[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122568-en":3,"doc-seo-122568-105":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},122568,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Comparative Analysis of IndoBERT and Classic Machine Learning Models for Sentiment Classification of Education Policy on Social Media X - Research Findings","Education policy leadership transitions in Indonesia generate dense public debate on social media X, where opinions are often expressed through implicit sentiment such as sarcasm and context-specific slang. This study conducts a comparative evaluation of IndoBERT versus classic machine learning classifiers (SVM, Naïve Bayes, Logistic Regression, KNN, and Random Forest) for tweet sentiment classification. Indonesian tweets are crawled, pre-processed, and labeled via a Lexicon–LLM hybrid approach. Performance is measured using accuracy, precision, recall, and F1-score, and results show IndoBERT reaching 97% accuracy, outperforming Random Forest and SVM, while demonstrating stronger context understanding and robustness for nuanced public sentiment.","Comparative Analysis of IndoBERT and Classic Machine Learning Models for Sentiment Classification of Education Policy on  \nSocial Media X  \nGabriella Fani Suciarti Medantoro1 * , Muljono2 *  \n* Department Informatic Engineering, Dian Nuswantoro University, Semarang, Indonesia  \n[111202214441@mhs.dinus.ac.id](111202214441@mhs.dinus.ac.id1)[1](111202214441@mhs.dinus.ac.id1) , [muljono@dsn.dinus.ac.id](muljono@dsn.dinus.ac.id2)[2](muljono@dsn.dinus.ac.id2)  \n\n| Article history:\u003Cbr>Received 2025-11-08 Revised 2025-12-29 Accepted 2026-01-07 | Leadership changes provide an opportunity for new education policies, generating complex public opinions on social media X that often contain implicit sentiments like satire, making automated analysis challenging. This study aims to address this challenge by conducting a comparative analysis to evaluate the effectiveness of the IndoBERT model in capturing nuanced, implicit sentiments compared to traditional machine learning classifiers (SVM, Naïve Bayes, Logistic Regression, KNN, and Random Forest) . This research utilized a dataset of Indonesian-language tweets, collected via crawling. Data was pre-processed (cleaning, case folding, etc.) and labeled (positive/negative) using a hybrid Lexicon-LLM approach. The TF-IDF technique was used for feature extraction for the machine learning models, while IndoBERT used its internal tokenization. Models were evaluated using accuracy, precision, recall, and F1-score. The results showed that the IndoBERT model performed best with an accuracy score of 97%, significantly outperforming the other best machine learning models, namely Random Forest 95% and SVM 95%. This study concludes that the IndoBERT model is a superior and more robust solution for analyzing nuanced public sentiment on educational policies, demonstrating a greater ability to understand complex context and implicit language compared to traditional TF-IDF-based methods.\u003Cbr>\u003Cbr>This is an open access article under the CC–BY-SA license. |\n| --- | --- |\n| Keyword:\u003Cbr>Sentyment Analysist, Social Media X, Machine Learning, Implicit, Education. |  |\n\nArticle Info ABSTRACT  \nI. INTRODUCTION  \nEntering 2024, the national leadership transition in Indonesia has sparked a massive public discourse on the direction of state policy, with the education sector emerging as one of the primary focuses [1] . The period of national leadership transition in 2024, particularly between December 2023 and December 2024, which covers the campaign period to the early phase of the new administration, is not merely a change of authority figures, but a crucial moment for public evaluation of the sustainability of strategic programs such as the Merdeka Curriculum and sensitive issues related to the accessibility of education costs (UKT) and teacher welfare. The social media platform X (formerly Twitter) serves as the primary arena for this discourse, where millions of opinions are expressed in realtime [2] . With Indonesia ranking as the fourth-largest user base of X globally, reaching 24.45 million users by April 2024, the  \nplatform has become an exceptionally rich data source for capturing public aspirations and views on the dynamics of national education.  \nHowever, automatically analyzing these millions of raw opinions presents significant technical challenges. Public opinion on the X platform is often expressed not just literally, but also through implicit language, sarcasm, and context-specific slang [3]. Implicit sentiment is defined asthe expression of opinion that does not directly contain polarity adjectives (such as ‘bad’ or ‘disappointed’), but still carries emotional weight through contextual understanding or the use of metaphors. This phenomenon, often referred to as Post-level Implicit Sentiment Analysis (PISA), is particularly prevalent in social media discussions where users convey criticism through irony or satire [4]. Conventional sentiment classification models that rely solely on word-matching (such as","cbCaiqRDbo6AMJM6","https://ap.wps.com/l/cbCaiqRDbo6AMJM6","pdf",730124,1,10,"English","en",105,"# Abstract\n# Introduction\n## Context: leadership transition and public discourse on X\n## Challenge: implicit sentiment, sarcasm, and slang\n## Study objective and approach\n# Keywords","[{\"question\":\"What is the main challenge addressed in the sentiment analysis of education policy discussions on X?\",\"answer\":\"The discussions often contain implicit sentiment, sarcasm, and context-specific slang, which makes automated models that rely on simple word matching prone to misclassification.\"},{\"question\":\"Which models are compared in this study?\",\"answer\":\"The study compares IndoBERT against classic machine learning classifiers including SVM, Naïve Bayes, Logistic Regression, KNN, and Random Forest.\"},{\"question\":\"How is model performance evaluated and what is the key result?\",\"answer\":\"Models are evaluated using accuracy, precision, recall, and F1-score. IndoBERT achieves the best performance with 97% accuracy, outperforming the best classic baselines such as Random Forest (95%) and SVM (95%).\"}]","Comparative Analysis of IndoBERT and Classic Machine Learning Models for Sentiment Classification of Education Policy on Social Media X - Research Findings | PDF",1785811358,25,{"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},"comparative-analysis-of-indobert-and-classic-machine-learning-models-for-sentiment-classification-of-education-policy-on-social-media-x-research-findings","",{"@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/comparative-analysis-of-indobert-and-classic-machine-learning-models-for-sentiment-classification-of-education-policy-on-social-media-x-research-findings/122568/",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","2026-08-04",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 is the main challenge addressed in the sentiment analysis of education policy discussions on X?","Question",{"text":75,"@type":76},"The discussions often contain implicit sentiment, sarcasm, and context-specific slang, which makes automated models that rely on simple word matching prone to misclassification.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which models are compared in this study?",{"text":80,"@type":76},"The study compares IndoBERT against classic machine learning classifiers including SVM, Naïve Bayes, Logistic Regression, KNN, and Random Forest.",{"name":82,"@type":73,"acceptedAnswer":83},"How is model performance evaluated and what is the key result?",{"text":84,"@type":76},"Models are evaluated using accuracy, precision, recall, and F1-score. IndoBERT achieves the best performance with 97% accuracy, outperforming the best classic baselines such as Random Forest (95%) and SVM (95%).","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},[93,97,101,105,110,115,120,123,128,131,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]