[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128609-en":3,"doc-seo-128609-105":30,"detail-sidebar-cat-0-en-105":92},{"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},128609,962084925502,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Automatic Document Classification in Technical Logbooks - A Comparative Study of Supervised Weakly Supervised and Unsupervised Machine Learning Approaches - Master Thesis","This study investigates automatic document classification in technical logbooks, introducing Labeling Functions by Dependency. Moving beyond conventional weakly supervised approaches, the work analyzes linguistic patterns and dependencies inside textual data and applies chi-squared tests for statistical validation. The study compares unsupervised, supervised, and weakly supervised strategies, and shows that Labeling Functions by Dependency delivers strong results, underscoring the role of rigorous NLP preprocessing. Overall, the research advances weakly supervised learning insights for unstructured text.","Master Degree Program in  \nData Science and Advanced Analytics  \nMDSAA  \nAutomatic Document Classification in Technical Logbooks  \nA Comparative Study of Supervised Weakly Supervised and Unsupervised Machine Learning Approaches  \nRobin Karl Schmidt  \nMaster Thesis  \npresented as partial requirement for obtaining a Master’s Degree in Data Science and Advanced Analytic~~s~~  \nNOVA Information Management School Instituto Superior de Estatística e Gestão de Informação  \nUniversidade Nova de Lisboa  \nNOVA Information Management School Instituto Superior de Estatística e Gestão de Informação  \nUniversidade Nova de Lisboa  \nAutomatic Document Classification in Technical Logbooks  \nA Comparative Study of Supervised Weakly Supervised and Unsupervised Machine Learning  \nApproaches  \nby  \nRobin Karl Schmidt  \nMaster Thesis presented as partial requirement for obtaining the Master’s degree in Data Science and Advanced Analytics, with a specialization in Business Analytics.  \nSupervised by  \nRoberto Henriques, PhD, NOVA Information Management School  \nFebruary, 2024  \nSTATEMENT OF INTEGRITY  \nI hereby declare having conducted this academic work with integrity. I confirm that I have not used plagiarism or any form of undue use of information or falsification of results along the process leading to its elaboration. I further declare that I have fully acknowledged the Rules of Conduct and Code of Honor from the NOVA Information Management School.  \nVienna, 04.02.2024  \nAbstract  \nThis study investigates automatic document classification in technical logbooks, introducing the innovative Labeling Functions by Dependency methodology. Departing from conventional weakly supervised approaches, this method focuses on unveiling linguistic patterns and dependencies within textual data, employing chi-squared tests for statistical validation. Alongside unsupervised and supervised approaches, Labeling Functions by Dependency demonstrated notable efficacy, highlighting the importance of thorough NLP preprocessing. The study contributes insights into weakly supervised learning, emphasizing the pivotal role of linguistic dependencies and preprocessing in achieving accurate document classification. The novel approach opens avenues for advancements in machine learning methodologies tailored to unstructured textual data.  \nKeywords: Document Classification, Technical Language, Supervised Machine Learning, Unsupervised Machine Learning, Semi-Supervised Machine Learning  \nContents  \nList of Figures vi  \n1 Introduction 1  \n2 Technical Background 4  \n2.1 Natural Language Processing ....................... 4  \n2.1.1 Key Components .......................... 4  \n2.1.2 Recent Advances . . . . . . . . . . . . . . . . . . . . . . . . . . 8  \n2.2 Unsupervised Machine Learning ..................... 10  \n2.2.1 Techniques .............................. 10  \n2.2.2 Challenges .............................. 14  \n2.2.3 Application ............................. 14  \n2.3 Supervised Machine Learning ....................... 15  \n2.3.1 Techniques .............................. 15  \n2.3.2 Metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17  \n2.3.3 Challenges .............................. 17  \n2.3.4 Application ............................. 18  \n2.4 Weakly Supervised Machine Learning .................. 19  \n2.4.1 Techniques .............................. 20  \n2.4.2 Metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21  \n2.4.3 Challenges .............................. 22  \n2.4.4 Application ............................. 23  \n2.5 Technical Language in Aviation ...................... 25  \n3 Related Work 27  \n4 Methodology 32  \n4.1 Data Collection and Preprocessing .................... 32  \n4.1.1 Technical Logbook ......................... 32  \n4.1.2 Test and Training Data ....................... 33  \n4.1.3 Preprocessing ............................ 34  \n4.1.4 Duplicates .............................. 37  \n4.2 Feature Selection and Extraction ","cbCaiuzy7zeRZptZ","https://ap.wps.com/l/cbCaiuzy7zeRZptZ","pdf",4497360,1,87,"English","en",105,"# Abstract\n# Keywords\n# Contents\n## List of Figures\n## 1 Introduction\n## 2 Technical Background\n## 3 Related Work\n## 4 Methodology\n## 5 Results","[{\"question\":\"What problem does the thesis address?\",\"answer\":\"The thesis addresses automatic document classification in technical logbooks, aiming to assign appropriate labels based on textual content.\"},{\"question\":\"What is the core methodological contribution?\",\"answer\":\"It introduces Labeling Functions by Dependency, which identifies linguistic patterns and dependencies and uses chi-squared tests to validate the approach.\"},{\"question\":\"How does the study evaluate different machine learning approaches?\",\"answer\":\"The research compares unsupervised, supervised, and weakly supervised methods, including labeling functions, with an emphasis on the impact of NLP preprocessing on classification quality.\"}]","Automatic Document Classification in Technical Logbooks - A Comparative Study of Supervised Weakly Supervised and Unsupervised Machine Learning Approaches - Master Thesis | PDF",1786002085,219,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"automatic-document-classification-in-technical-logbooks-a-comparative-study-of-supervised-weakly-supervised-and-unsupervised-machine-learning-approaches-master-thesis","",{"@graph":36,"@context":86},[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/automatic-document-classification-in-technical-logbooks-a-comparative-study-of-supervised-weakly-supervised-and-unsupervised-machine-learning-approaches-master-thesis/128609/",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","2026-08-23","2026-08-06",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the thesis address?","Question",{"text":76,"@type":77},"The thesis addresses automatic document classification in technical logbooks, aiming to assign appropriate labels based on textual content.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What is the core methodological contribution?",{"text":81,"@type":77},"It introduces Labeling Functions by Dependency, which identifies linguistic patterns and dependencies and uses chi-squared tests to validate the approach.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the study evaluate different machine learning approaches?",{"text":85,"@type":77},"The research compares unsupervised, supervised, and weakly supervised methods, including labeling functions, with an emphasis on the impact of NLP preprocessing on classification quality.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]