[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119610-en":3,"doc-seo-119610-105":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":4,"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},119610,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Pathways to Radicalisation - On Radicalisation Research in Natural Language Processing and Machine Learning","Violent ideologies flourish in online communities that sanction extremist content. Communication in such communities spans multiple modalities—text, memes, videos, and podcasts—that collectively radicalise their audiences. This position paper argues that radicalisation is an emerging research area where NLP and machine learning are especially well-suited. These approaches can reduce harms from human review while helping validate theories, while also enabling progress on key ML/NLP challenges such as temporal distribution shifts and multimodal alignment.","Edinburgh Research Explorer  \nPathways to radicalisation  \nOn research for online radicalisation in natural language processing and machine learning  \nCitation for published version:  \nTalat, Z, Schlichtkrull, MS, Madhyastha, P & De Kock, C 2025, Pathways to radicalisation: On research for online radicalisation in natural language processing and machine learning. in A Calabrese, C de Kock, DNozza, FM Plaza-del-Arco, Z Talat & F Vargas (eds), Proceedings of the 9th Workshop on Online Abuse and Harms. Association for Computational Linguistics, Kerrville, TX, USA, pp. 276-283, The 9th Workshop on Online Abuse and Harms, Vienna, Austria, 31/07/25 . \u003C[https://aclanthology.org/2025.woah-1.25/](https://aclanthology.org/2025.woah-1.25/)>  \nLink:  \nLink to publication record in Edinburgh Research Explorer  \nDocument Version:  \nPublisher's PDF, also known as Version of record  \nPublished In:  \nProceedings of the 9th Workshop on Online Abuse and Harms  \nPublisher Rights Statement:  \nACL materials are Copyright © 1963–2025 ACL; other materials are copyrighted by their respective copyright holders. Materials prior to 2016 here are licensed under the Creative Commons Attribution-NonCommercialShareAlike 3.0 International License. Permission is granted to make copies for the purposes of teaching and research. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.  \nGeneral rights  \nCopyright for the publications made accessible via the Edinburgh Research Explorer is retained by the author(s) and / or other copyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights.  \nTake down policy  \nThe University of Edinburgh has made every reasonable effort to ensure that Edinburgh Research Explorer content complies with UK legislation. If you believe that the public display of this file breaches copyright please [contact openaccess@ed.ac.uk](contact openaccess@ed.ac.uk) providing details, and we will remove access to the work immediately and investigate your claim.  \nDownload date: 11. Jan. 2026  \nPathways to Radicalisation: On Radicalisation Research in Natural Language Processing and Machine Learning  \nZeerak Talat  \nUniversity of Edinburgh [z@zeerak.org](z@zeerak.org)  \nPranava Madhyasta  \nThe Alan Turing Institute City, University of London [pmadhyastha@turing.ac.uk](pmadhyastha@turing.ac.uk)  \nMichael Sejr Schlichtkrull  \nQueen Mary University of London [m.schlichtkrull@qmul.ac.uk](m.schlichtkrull@qmul.ac.uk)  \nChristine de Kock  \nUniversity of Melbourne [christine.dekock@unimelb.edu.au](christine.dekock@unimelb.edu.au)  \nAbstract  \nViolent ideologies flourish in online communities that sanction extremist content. Communication in such communities includes a variety of modalities, such as text, memes, videos, and podcasts, which collectively radicalise their consumers. In this position paper, we argue that radicalisation is a nascent area for which machine learning and NLP are particularly apt. On the one hand, these technologies could mitigate the harms of human review of extremist content and stand to validate theories of radicalisation. On the other, such communities present an avenue for addressing key challenges in machine learning and NLP technologies, such as temporal distribution shiftsand multi-modal alignment.  \n1 Introduction  \nInternet-facilitated radicalisation is an urgent modern challenge, with links to both acts of physical violence and intangible social harms. The proliferation of online content that espouses extremist views presents a challenge for scalable content moderation and prevention of radicalization. For NLP methods tobe applied for such purposes, they must take into account the nature of radicalisation and communication in fora where radicalisation occurs. First, language use in radicalised communities is highly dissimilar from standard language use in more sanitised ar","cbCaibWb1lJl5e1G","https://ap.wps.com/l/cbCaibWb1lJl5e1G","pdf",332648,1,9,"English","en",105,"# Abstract\n# Introduction\n## Internet-facilitated radicalisation as a moderation challenge\n## Language divergence in radicalised communities\n## Temporal distribution shifts and few-shot adaptation\n## Governance dynamics and policy/legal constraints\n## Longitudinal multimodal data shaping ideology\n# Position paper contributions and implications","[{\"question\":\"Why is NLP and machine learning considered suitable for radicalisation research?\",\"answer\":\"The paper argues that these technologies can both mitigate harms associated with human review and support validation of theories of radicalisation in an emerging research area.\"},{\"question\":\"What challenges does the paper highlight for applying NLP methods in radicalised communities?\",\"answer\":\"It emphasizes dissimilar language from mainstream internet usage and major temporal distribution shifts that break assumptions of static models.\"},{\"question\":\"How does the paper describe the role of multimodal data in radicalisation?\",\"answer\":\"It states that memes, podcasts, videos, and written documents collectively influence opinions, beliefs, and actions over time, requiring models that account for multimodal radicalisation.\"}]","Pathways to Radicalisation - On Radicalisation Research in Natural Language Processing and Machine Learning | PDF",1785725280,23,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"pathways-to-radicalisation-on-radicalisation-research-in-natural-language-processing-and-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@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/pathways-to-radicalisation-on-radicalisation-research-in-natural-language-processing-and-machine-learning/119610/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is NLP and machine learning considered suitable for radicalisation research?","Question",{"text":75,"@type":76},"The paper argues that these technologies can both mitigate harms associated with human review and support validation of theories of radicalisation in an emerging research area.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What challenges does the paper highlight for applying NLP methods in radicalised communities?",{"text":80,"@type":76},"It emphasizes dissimilar language from mainstream internet usage and major temporal distribution shifts that break assumptions of static models.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the paper describe the role of multimodal data in radicalisation?",{"text":84,"@type":76},"It states that memes, podcasts, videos, and written documents collectively influence opinions, beliefs, and actions over time, requiring models that account for multimodal radicalisation.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":20,"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":53,"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":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]