[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123375-en":3,"doc-seo-123375-105":30,"detail-sidebar-cat-0-en-105":96},{"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},123375,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Machine Learning-Based Fake Account Detection System - Instagram Case Study","People create fake social media accounts to hide identities, inflate follower counts, and support malicious activities, which can damage individuals and businesses and reduce authentic engagement on Instagram. This study evaluates multiple machine learning approaches for fake account detection, including single models (SVM, naïve Bayes, logistic regression, multilayer perceptron) and ensemble methods using bootstrap aggregating and boosting. A 10-fold cross-validation training/testing setup is used to reduce overfitting. Results show adaptive and gradient boosting achieve the strongest performance, exceeding 92% F1 and 93% precision.","| J. lnf. Commun. Converg. Eng. 23(2): 94-100, Jun. 2025 Regular paper |  |\n| --- | --- |\n| Machine Learning-Based Fake Account Detection System: Instagram Case Study\u003Cbr>Yulia1 , Hendy Gunawan1, Gregorius Satia Budhi1* , and Kartika Gunadi Kartawidjaja1 \u003Cbr>1Informatics Department, Petra Christian University, Surabaya 60236, Indonesia\u003Cbr>Abstract\u003Cbr>People often create fake social media accounts to express themselves anonymously. However, these fake accounts can harm the reputation of individuals and businesses, resulting in fewer genuine likes and followers. Instagram, a top-rated social media platform often used for business and political engagement, suffers from the negative impacts of these accounts. This highlights the urgent need for a dependable system to identify whether Instagram accounts are genuine. This study investigated several machine learning models for developing a fake account detection system. Single models, such as support vector machines, naïve Bayes, logistic regression, multilayer perceptron, and ensemble models based on bootstrap aggregating techniques and boosting, were trained and tested. The training and testing processes were conducted using a 10-fold cross-validation to prevent overfitting. The test results indicated that the adaptive and gradient boosting models achieved the best accuracy and an F1 score of more than 92%, with precision surpassing 93% .\u003Cbr>Index Terms: Fake account detection, Machine learning, Single and ensemble models, Social media |  |\n| I INTRODUCTION\u003Cbr>Many individuals endeavor to increase their follower count for various reasons, such as seeking fame or earning trust from others based on a large follower count [1] . Consequently, individuals create fake accounts to inflate their follower counts and use platforms for malicious activities, such as fraud and cyberbullying [2,3] . Furthermore, individuals create fake accounts to express themselves, exploit social media, and engage in other online activities without revealing their true identities to others [4] .\u003Cbr>Fake accounts pose problems for business owners who use influencers to promote their products. The influencers are paid using endorsements. The total number of influencer followers determines the endorsement process. It is crucial to recognize that this number can be artificially inflated by up to 78% by using fictitious followers (fake accounts) . Such manipulation | distorts the influencer’s genuine value and influence, resulting in business owners potentially overpaying for their endorsements [5] . The creation of fake accounts under false identities can be detrimental to the reputations of individuals and businesses, leading to a decrease in genuine likes and followers [1] .\u003Cbr>Instagram is one of the most active social media platforms worldwide [2,5] . It is used to share images and creative work for communication [1] . Over time, Instagram's role in social media has evolved. In addition to being a communication medium, Instagram is used for business and political purposes. Many celebrities have recently created Instagram accounts to develop their businesses and fan bases [6] . All types of fake accounts adversely affect social media benefits. This underscores the critical need for a reliable system to detect whether an Instagram account is fake. Real accounts are those in which the account owners utilize their real identity to make them |\n\nReceived 19 November 2024, Revised 16 March 2025, Accepted 1 April 2025  \n*Corresponding Author Gregorius Satia Budhi (E-mail: [greg@petra.ac.id](greg@petra.ac.id))  \nPetra Christian University, Informatics Department, Siwalankerto 103-144, Surabaya, East Java, 60236, Indonesia  \n [https://doi.org/10.56977/jicce.2025.23.2.94](https://doi.org/10.56977/jicce.2025.23.2.94) print ISSN: 2234-8255 online ISSN: 2234-8883  \nThis is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ([http://creativecommons.org/licenses/by](ht","cbCaiiglu3ES7tiV","https://ap.wps.com/l/cbCaiiglu3ES7tiV","pdf",1058895,1,7,"English","en",105,"# Introduction\n## Problems caused by fake social media accounts\n## Importance of detecting fake Instagram accounts\n## Related work and prior studies","[{\"question\":\"What problem does the study address for Instagram users and businesses?\",\"answer\":\"Fake accounts can inflate followers and engagement numbers, enabling fraud or cyberbullying and distorting influencers’ real impact, which can harm reputations and cause businesses to overpay endorsements.\"},{\"question\":\"Which machine learning models are evaluated in the study?\",\"answer\":\"The study tests single models including support vector machines, naïve Bayes, logistic regression, and multilayer perceptron, as well as ensemble models using bootstrap aggregating and boosting.\"},{\"question\":\"How are the models trained and evaluated to avoid overfitting?\",\"answer\":\"Training and testing use a 10-fold cross-validation procedure to reduce overfitting and obtain reliable performance estimates.\"},{\"question\":\"What models achieved the best reported performance?\",\"answer\":\"Adaptive boosting and gradient boosting deliver the best results, with accuracy over 92% F1 and precision above 93%.\"}]","Machine Learning-Based Fake Account Detection System - Instagram Case Study | PDF",1785816178,18,{"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":91,"head_meta":93,"extra_data":95,"updated_unix":28},"machine-learning-based-fake-account-detection-system-instagram-case-study","",{"@graph":36,"@context":90},[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/machine-learning-based-fake-account-detection-system-instagram-case-study/123375/",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",[72,78,82,86],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the study address for Instagram users and businesses?","Question",{"text":76,"@type":77},"Fake accounts can inflate followers and engagement numbers, enabling fraud or cyberbullying and distorting influencers’ real impact, which can harm reputations and cause businesses to overpay endorsements.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which machine learning models are evaluated in the study?",{"text":81,"@type":77},"The study tests single models including support vector machines, naïve Bayes, logistic regression, and multilayer perceptron, as well as ensemble models using bootstrap aggregating and boosting.",{"name":83,"@type":74,"acceptedAnswer":84},"How are the models trained and evaluated to avoid overfitting?",{"text":85,"@type":77},"Training and testing use a 10-fold cross-validation procedure to reduce overfitting and obtain reliable performance estimates.",{"name":87,"@type":74,"acceptedAnswer":88},"What models achieved the best reported performance?",{"text":89,"@type":77},"Adaptive boosting and gradient boosting deliver the best results, with accuracy over 92% F1 and precision above 93%.","https://schema.org",{"og:url":52,"og:type":92,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":94,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":97},[98,102,106,110,115,120,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"Exam",70,"exam",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},5,"Comic",60,"comic",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},6,"Technology",50,"technology",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},"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":111,"slug":142},19,"General","general"]