[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-154687-105":59,"doc-detail-154687-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","comparison-of-naive-bayes-k-nearest-neighbor-and-support-vector-machine-classification-methods-in-semi-supervised-learning-for-sentiment-analysis-of-kereta-cepat-jakarta-bandung-kcjb","Comparison of Naive Bayes, K-Nearest Neighbor, and Support Vector Machine Classification Methods in SemiSupervised Learning for Sentiment Analysis of Kereta Cepat Jakarta Bandung (KCJB)","","Transportation technology advanced rapidly in the 21st century, highlighted by Indonesia’s Kereta Cepat Jakarta–Bandung (KCJB) high-speed rail project developed with China. Public reactions on Twitter and social media motivate sentiment mining from scraped tweets. The research compares semi-supervised Naïve Bayes, K-Nearest Neighbor (K-NN), and Support Vector Machine (SVM) for classifying tweets as positive, negative, or neutral. Results show semi-supervised SVM achieves the highest average accuracy (86%), followed by semi-supervised Naïve Bayes (81%) and semi-supervised K-NN (58%).",{"@graph":69,"@context":122},[70,84,105],{"@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/comparison-of-naive-bayes-k-nearest-neighbor-and-support-vector-machine-classification-methods-in-semi-supervised-learning-for-sentiment-analysis-of-kereta-cepat-jakarta-bandung-kcjb/154687/",{"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/comparison-of-naive-bayes-k-nearest-neighbor-and-support-vector-machine-classification-methods-in-semi-supervised-learning-for-sentiment-analysis-of-kereta-cepat-jakarta-bandung-kcjb/154687.png","ImageObject",300,407,{"name":92,"@type":93},"Alex Sinclair","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-21","2026-08-28",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the goal of the research in the document?","Question",{"text":112,"@type":113},"To compare Naïve Bayes, K-Nearest Neighbor (K-NN), and Support Vector Machine (SVM) classification methods for sentiment analysis of tweets about the KCJB high-speed train project using semi-supervised learning.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Which model achieves the best performance and what is its accuracy?",{"text":117,"@type":113},"The semi-supervised SVM model performs best, with an average accuracy of 86%.",{"name":119,"@type":110,"acceptedAnswer":120},"How do the sentiment results generally compare across the three classes?",{"text":121,"@type":113},"The overall prediction indicates more tweets with negative sentiment than positive and neutral sentiment.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},154687,1787896992,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":39,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":41},1099523882182,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","M Farhan et al  \nComparison of Naive Bayes, K-Nearest Neighbor, and Support Vector Machine Classification Methods in SemiSupervised Learning for Sentiment Analysis ofKereta Cepat Jakarta Bandung (KCJB)  \nM Farhan 1, R D L R Manik1, H R Jannah 1, L H Suadaa 1,*  \n1 Politeknik Statistika STIS, Jl. Otto Iskandardinata No. 64C, East Jakarta, DKI Jakarta  \n*Corresponding author’s e-mail: [lya@stis.ac.id](lya@stis.ac.id)  \nAbstract. Transportation technology has developed very rapidly in the 21st century; one of themis high-speed trains. Currently, the Indonesian government is implementing the construction of the Kereta Cepat Jakarta-Bandung (KCJB) project in collaboration with China. The construction of this fast train project has attracted various comments and opinions from the public on Twitter and social media. This research aims to compare the classification methods of Naïve Bayes, KNearest Neighbor (K-NN), and Support Vector Machine (SVM) in classifying sentiment in tweets about high-speed trains obtained by scraping Twitter. The comparison process was carried out using semi-supervised learning, and the results showed that the semi-supervised SVM model had the best performance with an average accuracy of 86%, followed by the semi-supervised Naïve Bayes model and semi-supervised K-NN with an average accuracy of 81% and 58% respectively. Overall, the prediction results from the three models conclude that there are more tweets with negative sentiment than tweets with positive and neutral sentiment.  \n1. Introduction  \nTechnology is developing all the time, including transportation technology. Public transportation as a passenger transport service is available for the general public. The higher level of mobility raises the need for public transportation that can run more efficiently [1]. The Indonesian government is trying to improve transportation services and support development in the Jakarta-Bandung area by building a fast train. The project is a collaboration between Indonesia and China. A consortium called PT. Kereta Api Indonesia China (KCIC) was formed as the executor of the Kereta Cepat Jakarta-Bandung development and construction project [2] .  \nThe construction of the Jakarta-Bandung high-speed train sparked a lot of attention and varied opinions from various levels of society. Former Minister of BUMN, Rini Mariani Soemarno, said that the benefits of building the Jakarta-Bandung high-speed train include improving the economy and the tourism sector and opening up new job opportunities [3]. However, during its construction, there needed to be more attention to smooth access in and out of toll roads, allowing the accumulation of materials that disrupted drainage functions, building LRT pillars without permits, and occupational safety and  \n109  \nM Farhan et al  \nhealth (K3) issues [4]. Few also focus on economic figures regarding how much the country profits and losses [5] .  \nNowadays, people can express their opinions through various media. One is the social media Twitter, which is massively used because it is considered adequate for expressing their opinions and thoughts, including voicing their perspectives on the construction of the Jakarta-Bandung Fast Train. Indonesian people tweeted many comments regarding this project. Some comments are in acceptance, others are against, and some are neither. Things like this are usually called sentiments [6] .  \nSentiment analysis can be performed to determine public opinion on an event [7] . Sentiment analysis, also known as opinion mining, is the study of how a person's opinions, sentiments or feelings, behavior, and emotions about an entity are expressed through writing. The information obtained can be in the form of positive, negative, or neutral sentiments. Through a data mining approach, a classification model can be built to label a tweet, whether it is positive, negative, or neutral, automatically so that conclusionsand information gathering can be made quickly [8] .  \nVa","cbCaiciGfvNoRUFf","https://ap.wps.com/l/cbCaiciGfvNoRUFf","pdf",894576,12,"English","# Introduction\n## Transportation technology and the KCJB project\n## Sentiment analysis and opinion mining\n# Literature Review\n## Theoretical basis\n## Preprocessing","[{\"question\":\"What is the goal of the research in the document?\",\"answer\":\"To compare Naïve Bayes, K-Nearest Neighbor (K-NN), and Support Vector Machine (SVM) classification methods for sentiment analysis of tweets about the KCJB high-speed train project using semi-supervised learning.\"},{\"question\":\"Which model achieves the best performance and what is its accuracy?\",\"answer\":\"The semi-supervised SVM model performs best, with an average accuracy of 86%.\"},{\"question\":\"How do the sentiment results generally compare across the three classes?\",\"answer\":\"The overall prediction indicates more tweets with negative sentiment than positive and neutral sentiment.\"}]","Comparison of Naive Bayes, K-Nearest Neighbor, and Support Vector Machine Classification Methods in SemiSupervised Learning for Sentiment Analysis of Kereta Cepat Jakarta Bandung (KCJB) | PDF"]