[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-116966-en":3,"doc-seo-116966-105":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},116966,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Rating online news popularity using machine learning - Degree Thesis","Recent advances in machine learning and deep learning have driven the creation of systems that learn from data to support real-world decisions. This degree thesis analyzes existing machine learning proposals for estimating the popularity of news published online, focusing on identifying key patterns and the most influential elements. It introduces and applies core machine learning concepts using multiple techniques to assess impact on readers and to inform writing and publishing strategies, then compares the effectiveness of the methods tested.","Rating online news popularity using machine learning  \nA Degree Thesis Submitted to the Faculties of  \nEscola Tècnica d'Enginyeria de Telecomunicació de  \nBarcelona  \nUniversitat Politècnica de Catalunya  \n&  \nDepartment of Information Engineering University of Padua  \nby  \nEduard Guitart i Manuel  \nAdvisors:  \nJuan Luis Gorricho  \n&  \nGiorgio Maria Di Nunzio  \nBarcelona, February 2023  \nAbstract  \nThe recent growth of machine learning and deep learning applications in the industry these last years has encouraged me to carry out this project. This thesis focuses on analyzing the existing proposals for systems based on machine learning to evaluate the popularity of news published online.  \nThis project explores the fundamentals of machine learning using different techniques to detect patterns in the data and the most relevant elements, in order to develop a strategy when writing and publishing news, so that they have a greater impact on the reader and therefore greater popularity. Finally, this work performs a comparative evaluation between the different methods used.  \nRevision history and approval record  \n\n| Revision | Date | Purpose |\n| --- | --- | --- |\n| 0 | 10/10/2022 | Document creation |\n| 1 | 10/12/2022 | Critical review |\n| 2 | 17/01/2023 | Final review |\n| 3 | 21/01/2023 | Delivery |\n|  |  |  |\n\nDOCUMENT DISTRIBUTION LIST  \n\n| Name | e-mail |\n| --- | --- |\n| Eduard Guitart i Manuel |  |\n| Juan Luis Gorricho Moreno |  |\n| Giorgio Maria Di Nunzio |  |\n|  |  |\n|  |  |\n|  |  |\n\n\n| Written by: Eduard Guitart i Manuel |  | Reviewed and approved by:\u003Cbr>Juan Luis Gorricho Moreno &\u003Cbr>Giorgio Maria Di Nunzio |  |\n| --- | --- | --- | --- |\n| Date | 10/10/2022 | Date |  |\n| Name | Eduard Guitart i Manuel | Name | Juan Luis Gorricho Moreno & Giorgio Maria Di Nunzio |\n| Position | Project Author | Position | Advisor |\n\nTable of contents  \nAbstract 1  \nRevision history and approval record 2  \nTable of contents 3  \n1. Introduction 4  \n1.1. Motivation 4  \n1.2. Project objectives 5  \n1.3. Project requirements and specifications 5  \n1.4. Methods and procedures 6  \n1.5. Workplan 6  \n1.5.1. Work Packages 6  \n1.5.2. Gantt Diagram 7  \n1.6. Deviations from original plan 8  \n2. Data Exploration 9  \n2.1. Dataset acquisition 9  \n2.2. Dataset variables description 9  \n2.3. Balancing data and dealing with null values 12  \n2.4. Detecting outliers 13  \n2.5. Feature selection & importance 13  \n3. Training Methodology 15  \n3.1. Linear / Quadratic 15  \n3.1.1.• Linear Regression 15  \n3.1.2.• Linear SVM 16  \n3.1.3.• Quadratic SVM 17  \n3.2. Non-linear 18  \n3.2.1.• SVM with RBF kernel 18  \n3.2.2.• Random Forest 19  \n3.2.3.• Neural Network 20  \n3.2.4.• LightGBM 20  \n3.3. Linear & Non-linear 21  \n3.3.1.• XGBoost 21  \n3.3.2.• PCA 21  \n4. Discussion of results 22  \n5. Conclusions and future improvements 27  \n6. Bibliography and Webliography 28  \n7. Annex 30  \n1. Introduction  \n1. 1. Motivation  \nIn this information age, reading and sharing news has become the focus of people’s entertainment lives. Therefore, it would be of great help if we could accurately predict the popularity of news before publication, for social media workers. The media can differentiate themselves from the competition by knowing the interests of their audience and by selecting from all available news the ones that their readers will find interesting. In this case, advertisers can also take advantage of knowing if a certain item becomes popular, if it gets a certain popularity rank, they can place their ads and increase sales.  \nWhich articles the readers click on, or don’t click, is influenced by several factors, typically, only the titles and short introductory descriptions of articles are displayed on the ‘‘Mainpage’’ of an outlet. Interesting and popular news are therefore those that succeed in getting the readers’ attention, and consequently their clicks. Popularity prediction is hard to capture as it depends upon various factors like its topic, text, timing, article’s position o","cbCaihARnPHsO2Eg","https://ap.wps.com/l/cbCaihARnPHsO2Eg","pdf",4417757,1,42,"English","en",105,"# Abstract\n# Revision history and approval record\n# Table of contents\n# 1. Introduction\n## 1.1 Motivation\n## 1.2 Project objectives\n## 1.3 Project requirements and specifications\n## 1.4 Methods and procedures\n## 1.5 Workplan\n## 2. Data Exploration\n## 3. Training Methodology\n## 4. Discussion of results\n## 5. Conclusions and future improvements\n## 6. Bibliography and Webliography\n## 7. Annex","[{\"question\":\"What problem does the thesis address?\",\"answer\":\"The thesis targets predicting the popularity of online news before publication using machine learning, aiming to quantify which factors influence readership attention and clicks.\"},{\"question\":\"Which types of data analysis and preprocessing are included?\",\"answer\":\"It covers dataset acquisition, dataset variable description, balancing data, handling null values, detecting outliers, and performing feature selection and importance estimation.\"},{\"question\":\"How does the thesis evaluate different machine learning methods?\",\"answer\":\"It trains and compares multiple models, including linear and non-linear methods such as Linear Regression, Linear SVM, Quadratic SVM, SVM with RBF kernel, Random Forest, Neural Network, LightGBM, XGBoost, and PCA.\"}]","Rating online news popularity using machine learning - Degree Thesis | PDF",1785672889,106,{"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},"rating-online-news-popularity-using-machine-learning-degree-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/rating-online-news-popularity-using-machine-learning-degree-thesis/116966/",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],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address?","Question",{"text":75,"@type":76},"The thesis targets predicting the popularity of online news before publication using machine learning, aiming to quantify which factors influence readership attention and clicks.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which types of data analysis and preprocessing are included?",{"text":80,"@type":76},"It covers dataset acquisition, dataset variable description, balancing data, handling null values, detecting outliers, and performing feature selection and importance estimation.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis evaluate different machine learning methods?",{"text":84,"@type":76},"It trains and compares multiple models, including linear and non-linear methods such as Linear Regression, Linear SVM, Quadratic SVM, SVM with RBF kernel, Random Forest, Neural Network, LightGBM, XGBoost, and PCA.","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"]