[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-291064-105":59,"doc-detail-291064-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","a-machine-learning-approach-for-pornographic-website-content-detection-part","A Machine Learning Approach for Pornographic Website Content Detection - Part","","Rapid internet expansion has heightened concerns about exposure to pornographic material, especially for younger users. This study targets the shortage of large-scale Indonesian-focused research by proposing a Naïve Bayes-based classifier enhanced with comprehensive preprocessing and class balancing. A dataset of 50,329 Indonesian website entries collected from 2019 to 2026 was processed to improve textual feature quality. SMOTE mitigated class imbalance, and 5-fold cross-validation compared MNB, BNB, and GNB, where MNB achieved about 94% accuracy and 0.986 ROC-AUC, supporting automated web filtering.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/a-machine-learning-approach-for-pornographic-website-content-detection-part/291064/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/a-machine-learning-approach-for-pornographic-website-content-detection-part/291064.png","ImageObject",300,407,{"name":92,"@type":93},"Theodora","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-06","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",17,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the study address?","Question",{"text":113,"@type":114},"The study addresses the increased risk of users—especially younger users—being exposed to pornographic content online and the need for effective automated detection methods.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How is class imbalance handled in the proposed approach?",{"text":118,"@type":114},"The Synthetic Minority Oversampling Technique (SMOTE) is applied during training to balance pornographic and non-pornographic classes.",{"name":120,"@type":111,"acceptedAnswer":121},"Which Naïve Bayes variant performs best and what metrics are reported?",{"text":122,"@type":114},"Multinomial Naïve Bayes (MNB) achieves the best results, with about 94% accuracy, precision 0.92, recall 0.94, F1-score 0.93, and ROC-AUC 0.986.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},291064,1790500138,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":4},687197207919,"https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552","A Machine Learning Approach for Pornographic Website Content Detection Using an Optimised Naïve Bayes Classifier Rahmalia Syahputri a, 1,*, Taufik b,2 , Aldwi Mandak a,3 , Prana Alfath Raisa,4  \na Institut Informatika dan Bisnis Darmajaya, Jl. Z.A Pagar Alam No. 93, Bandar Lampung 35142, Indonesia b Institut Bakti Nusantara, Jl. Raya Wisma Rini No. 9, Pringsewu 35711, Indonesia  \n[1](1 rahmalia@darmajaya.ac.id)[ rahmalia@darmajaya.ac.id](1 rahmalia@darmajaya.ac.id)*; [2](2 taufiktsani@gmail.com)[ taufiktsani@gmail.com](2 taufiktsani@gmail.com); [3](3 aldwimandak.1911010070@mail.darmajaya.ac.id)[ ](3 aldwimandak.1911010070@mail.darmajaya.ac.id)[aldwimandak.1911010070@mail.darmajaya.ac.id](3 aldwimandak.1911010070@mail.darmajaya.ac.id),[4](4dafaaje222.2211010107@mail.darmajaya.ac.id)[dafaaje222.2211010107@mail.darmajaya.ac.id](4dafaaje222.2211010107@mail.darmajaya.ac.id)[ ](4dafaaje222.2211010107@mail.darmajaya.ac.id)* corresponding author: Rahmalia Syahputri  \nARTICLE INFO  \nArticle history  \nReceived 22/03/2026 Revised 10/05/2026  \nAccepted 13/06/2026  \nKeywords  \nBahasa Indonesia Machine Learning  \nNaïve Bayes Pornography Classification Text Mining  \nABSTRACT  \nThe rapid growth of internet usage has increased concerns about exposure to pornographic content, particularly among younger users. This study addresses the limited availability of large-scale Indonesianlanguage studies on the classification of pornographic websites and proposes a Naïve Bayes (NB)-based approach that employs comprehensive preprocessing and class balancing to improve classification performance. The main contribution of this study is the use of a large-scale dataset combined with a tailored preprocessing pipeline and SMOTE-based class balancing for improved classification reliability. A dataset comprising 50,329 website entries collected between 2019 and 2026 was processed using standard text preprocessing techniques to enhance the quality of textual features. To address class imbalance between pornographic and non-pornographic categories, the Synthetic Minority Oversampling Technique (SMOTE) was applied during the training phase. Model performance was evaluated using a 5-fold cross-validation strategy and compared across three Naïve Bayes variants: Multinomial Naïve Bayes (MNB), Bernoulli Naïve Bayes (BNB), and Gaussian Naïve Bayes (GNB) . Experimental results showed that the Multinomial Naïve Bayes model achieved the best performance, with an accuracy of approximately 94%, a precision of 0.92, a recall of 0.94, an F1-score of 0.93, and an ROC-AUC of 0.986. These findings demonstrate that the proposed approach is effective in classifying pornographic website content and can support automated web content filtering systems. Future work may explore real-time implementation and the integration of more advanced machine learning techniques to further improve classification performance.  \nThis is an open access article under the CC–BY-SA license.  \n1. Introduction  \nIndonesia has experienced rapid digital growth, leading to increased internet usage and higher engagement in online activities, particularly among younger users[1], [2] . This expansion has significantly transformed how users access and interact with online information. However, the growth of digital access also introduces challenges related to the increasing availability of harmful  \nonline content. In particular, the dynamic and evolving nature of web content makes it difficult to control and regulate effectively, especially in open and large-scale internet environments [1] .  \nExposure to pornographic content can have significant negative effects on adolescents, including impacts on mental health, behaviour, and social development [3], [4], [5], [6] . The accessibility, affordability, and anonymity provided by the internet further facilitate the widespread distribution and consumption of such content [7] . Additionally, anonymous platforms operating on the Tor network enable the dissemination of","cbCais9R0bKBGnhK","https://ap.wps.com/l/cbCais9R0bKBGnhK","pdf",957499,14,"English","# Introduction\n## Automated pornographic content detection using text classification\n## Related work and machine learning approaches\n# Method overview\n## Naïve Bayes variants and evaluation strategy","[{\"question\":\"What problem does the study address?\",\"answer\":\"The study addresses the increased risk of users—especially younger users—being exposed to pornographic content online and the need for effective automated detection methods.\"},{\"question\":\"How is class imbalance handled in the proposed approach?\",\"answer\":\"The Synthetic Minority Oversampling Technique (SMOTE) is applied during training to balance pornographic and non-pornographic classes.\"},{\"question\":\"Which Naïve Bayes variant performs best and what metrics are reported?\",\"answer\":\"Multinomial Naïve Bayes (MNB) achieves the best results, with about 94% accuracy, precision 0.92, recall 0.94, F1-score 0.93, and ROC-AUC 0.986.\"}]","A Machine Learning Approach for Pornographic Website Content Detection - Part | PDF",1789643350,35]