[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83873-en":3,"doc-seo-83873-105":30,"detail-sidebar-cat-0-en-105":91},{"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":13,"seo_description":14,"update_tm":28,"read_time":29},83873,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Who’s Behind It Annotating and Extracting Conspiratorial Actors from German Telegram Posts","Conspiracy theories attribute major events to powerful, secretive actors pursuing harmful goals. While computational work often relies on document-level labels, this study targets the identification of actor mentions that structure conspiratorial narratives. It introduces annotation guidelines and a span-annotated corpus of German Telegram posts, then trains transformer-based models to extract conspiratorial actors. The model is applied to Schwurbelarchiv, enabling large-scale actor representation analysis despite linguistic complexity.","Who’s Behind It? Annotating and Extracting Conspiratorial Actors from  \nGerman Telegram Posts  \nHelena Mihaljevi, Jolanda Beer, Mareike Lisker HTW Berlin, Germany [mihalje@htw-berlin.de](mihalje@htw-berlin.de)  \nKatharina Soemer  \nGoethe University, Frankfurt, Germany  \narXiv :2607 .04962v 1 [ cs .CL] 6 Jul 2026  \nAbstract  \nConspiracy theories commonly attribute important events to the actions of powerful and secretive actors. While computational research has largely focused on document-level analyses of conspiracy theories, less attention has been paid to identifying the actors that drive such narratives. We develop annotation guidelines for conspiratorial actors, present a spanannotated corpus of German Telegram posts, and investigate their automatic extraction using transformer-based models. We further apply the resulting model to the Schwurbelarchiv, a large-scale archive of German conspiracyrelated Telegram channels. Our results demonstrate that conspiratorial actors can be annotated with meaningful agreement and extracted with reasonable accuracy despite the linguistic complexity of conspiracy discourse, enabling large-scale analyses of actor representations in conspiracy narratives.  \n1 Introduction  \nConspiracy theories (CTs) are commonly understood as narratives that explain important events through the intentional actions of powerful and secretive actors pursuing allegedly malicious goals (Douglas and Sutton, 2023 ; Butter, 2021) . They are a recurring form of sense-making in public discourse, typically gaining prominence during periods of societal uncertainty and crisis, and affecting trust in democratic institutions, public health behavior, and the interpretation of societal events (Samory and Mitra, 2018 ; van Prooijen and Douglas, 2017 ; Douglas et al., 2019) .  \nComputational research on conspiracy theories has grown substantially in recent years. Numerous datasets and algorithmic approaches have been proposed for conspiracy theory detection, stance classification, topic analysis, or the study of information diffusion (Moffitt et al., 2021 ; Steffen et al., 2023 ; Langguth et al., 2023 ; Corso et al., 2024 ;  \nPustet et al., 2024 ; Liu et al., 2024 ; Steffen, 2025) . While these approaches have improved our ability to identify conspiracy-related content, they typically represent CTs as document-level labels. Asa result, relatively little is known about how conspiracy narratives themselves are structured and communicated at scale. A few studies have begun to model conspiracy theories through recurring narrative elements (Batzdorfer, 2024 ; Piva et al., 2026) or cognitive traits (Bates et al., 2025) . However, these approaches primarily use such representations to support CT detection or to explain engagement with conspiratorial content. The automatic extraction of narrative components and their use for large-scale analyses of conspiracy discourse remain largely unexplored.  \nAmong these narrative components, actors occupy a central role. By identifying hidden actors behind seemingly unrelated events, conspiracy theories transform coincidence into intention and construct coherent explanatory narratives (Barkun, 2003) . Although actor-related categories have recently been proposed in conspiracy theory annotation frameworks (Batzdorfer, 2024 ; Piva et al., 2026), little attention has been paid to their reliable annotation and algorithmic extraction. This is particularly challenging because conspiratorial actors are often collective, implicit, or highly descriptive, making them fundamentally different from conventional named entities.  \nWe address this gap by developing annotation guidelines and a span-annotated corpus for conspiratorial actors in German Telegram posts. Building on this corpus, we train and evaluate transformerbased actor extraction models and demonstrate their utility by analyzing the representation and temporal evolution of conspiratorial actors in the Schwurbelarchiv (Angermaier et al., 2025), a ","cbCaipOcvmNnGT3K","https://ap.wps.com/l/cbCaipOcvmNnGT3K","pdf",328443,3,1,11,"English","en",105,"# Abstract\n# Introduction\n# Related Work\n# Actor Annotation\n## Conspiratorial Actors","[{\"question\":\"What does the document focus on regarding conspiracy theories?\",\"answer\":\"It focuses on identifying and extracting conspiratorial actors that drive conspiracy narratives, rather than relying mainly on document-level labels.\"},{\"question\":\"What resources and methods are introduced for actor identification?\",\"answer\":\"The study develops annotation guidelines, provides a span-annotated corpus of German Telegram posts, and trains transformer-based models to extract actor spans.\"},{\"question\":\"How is the proposed extraction approach validated or used after training?\",\"answer\":\"The resulting model is applied to Schwurbelarchiv, a large-scale archive of German conspiracy-related Telegram channels, to analyze actor representations and their temporal evolution.\"}]",1784191130,28,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"whos-behind-it-annotating-and-extracting-conspiratorial-actors-from-german-telegram-posts","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"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":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/whos-behind-it-annotating-and-extracting-conspiratorial-actors-from-german-telegram-posts/83873/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-23","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What does the document focus on regarding conspiracy theories?","Question",{"text":75,"@type":76},"It focuses on identifying and extracting conspiratorial actors that drive conspiracy narratives, rather than relying mainly on document-level labels.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What resources and methods are introduced for actor identification?",{"text":80,"@type":76},"The study develops annotation guidelines, provides a span-annotated corpus of German Telegram posts, and trains transformer-based models to extract actor spans.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the proposed extraction approach validated or used after training?",{"text":84,"@type":76},"The resulting model is applied to Schwurbelarchiv, a large-scale archive of German conspiracy-related Telegram channels, to analyze actor representations and their temporal evolution.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]