[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118589-en":3,"doc-seo-118589-105":30,"detail-sidebar-cat-0-en-105":95},{"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},118589,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Classifying Bugs in Code Using Machine Learning Models - Bachelor’s Thesis","Rapid growth in software development has increased the number and frequency of bugs in large code bases, while strict deadlines make accurate issue understanding more critical than ever. Bug reports stored in repositories provide key starting information, but effective resolution depends on developers interpreting descriptions and selecting suitable tools. This thesis presents a machine learning approach that predicts bug categories from bug-report text using trained and evaluated models with multiple feature extraction techniques, reaching up to 60% macro-average F1. It also compares model performance and assesses practical feasibility.","Vasav Juyal  \nCLASSIFYING BUGS IN CODE USING MACHINE LEARNING MODELS  \nBachelor’s Thesis  \nFaculty of Engineering and Natural Sciences Examiner: Mika Saari  \nMarch 2025  \nABSTRACT  \nVasav Juyal: Classifying bugs in code using machine learning models Bachelor’s Thesis  \nTampere University  \nBachelor’s Degree in Science and Engineering  \nMarch 2025  \nThe rapid growth of the software development industry has resulted in an exponential increase in the number of code-based applications. As the volume of code continues to grow daily and strict deadlines remain, the prevalence of bugs in the code is increasing at an accelerated pace. Developing teams keep track of bugs in the code base by documenting them in repositories, usually in the form of issues or bug reports. Bug reports serve as a valuable resource, detailing where bugs occur and the issues they create. They provide a starting point for developers tasked with resolving them. The decisions a developer makes to address the issue depend on their comprehension of the bug. Their ability to choose the right tools or enhance efficiency depends on understanding the bug, which can be improved by categorizing bugs into classes for added insight.  \nThis thesis proposes a machine learning approach to predict the category that the bugs fall into based on their descriptions. Using bug reports gathered from projects into datasets, machine learning models were trained and evaluated for this approach. With various feature extraction techniques, the models were able to reach up to 60% macro average F1 score for the bug classification objective. Additionally, the machine learning models were evaluated to identify the best-performing one, along with an assessment of the overall feasibility of this approach in practical applications.  \nKeywords: software development, machine learning, bugs, bug classification, natural language processing  \nThe originality of this thesis has been checked using the Turnitin OriginalityCheck service.  \nThe AI tools used in my thesis are described below:  \nMicrosoft Copilot:  \nSynonyms for words as well as advice on phrasing in paragraphs , Sections 1, 2. 1, 5  \nChatGPT (OpenAI GPT-4):  \nHelp with manual labelling of bug reports into different classes.  \nI am aware that I am fully responsible for the entire content of my thesis, including the AIgenerated parts, and I accept responsibility for any violations of the ethical guidelines.  \nPREFACE  \nI would like to thank my brother for his advice in the writing of this thesis. His help played a key role in ensuring the completion of this thesis.  \nI would also like to thank my supervisor for his guidance throughout the whole process and his essential feedback that contributed to the quality of this work.  \n15th March, 2025 Vasav Juyal  \nCONTENTS  \n1. INTRODUCTION .................................................................................................. 1  \n2. BACKGROUND AND THEORY ............................................................................ 3  \n2.1 Bug Reporting........................................................................................ 3  \n2.2 Feature Extraction ................................................................................. 3  \n2.3 Machine Learning Models ...................................................................... 5  \n2.3.1 Logistic Regression....................................................................... 6  \n2.3.2 Random Forest ............................................................................. 7  \n2.3.3 Support Vector Machine................................................................ 8  \n2.4 Performance Metrics.............................................................................. 9  \n3. DATA PROCESSING AND TRAINING ............................................................... 10  \n3.1 Dataset Description and Labelling ....................................................... 11  \n3.2 Data Preparation .....................","cbCaiaSDsmt0FWyQ","https://ap.wps.com/l/cbCaiaSDsmt0FWyQ","pdf",779094,1,31,"English","en",105,"# Introduction\n# Background and Theory\n## Bug Reporting\n## Feature Extraction\n## Machine Learning Models\n## Performance Metrics\n# Data Processing and Training\n## Dataset Description and Labelling\n## Data Preparation\n## Model Training\n# Results Analysis\n# Conclusion","[{\"question\":\"What problem does the thesis address?\",\"answer\":\"The thesis targets the increasing volume of bugs in growing code bases and the need to better understand bug reports so developers can address issues more efficiently.\"},{\"question\":\"How does the proposed approach classify bugs?\",\"answer\":\"It trains machine learning models on bug-report datasets so the models can predict a bug’s category based on the textual bug description, using multiple feature extraction techniques.\"},{\"question\":\"What performance level did the models achieve?\",\"answer\":\"Using the bug-classification objective, the models reached up to 60% macro average F1 score across evaluated settings.\"},{\"question\":\"Which machine learning models were evaluated in the study?\",\"answer\":\"The thesis evaluates models including Logistic Regression, Random Forest, and Support Vector Machine, and compares their best-performing results across feature sets.\"}]","Classifying Bugs in Code Using Machine Learning Models - Bachelor’s Thesis | PDF",1785684405,78,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"classifying-bugs-in-code-using-machine-learning-models-bachelors-thesis","",{"@graph":36,"@context":89},[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/classifying-bugs-in-code-using-machine-learning-models-bachelors-thesis/118589/",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","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address?","Question",{"text":75,"@type":76},"The thesis targets the increasing volume of bugs in growing code bases and the need to better understand bug reports so developers can address issues more efficiently.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed approach classify bugs?",{"text":80,"@type":76},"It trains machine learning models on bug-report datasets so the models can predict a bug’s category based on the textual bug description, using multiple feature extraction techniques.",{"name":82,"@type":73,"acceptedAnswer":83},"What performance level did the models achieve?",{"text":84,"@type":76},"Using the bug-classification objective, the models reached up to 60% macro average F1 score across evaluated settings.",{"name":86,"@type":73,"acceptedAnswer":87},"Which machine learning models were evaluated in the study?",{"text":88,"@type":76},"The thesis evaluates models including Logistic Regression, Random Forest, and Support Vector Machine, and compares their best-performing results across feature sets.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]