dataset of 566 shutdown events (1995–2011) and regime attributes from the Polity 5 project, it builds interpretable models to estimate shutdown severity and classify regime type. A decision tree regressor and a bootstrapped logistic classifier show strong associations between shutdown characteristics and political context, reaching over 93% accuracy. The models support early warning, policy evaluation, and digital rights monitoring by treating shutdowns as governance decisions embedded in digital infrastructure.","Proceedings of the 59th Hawaii International Conference on System Sciences | 2026  \nModeling Digital Repression: A Machine Learning Analysis of Shutdowns as  \nGovernance Signals  \nDenton Forner  \nUniversity of Hawaii  \n[dforner@hawaii.edu](dforner@hawaii.edu)  \nAbstract  \nThis study advances Digital Government research by applying machine learning to analyze internet shutdowns as structured signals of digital repression. Using a dataset of 566 shutdown events (1995–2011) and regime attributes from the Polity 5 project, the study builds interpretable models to estimate shutdown severity and classify regime type. A decision tree regressor and bootstrapped logistic classifier reveal strong associations between shutdown characteristics and political context, achieving over 93% accuracy. While not designed for real-time prediction, these models demonstrate how event-level data can inform early warning, policy evaluation, and digital rights monitoring. By modeling shutdowns as governance decisions embedded in digital infrastructure, this research shows how computational methods can support accountability in opaque information environments.  \nKeywords: internet shutdowns, machine learning, digital repression, digital governance, regime type  \n1. Introduction  \nAfter the Arab Spring in 2011, many observers believed that social media platforms like Twitter and Facebook would usher in a new era of government accountability. But this vision of technological determinism underestimated the adaptability of authoritarian regimes and overlooked the enabling role that civil society played in sustaining protest movements (MacKinnon, 2011) . Over the past decade, states such as China, Russia, and Iran have adapted to the digital age by integrating information control into governance itself—a phenomenon MacKinnon describes as networked authoritarianism (2011) . These regimes deploy a broad suite of tools to dominate the information environment, including content filtering, surveillance, legal intimidation, and disinformation (Deibert & Rohozinski, 2010; Akgül & Kırlıdoğ, 2015) .  \nAmong these tactics, internet and network shutdowns have become one of the most visible—and contested—forms of digital repression (Marchant &  \nStremlau, 2020) . Often imposed during protests, elections, or political unrest, they are typically justified under vague legal pretexts and implemented with limited transparency (Ruijgrok, 2022). A 2022 report by the UN Office of the High Commissioner for Human Rights (OHCHR) documented over 931 incidents across 74 countries in just six years, raising concerns over their legality, proportionality, and disproportionate impact on civil society (OHCHR, 2022) . Yet attributing responsibility remains difficult: governments may blame technical faults, pressure telecom providers behind closed doors, or use proxies that obscure direct state involvement (Marchant & Stremlau, 2020) . While often framed as censorship, shutdowns also function as structured governance decisions enacted through digital infrastructure—revealing how states regulate connectivity as a form of institutional control.  \nDigital infrastructure—once viewed primarily as a tool for transparency, service delivery, and civic engagement—has increasingly become a domain of governance itself, used by states to exert authority and manage information flows. Scholars in Digital Government have emphasized that digital systems are not neutral platforms but embedded policy tools shaped by institutional priorities, legal frameworks, and evolving governance logics (Fountain, 2001; Janssen et al., 2012) . This model of networked authoritarianism reflects how state actors leverage digital networks not to democratize governance, but to monitor, suppress, and shape public discourse (MacKinnon, 2011) . Internet shutdowns—central to this study—exemplify how digital infrastructure becomes a mechanism of repression, transforming the governance of connectivity into a tool of exclusion and e","cbCaivKBvpKK7J1C","https://ap.wps.com/l/cbCaivKBvpKK7J1C","pdf",528829,1,10,"English","en",105,"# Introduction\n## Digital repression and networked authoritarianism\n## Legal justifications, transparency limits, and attribution challenges\n## Digital infrastructure as governance\n# Methodology and Data\n## Shutdown event dataset (1995–2011)\n## Regime context via Polity 5","[{\"question\":\"What is the main research goal of this study?\",\"answer\":\"The study models internet shutdowns as structured signals of digital repression and governance decisions, aiming to estimate severity and infer regime type.\"},{\"question\":\"Which data sources are used for modeling?\",\"answer\":\"It uses 566 shutdown events from 1995–2011 and integrates regime attributes from the Polity 5 project to provide political context.\"},{\"question\":\"What machine learning methods are reported and what performance is achieved?\",\"answer\":\"A decision tree regressor estimates shutdown severity and a bootstrapped logistic classifier classifies regime type, achieving over 93% accuracy.\"},{\"question\":\"How can the results be used in practice?\",\"answer\":\"The models can inform early warning, policy evaluation, and digital rights monitoring, supporting accountability in information environments where responsibility is opaque.\"}]","Modeling Digital Repression - A Machine Learning Analysis of Shutdowns as Governance Signals | PDF",1785938799,25,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":91,"head_meta":93,"extra_data":95,"updated_unix":28},"modeling-digital-repression-a-machine-learning-analysis-of-shutdowns-as-governance-signals","",{"@graph":36,"@context":90},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/modeling-digital-repression-a-machine-learning-analysis-of-shutdowns-as-governance-signals/127423/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82,86],{"name":73,"@type":74,"acceptedAnswer":75},"What is the main research goal of this study?","Question",{"text":76,"@type":77},"The study models internet shutdowns as structured signals of digital repression and governance decisions, aiming to estimate severity and infer regime type.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which data sources are used for modeling?",{"text":81,"@type":77},"It uses 566 shutdown events from 1995–2011 and integrates regime attributes from the Polity 5 project to provide political context.",{"name":83,"@type":74,"acceptedAnswer":84},"What machine learning methods are reported and what performance is achieved?",{"text":85,"@type":77},"A decision tree regressor estimates shutdown severity and a bootstrapped logistic classifier classifies regime type, achieving over 93% accuracy.",{"name":87,"@type":74,"acceptedAnswer":88},"How can the results be used in practice?",{"text":89,"@type":77},"The models can inform early warning, policy evaluation, and digital rights monitoring, supporting accountability in information environments where responsibility is opaque.","https://schema.org",{"og:url":52,"og:type":92,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":94,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":97},[98,102,106,110,115,120,125,128,133,136,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"Exam",70,"exam",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},5,"Comic",60,"comic",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},6,"Technology",50,"technology",{"id":121,"doc_module":4,"doc_module_name":46,"category_name":122,"show_sort_weight":123,"slug":124},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":126,"slug":127},30,"research-report",{"id":129,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":131,"slug":132},9,"Religion & Spirituality",20,"religion-spirituality",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":131,"slug":135},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":21,"slug":138},"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":111,"slug":142},19,"General","general"]