[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124310-en":3,"doc-seo-124310-105":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},124310,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Towards Better Product Quality - Identifying Legitimate Quality Issues through NLP & Machine Learning Techniques","High-end manufacturers rely on customer complaints and service repair job records to monitor product quality and guide corrective actions that improve design, manufacturing, and support. Distinguishing legitimate quality issues from short, domain-specific service text remains difficult, especially as multilingual, unstructured data volumes grow. This study automates classification of technical service repair data into legitimate quality issues or non-issues using an NLP and machine learning pipeline with preprocessing, imbalance handling, TF-IDF feature extraction, and model evaluation. Experimental results indicate strong performance, with a passive-aggressive classifier achieving top accuracy and macro F1.","Towards Better Product Quality: Identifying Legitimate Quality Issues through NLP & Machine Learning Techniques  \nRakhshanda Jabeen 1 ,2 , Morgan Ericsson2 and Jonas Nordqvist3  \nAbstract—Manufacturers of high-end professional products are committed to delivering outstanding customer-quality experiences. They maintain databases of customer complaints and repair service jobs data to monitor product quality. Analyzing the text data from service jobs can help identify common problems, recurring issues, and patterns that impact customer satisfaction, and aid manufacturers in taking corrective actions to improve product design, manufacturing processes, and customer support services. However, distinguishing legitimate quality issues from a brief, domain-specific text in service jobs remains a challenge. This study aims to automate the classification of technical service repair job data into legitimate quality issues or non-issues to assist individuals in the quality field department in a large company. To achieve this goal, we developed a comprehensive pipeline based on natural language processing and machine learning techniques including raw text preprocessing, dealing with imbalance class distribution, feature extraction, and classification. In this study, We evaluate several feature extraction and machine learning classification methods and perform the Friedman test followed by Nemenyi post-hoc analysis to find the best-performing model. Our results show that the passive-aggressive classifier achieved the highest average accuracy of 94% and 89% average macro F1-score when trained on TF-IDF vectors.  \nI. INTRODUCTION  \nWith the rapid growth of unstructured data in electronic text formats, natural language processing (NLP)—a subfield of linguistics, computer science, and AI, has emerged as a vital field of research. NLP enables machines to understand and interpret human language. Companies are beginning to recognize the economic value of their text data repositories, including social media platforms and internal document collections, for informed decision-making [1] .  \nThe text classification task is one of the most essential tasks in NLP. It involves the automatic categorization of text documents into predefined classes based on their content using machine learning (ML) methods. The process generally includes several steps, including preprocessing (which involvestokenization, stopwords and noise removal, and lemmatization [2]), feature extraction (which involves converting natural language into numerical vectors for mathematical computation), and finally, modeling the data using an appropriate machine learning algorithm for classification. These techniques have a wide range of applications in various industries, such as healthcare, the Internet of Things (IoT), security, spam filtering, digital marketing, and sentiment analysis [3, 4] .  \nThis research aims to address the challenge faced by a multinational professional appliance manufacturing company,  \n1Electrolux Professional AB, Sweden  \n2Department of Computer Science and Media Technology, Linnaeus University, Växjö, Sweden  \n3Department of Mathematics, Linnaeus University, Växjö, Sweden  \nin the manual categorization of service repair data of machines to filter the legitimate quality issues in service jobs. Technical service agents are responsible for resolving customers’ issues and providing a text description of the resolution. The quality field department then manually assesses and classifies the service jobs to determine if it is a genuine quality issue and requires attention at the production and design levels. However, with a growing volume of data in multiple languages, manual classification has become increasingly complex. Therefore, an  \nautomatic solution for the classification process is necessary to save time and resources while ensuring consistency and accuracy.  \nWang et al. [5] proposed a medical triage system that uses NLP and ML methods to classify questions","cbCainI3pVTJp0lt","https://ap.wps.com/l/cbCainI3pVTJp0lt","pdf",218779,1,9,"English","en",105,"# Introduction\n## Text Classification in NLP\n## Industry Applications of NLP & ML\n## Problem Statement and Research Questions","[{\"question\":\"What problem does the study address in product quality monitoring?\",\"answer\":\"The study targets the challenge of separating legitimate quality issues from non-issues in brief, domain-specific text from technical service repair jobs.\"},{\"question\":\"How does the proposed solution work?\",\"answer\":\"It builds an NLP and machine learning pipeline including raw text preprocessing, handling imbalanced classes, feature extraction (TF-IDF vectors), and supervised classification.\"},{\"question\":\"Which model performed best in the study’s evaluation?\",\"answer\":\"The passive-aggressive classifier delivered the highest average accuracy (94%) and the best average macro F1-score (89%) when trained on TF-IDF vectors.\"}]","Towards Better Product Quality - Identifying Legitimate Quality Issues through NLP & Machine Learning Techniques | PDF",1785821514,23,{"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},"towards-better-product-quality-identifying-legitimate-quality-issues-through-nlp-machine-learning-techniques","",{"@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/towards-better-product-quality-identifying-legitimate-quality-issues-through-nlp-machine-learning-techniques/124310/",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","2026-08-05","2026-08-04",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 study address in product quality monitoring?","Question",{"text":76,"@type":77},"The study targets the challenge of separating legitimate quality issues from non-issues in brief, domain-specific text from technical service repair jobs.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the proposed solution work?",{"text":81,"@type":77},"It builds an NLP and machine learning pipeline including raw text preprocessing, handling imbalanced classes, feature extraction (TF-IDF vectors), and supervised classification.",{"name":83,"@type":74,"acceptedAnswer":84},"Which model performed best in the study’s evaluation?",{"text":85,"@type":77},"The passive-aggressive classifier delivered the highest average accuracy (94%) and the best average macro F1-score (89%) when trained on TF-IDF vectors.","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},[94,98,102,106,111,116,121,124,128,131,135],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},"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":107,"slug":138},19,"General","general"]