[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-502079-105":59,"doc-detail-502079-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","authorship-attribution-using-text-distortion","Authorship Attribution Using Text Distortion","","Authorship attribution supports forensic and humanities research by identifying the writer of disputed text and by modeling individual writing style. The paper introduces a text distortion step before computing stylometric features, aiming to suppress topic-specific content unrelated to personal style. Experiments on closed-set attribution and authorship verification show improved effectiveness, particularly under cross-topic conditions where training and test corpora differ in topic.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/authorship-attribution-using-text-distortion/502079/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/authorship-attribution-using-text-distortion/502079.png","ImageObject",300,407,{"name":92,"@type":93},"Terk","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-18","2026-10-03",true,{"@type":102,"interactionType":103,"userInteractionCount":24},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the main goal of the proposed method?","Question",{"text":112,"@type":113},"To enhance authorship attribution by applying a text distortion step before extracting stylometric measures, masking topic-specific information not tied to personal writing style.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How is the personal writing style modeled in the paper?",{"text":117,"@type":113},"Through stylometry, using features intended to depend on personal style while ideally being robust to shifts in topic or genre.",{"name":119,"@type":110,"acceptedAnswer":120},"In which settings does the method improve results?",{"text":121,"@type":113},"It improves effectiveness in both closed-set attribution and authorship verification, especially under cross-topic conditions where training and test corpora do not match in topic.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},502079,1791406358,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":24,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":41},1099525198933,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Authorship Attribution Using Text Distortion  \nEfstathios Stamatatos  \nUniversity of the Aegean 83200, Karlovassi, Samos, Greece [stamatatos@aegean.gr](stamatatos@aegean.gr)  \nAbstract  \nAuthorship attribution is associated with important applications in forensics and humanities research. A crucial point in this field is to quantify the personal style of writing, ideally in a way that is not affected by changes in topic or genre. In this paper, we present a novel method that enhances authorship attribution effectiveness by introducing a text distortion step before extracting stylometric measures. The proposed method attempts to mask topicspecific information that is not related to the personal style of authors. Based on experiments on two main tasks in authorship attribution, closed-set attribution and authorship verification, we demonstrate that the proposed approach can enhance existing methods especially under cross-topic conditions, where the training and test corpora do not match in topic.  \n1 Introduction  \nAuthorship attribution is the task of determining the author of a disputed text given a set of candidate authors and samples of their writing (Juola, 2008; Stamatatos, 2009) . This task has gained increasing popularity since it is associated with important forensic applications, e.g., identifying the authors of anonymous messages in extremist forums, verifying the author of threatening email messages, etc. (Abbasi and Chen, 2005; Lambersand Veenman, 2009; Coulthard, 2013), as well as humanities and historical research, e.g., unmasking the authors of novels published anonymously or under aliases, verifying the authenticity of literary works by specific authors, etc. (Koppel and Seidman, 2013; Juola, 2013; Stover et al., 2016) .  \nThe majority of published works in authorship  \nattribution focus on closed-set attribution where it is assumed that the author of the text under investigation is necessarily a member of a given well-defined set of candidate authors (Stamatatoset al., 2000; Gamon, 2004; Escalante et al., 2011; Schwartz et al., 2013; Savoy, 2013; Seroussi et al., 2014) . This setting fits many forensic applications where usually specific individuals have access to certain resources, have knowledge of certain issues, etc. (Coulthard, 2013) A more general framework is open-set attribution (Koppel et al., 2011) . A special case of the latter is authorship verification where the set of candidate authors is singleton (Stamatatos et al., 2000; van Halteren, 2004; Koppel et al., 2007; Jankowska et al., 2014; Koppel and Winter, 2014) . This is essentially a one-class classification problem since the negative class (i.e., all texts by all other authors) is huge and extremely heterogeneous. Recently, the verification setting became popular in research community mainly due to the corresponding PAN shared tasks (Stamatatos et al., 2014; Stamatatos et al., 2015) .  \nIn authorship attribution it is not always realistic to assume that the texts of known authorship and the texts under investigation belong in the same genre and are in the same thematic area. In most applications, there are certain restrictions that do not allow the construction of a representative training corpus. Unlike other text categorization tasks, a recent trend in authorship attribution research is to build cross-genre and crosstopic models, meaning that the training and test corpora do not share the same properties (Kestemont et al., 2012; Stamatatos, 2013; Sapkota et al., 2014; Stamatatos et al., 2015) .  \nOne crucial issue in any authorship attribution approach is to quantify the personal style of authors, a line of research also called stylometry (Stamatatos, 2009) . Ideally, stylometric fea-  \n1138  \nProceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 1138–1149,  \nValencia, Spain, April 3-7, 2017 . 􀀍c2017 Association for Computational Linguistics  \ntures should not be affect","cbCaidbpcuLBpoMg","https://ap.wps.com/l/cbCaidbpcuLBpoMg","pdf",324178,12,"English","# 1 Introduction\n# 2 Related Work","[{\"question\":\"What is the main goal of the proposed method?\",\"answer\":\"To enhance authorship attribution by applying a text distortion step before extracting stylometric measures, masking topic-specific information not tied to personal writing style.\"},{\"question\":\"How is the personal writing style modeled in the paper?\",\"answer\":\"Through stylometry, using features intended to depend on personal style while ideally being robust to shifts in topic or genre.\"},{\"question\":\"In which settings does the method improve results?\",\"answer\":\"It improves effectiveness in both closed-set attribution and authorship verification, especially under cross-topic conditions where training and test corpora do not match in topic.\"}]","Authorship Attribution Using Text Distortion | PDF",1791028827]