[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122287-en":3,"doc-seo-122287-105":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},122287,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Leveraging Machine Learning and Natural Language Processing Techniques for Agriculture Experiment Station Project Classification - Master of Science Thesis","USDA Critical Issues are topic titles used to label and classify USDA projects (e.g., Hatch, Hatch Multistate, Smith-Lever) into consistent groups. Efficient automated classification by USDA Critical Issue aims to reduce time and subjectivity tied to manual processing. This thesis applies unsupervised and supervised machine learning approaches using text preprocessing and feature representations, evaluating topic models such as LDA and assessing performance with multiple metrics and grouping strategies.","Leveraging Machine Learning and Natural Language Processing Techniques for Agriculture Experiment Station Project Classification  \nby  \nJyothi Prasanth Durairaj Rajeswari  \nA Creative Component submitted to the graduate faculty in partial fulfillment of the requirements for the degree of  \nMASTER OF SCIENCE  \nMajor: Computer Engineering  \nProgram of Study Committee:  \nJulie Dickerson, Major Professor  \nCarolyn J Lawrence-Dill, Co-major Professor  \nIowa State University  \nAmes, Iowa  \n2024  \nCopyright © Jyothi Prasanth Durairaj Rajeswari, 2024 . All rights reserved.  \nii  \nDEDICATION  \nI would like to dedicate this work to my beloved grandmother, uncle, and Aunt: Durga Venkatachalam, Sujandharan & Dhiviya; to my brother, Sukh Rythin Dev; to my sister, Priyadharshini; to my lovely cousin and niece, Pugalinban and Kavipugazhi; and my best friends, Mohamed Saajid and Prathiksha Ravi Krishnan. Without their encouragement and support, I would not have been able to attain my dream.  \nI lovingly dedicate this work to the memory of my dear father, Durairaj, whose unwavering support and affection resonate within me always.  \niii  \nTABLE OF CONTENTS  \nPage  \nLIST OF TABLES .......................................... v  \nLIST OF FIGURES ......................................... vii  \nACKNOWLEDGMENTS ...................................... viii  \nABSTRACT ............................................. ix  \nCHAPTER 1 . INTRODUCTION ................................. 1  \nCHAPTER 2 . DATA AND PRE-PROCESSING ......................... 3  \n2.1 Dataset ........................................... 3  \n2.2 Data Pre-processing .................................... 4  \n2.2.1 Text Cleaning .................................... 4  \n2.2.2 Tokenization .................................... 4  \n2.2.3 Lowercasing ..................................... 4  \n2.2.4 Substitutions .................................... 4  \n2.2.5 Filtering ....................................... 5  \n2.2.6 Lemmatization ................................... 5  \n2.2.7 Spell Checking ................................... 5  \nCHAPTER 3 . METHODS AND RESULTS ........................... 6  \n3.1 Unsupervised Learning ................................... 6  \n3.1.1 Introduction .................................... 6  \n3.1.2 Topic Modeling ................................... 6  \n3.1.3 Latent Dirichlet Allocation (LDA) ........................ 6  \n3.1.4 LDA models .................................... 6  \n3.1.5 Performance Metrics ................................ 10  \n3.2 Supervised Learning .................................... 14  \n3.2.1 Introduction .................................... 14  \n3.2.2 Supervised Learning Algorithms ......................... 14  \n3.2.3 Model Performance ................................. 16  \n3.2.4 Experimenting with Four New Groupings .................... 17  \n3.2.5 Experimenting with Six New Groupings ..................... 19  \n3.2.6 Experimenting with Five and Seven Groupings ................. 21  \nCHAPTER 4 . Discussion ...................................... 25  \niv  \nREFERENCES ............................................ 27  \nv  \nLIST OF TABLES  \nPage  \n2.1 Current Project Classification.......................... 3  \n3.1 Unigram model with 5 topics .......................... 7  \n3.2 Unigram model with 6 topics .......................... 7  \n3.3 Unigram model with 7 topics .......................... 8  \n3.4 Unigram-Perplexity and Coherence Scores .................. 8  \n3.5 Bigram model with 5 topics ........................... 9  \n3.6 Bigram model with 6 topics ........................... 9  \n3.7 Bigram model with 7 topics ........................... 10  \n3.8 Bigram-Perplexity and Coherence Scores ................... 10  \n3.9 Performance with current critical issues ..................... 16  \n3.10 Model Comparison before and after fine-tuning with current Critical Issues . 17  \n3.11 Four New Groupings ............................... 18  \n3.12 Four New Groupings with Number ","cbCaiahYy5J6pNGr","https://ap.wps.com/l/cbCaiahYy5J6pNGr","pdf",339197,1,38,"English","en",105,"# Table of Contents\n## List of Tables\n## List of Figures\n## Acknowledgments\n## Abstract\n## Chapter 1 - Introduction\n## Chapter 2 - Data and Pre-processing\n## 2.1 Dataset\n## 2.2 Data Pre-processing\n## 2.2.1 Text Cleaning\n## 2.2.2 Tokenization\n## 2.2.3 Lowercasing\n## 2.2.4 Substitutions\n## 2.2.5 Filtering\n## 2.2.6 Lemmatization\n## 2.2.7 Spell Checking\n## Chapter 3 - Methods and Results\n## 3.1 Unsupervised Learning\n## 3.1.1 Introduction\n## 3.1.2 Topic Modeling\n## 3.1.3 Latent Dirichlet Allocation (LDA)\n## 3.1.4 LDA models\n## 3.1.5 Performance Metrics\n## 3.2 Supervised Learning\n## 3.2.1 Introduction\n## 3.2.2 Supervised Learning Algorithms\n## 3.2.3 Model Performance\n## 3.2.4 Experimenting with Four New Groupings\n## 3.2.5 Experimenting with Six New Groupings\n## 3.2.6 Experimenting with Five and Seven Groupings\n## Chapter 4 - Discussion\n## References","[{\"question\":\"What is the problem addressed in this thesis?\",\"answer\":\"The thesis targets efficient and consistent automated classification of USDA projects into groups labeled by USDA Critical Issues, reducing the time and subjectivity of manual classification.\"},{\"question\":\"Which machine learning approaches are used for project classification?\",\"answer\":\"It uses both unsupervised learning (including topic modeling with LDA) and supervised learning, with experiments across multiple grouping setups.\"},{\"question\":\"How is the text data prepared before modeling?\",\"answer\":\"The workflow includes text cleaning, tokenization, lowercasing, substitutions, filtering, lemmatization, and spell checking to standardize the input text.\"}]","Leveraging Machine Learning and Natural Language Processing Techniques for Agriculture Experiment Station Project Classification - Master of Science Thesis | PDF",1785809831,96,{"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},"leveraging-machine-learning-and-natural-language-processing-techniques-for-agriculture-experiment-station-project-classification-master-of-science-thesis","",{"@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/leveraging-machine-learning-and-natural-language-processing-techniques-for-agriculture-experiment-station-project-classification-master-of-science-thesis/122287/",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","2026-08-04",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},"What is the problem addressed in this thesis?","Question",{"text":75,"@type":76},"The thesis targets efficient and consistent automated classification of USDA projects into groups labeled by USDA Critical Issues, reducing the time and subjectivity of manual classification.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning approaches are used for project classification?",{"text":80,"@type":76},"It uses both unsupervised learning (including topic modeling with LDA) and supervised learning, with experiments across multiple grouping setups.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the text data prepared before modeling?",{"text":84,"@type":76},"The workflow includes text cleaning, tokenization, lowercasing, substitutions, filtering, lemmatization, and spell checking to standardize the input text.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":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"]