[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-595660-105":59,"doc-detail-595660-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","discourse-classification-into-rhetorical-functions-for-awe-feedback","Discourse Classification into Rhetorical Functions for AWE Feedback","","Research on automated writing evaluation develops an analysis engine for the Research Writing Tutor (RWT), an AWE program providing genre- and discipline-specific feedback for research-article discourse. The approach classifies every sentence in Introduction sections into communicative moves and rhetorical steps, rather than categorizing whole documents. A cascade of two SVM classifiers is trained on a multi-disciplinary corpus of annotated texts, demonstrating the value of NLP for automated genre analysis and enabling functional-meaning feedback in future AWE systems.",{"@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/discourse-classification-into-rhetorical-functions-for-awe-feedback/595660/",{"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/discourse-classification-into-rhetorical-functions-for-awe-feedback/595660.png","ImageObject",300,407,{"name":92,"@type":93},"Well Done","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-22","2026-10-15",true,{"@type":102,"interactionType":103,"userInteractionCount":81},"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 study presented in the paper?","Question",{"text":112,"@type":113},"To develop an automated analysis engine for an AWE system that identifies rhetorical structure in research articles using communicative moves and functional steps, and then provides feedback against genre norms in learners’ disciplines.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the analyzer differ from traditional document-level categorization?",{"text":117,"@type":113},"Instead of categorizing complete documents, it categorizes every sentence in Introduction section texts as both a communicative move and a rhetorical step.",{"name":119,"@type":110,"acceptedAnswer":120},"What machine learning approach is used in the proposed system?",{"text":121,"@type":113},"The system uses a cascade of two support vector machine (SVM) classifiers trained on a multi-disciplinary corpus of annotated texts.","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},595660,1792191668,{"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":81,"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":145},5909892210082,"https://ap-avatar.wpscdn.com/avatar/56001069da27c9f41e8?x-image-process=image/resize,m_fixed,w_180,h_180&k=1789614185077863061","calico journal (online) issn 2056–9017  \nArticle  \nDiscourse Classification into Rhetorical Functions for AWE Feedback  \nElena Cotos and Nick Pendar  \nAbstract  \nThis paper reports on the development of an analysis engine for the Research Writing Tutor (RWT), an AWE program designed to provide genre and discipline-specific feedback on the functional units of research article discourse. Unlike traditional NLP-based applications that categorize complete documents, the analyzer categorizes every sentence in Introduction section texts as both a communicative move anda rhetorical step. We describe the construction of a cascade of two support vector machine classifiers trained on a multi-disciplinary corpus of annotated texts. This work not only demonstrates the usefulness of NLP for automated genre analysis, but alsopaves the road for future AWE endeavors and forms of automated feedback that could facilitate effective expression of functional meaning in writing.  \nKeywords: Automated writing evaluation; genre; machine learning; moves; text categorization  \nIntroduction  \nSecond language acquisition research, in consensus with views in psychology, has long argued that individuals learn languages differently depending on such influencing factors as idiosyncratic learning strategies, cognitive styles, and various affective factors (Dörnyei & Skehan, 2003) . Since it is not in the power of a human teacher to adapt to all learner differences and to provide individualized instruction to groups of students, computers have been  \nAffiliation  \nIowa State University, Ames, IA 50011-12-01, United States [email: ecotos@iastate.edu](email: ecotos@iastate.edu) (corresponding author)  \ncalico journal vol 33.1 2016 92–116 ©2016, equinox publishing  \ndoi : 10.1558/cj.v33i1.27047  \nElena Cotos and Nick Pendar 93  \nproposed as a powerful and practical complementary alternative. In the past decades, Natural Language Processing (NLP), which is superior to the socalled pattern-markup and error-anticipation techniques used to generate conventional types of feedback (Garret, 1987), has been commonly employed for the purpose of identifying problematic aspects in learner language, diagnosing language errors, and providing detailed explanations about the nature of those errors. In particular, NLP techniques have been exploited for individual feedback generation by Intelligent Computer Assisted Language Learning (ICALL) systems, generally addressing the complexity of morphology, syntax, semantics, and pragmatics (see Gamper & Knapp, 2002). The domain of Automated Writing Evaluation (AWE) has also employed NLP in a variety of ways to provide learners with feedback on grammar, usage, mechanics, style, organization, coherence, content, etc. (see Dikli, 2006) .  \nDespite considerable advances in NLP, analyzing the various aspects of natural language is still a challenging problem that remains to be solved in order to meet a wider range of learning needs. One such need is mastering the writing conventions of academic genres. Research in English for academic purposes has a well-established genre-analysis agenda (see Biber, Connor, & Upton, 2007; Hyland, 2000) . This agenda needs to be extrapolated to interdisciplinary research involving applied and computational linguists and computer scientists, whose combined efforts would result in the creation of new needs-based intelligent feedback systems.  \nThe study presented in this paper is beginning to fill this void. Our main goal was to develop an automated analysis engine for an AWE system that identifies the rhetorical structure of research articles (RA) in terms of communicative moves and functional steps (Swales, 1990) and provides feedback compared to the RA genre norms in learners’ particular disciplines. Before describing this work, we review the approaches to and implementations of automated discourse categorization in order to provide a background for our automated genre analysis methodology. Focusing on RA I","cbCaiskKIidhDkpM","https://ap.wps.com/l/cbCaiskKIidhDkpM","pdf",1446408,25,"English","# Abstract\n# Introduction\n## Second language acquisition and NLP-based feedback\n## Need for academic genre analysis\n# Automated text categorization\n## Text categorization in machine learning\n## Supervised learning and corpus-based classifiers","[{\"question\":\"What is the main goal of the study presented in the paper?\",\"answer\":\"To develop an automated analysis engine for an AWE system that identifies rhetorical structure in research articles using communicative moves and functional steps, and then provides feedback against genre norms in learners’ disciplines.\"},{\"question\":\"How does the analyzer differ from traditional document-level categorization?\",\"answer\":\"Instead of categorizing complete documents, it categorizes every sentence in Introduction section texts as both a communicative move and a rhetorical step.\"},{\"question\":\"What machine learning approach is used in the proposed system?\",\"answer\":\"The system uses a cascade of two support vector machine (SVM) classifiers trained on a multi-disciplinary corpus of annotated texts.\"}]","Discourse Classification into Rhetorical Functions for AWE Feedback | PDF",1792081576,63]