[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119335-id":3,"doc-seo-119335-113":31,"detail-sidebar-cat-0-id-113":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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},119335,687207022233,"Riley","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",54,"Penelitian & Laporan","BAB II Landasan Teori - Penelitian Terdahulu","Bagian ini menyajikan landasan teori dengan fokus pada penelitian terdahulu sebagai pedoman penyusunan latar belakang masalah, pencegahan duplikasi, serta penguatan fondasi penelitian. Uraian memuat rangkuman studi lima tahun terakhir yang membahas penerapan sentiment analysis menggunakan berbagai pendekatan machine learning serta feature selection. Ditekankan bahwa optimasi berbasis swarm intelligence seperti PSO, ACO, dan CSO umumnya menghasilkan performa lebih baik, termasuk penggunaan SMOTE untuk mengatasi ketidakseimbangan data. Kebaruan penelitian diarahkan pada optimasi feature selection dan parameter untuk SVM, Naïve Bayes, dan KNN.","BAB II  \nLANDASAN TEORI  \n2.1 Penelitian Terdahulu  \nPenelitian terdahulu merupakan kumpulan studi atau riset yang dilakukansebelumnya dalam suatu bidang ilmu yang disesuaikan dengan topik penelitian. Penelitian terdahulu digunakan sebagai pedoman dalam mengidentifikasi latarbelakang masalah, mencegah duplikasi, dan membangun fondasi penelitian terbaru. Berikut adalah penelitian terdahulu yang digunakan dalam penelitianyang dapat dilihat pada Tabel 2.1 Penelitian Terdahulu  \nTabel 2. 1 Penelitian Terdahulu  \nNama Jurnal Penulis Metode  \n\n| Improved Support Vector Machine | Proceedings-4th International | Windha Mega, P. D., & | Feature Selection: | PSO unggul\u003Cbr>dibandingkan |\n| --- | --- | --- | --- | --- |\n\n\n| Judul |  |  |  | Hasil |\n| --- | --- | --- | --- | --- |\n| Prediction of Indonesia Presidential Election Results for the 2019-2024 Period Using Twitter Sentiment Analysis [21] | 2019 5th International Conference on New Media Studies Bali, Indonesia | Dinar Ajeng Kristiyanti, Normah, Akhmad Hairul Umam (2019) | Feature Selection:\u003Cbr>PSO, GA\u003Cbr>Machine\u003Cbr>Learning: SVM | PSO-SVMberkinjerjalebih optimal\u003Cbr>(Akurasi: 82. 85% dan 86.20%) |\n| Ant colony optimization for text feature selection in sentiment analysis [23] | Intelligent Data Analysis | Ahmad, S. R.,\u003Cbr>Bakar, A. A.,\u003Cbr>& Yaakub, M.\u003Cbr>R. (2019) | Feature Selection:\u003Cbr>ACO, Generic Algorithm (GA) Machine Learning:\u003Cbr>KNN, Information Gain (IG) | Hasil terbaiknya adalah ACO\u003Cbr>KNN dengan rata-ratafscore 82.7%,\u003Cbr>mengungguli IG-RSARdan IG-GA |\n| Optimization of Sentiment Analysis for Indonesian Presidential Election using Naïve Bayes and Particle Swarm Optimization [24] | Jurnal Online Informatika | Hayatin, N., Marthasari, G.\u003Cbr>I., & Nuraini, L. (2020) | Feature Selection:\u003Cbr>PSO\u003Cbr>Machine Learning:\u003Cbr>Naïve Bayes | Terdapat peningkatkanakurasisebesar 4.12% bila menggunakan\u003Cbr>PSO sebagai featureselection menjadi\u003Cbr>90.74% . |\n\n\n| Judul | Nama Jurnal | Penulis | Metode | Hasil |\n| --- | --- | --- | --- | --- |\n| (SVM) Performance on Go-Jek Service Review Classification Using Particle Swarm Optimization (PSO)\u003Cbr>[25] | Conference on Informatics, Multimedia, Cyber and Information System | Haryoko.(2022) | PSO Machine\u003Cbr>Learning: SVM | GA dalam meningkatkan\u003Cbr>kinerja model\u003Cbr>SVM dengan\u003Cbr>akurasi yang didapat sekitar 87% |\n| Hyper-parameter tuning for support vector machine using an improved catswarm optimization algorithm [26] | Journal of theNigerian Societyof PhysicalSciences | Silifat Adaramaja Abdulraheem,\u003Cbr>Salisu Aliyu,\u003Cbr>Fatimah Binta Abdullahi (2023) | Feature Selection:\u003Cbr>CSO Machine\u003Cbr>Learning: SVM | CSO-SVM menghasilkan\u003Cbr>akurasi yanglebih besar yakni 85,71% |\n| A new machine learning-based method for android malware detection on imbalanced dataset [27] | Multimedia Tools and Applications | Diyana Tehrany Dehkordy, Abbas Rasoolzadegan (2021) | Oversampling: SMOTE\u003Cbr>Machine Learning:\u003Cbr>SVM, KNN, dan ID3 | SMOTE + KNNmenghasilkan\u003Cbr>akurasi yang signifikansebesar 98,69% |\n| A decision support system for heart disease prediction based upon machine learning [28] | Journal of Reliable Intelligent Environments | Pooja Rani, Rajneesh Kumar, Nada.\u003Cbr>M.O.Sid Ahmed, Anurag Jain | Oversampling: SMOTE\u003Cbr>Machine Learning:\u003Cbr>Naïve Bayes, GA, SVM, Random Foreset, Adaboost | SMOTE + Naïve Bayes\u003Cbr>menghasilkantingkatakurasi yang signifikansebesar 85,07% |\n| Cryptocurrency Price Prediction Using Forecasting And Sentiment Analysis [29] | The Science and Information Organization | Shaimaa Alghamdi, Sara Alqethami, Tahani Alsubait, Hosam Alhakami | Machine Learning:\u003Cbr>Naïve Bayes, SVM | Algoritma SVMmenunjukan peformasi yang lebih baik dibandingkan\u003Cbr>Naïve Bayes denganakurasisebesar\u003Cbr>93,59% untuk\u003Cbr>dataset BTC\u003Cbr>dan 95,59% untuk ETH |\n| Twitter Text Mining For Sentiment Analysis On Government’s Response To Forest Fires With Vader Lexicon Polarity | 6th International Conference on Mathematics, Science, and Education | T Mustaqim*,\u003Cbr>K Umam and\u003Cbr>M A Mu","cbCaigBrtvEkrkeg","https://ap.wps.com/l/cbCaigBrtvEkrkeg","pdf",1378764,4,1,22,"Indonesian","id",113,"# 2.1 Penelitian Terdahulu\n## Tujuan dan peran penelitian terdahulu\n## Tabel rangkuman studi (judul, penulis, metode, hasil)\n## Temuan umum dan arah kebaruan penelitian","[{\"question\":\"Apa fungsi penelitian terdahulu dalam penelitian ini?\",\"answer\":\"Penelitian terdahulu digunakan sebagai pedoman untuk mengidentifikasi latar belakang masalah, mencegah duplikasi, serta membangun fondasi penelitian terbaru.\"},{\"question\":\"Metode apa yang paling sering digunakan dalam sentiment analysis pada penelitian terdahulu?\",\"answer\":\"Sentiment analysis menggunakan kombinasi machine learning seperti SVM, Naïve Bayes, dan KNN, dengan tambahan feature selection untuk meningkatkan performa model.\"},{\"question\":\"Bagaimana peran feature selection dan optimasi parameter berbasis swarm intelligence?\",\"answer\":\"Penerapan feature selection dan optimasi parameter berbasis swarm intelligence seperti PSO, ACO, dan CSO menunjukkan hasil model yang lebih baik dibanding pemodelan dengan algoritma machine learning tunggal.\"},{\"question\":\"Mengapa digunakan oversampling SMOTE pada beberapa penelitian terdahulu?\",\"answer\":\"SMOTE digunakan untuk mengatasi permasalahan data tidak seimbang sehingga model menghasilkan pemodelan yang lebih baik.\"}]","BAB II Landasan Teori - Penelitian Terdahulu | PDF",1785723764,34,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":91,"head_meta":93,"extra_data":95,"updated_unix":29},"chapter-2-theoretical-foundation-previous-research","",{"@graph":37,"@context":90},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/id/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/id/document/penelitian-laporan/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/id/document/chapter-2-theoretical-foundation-previous-research/119335/",{"url":53,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-18","2026-08-03",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},"Apa fungsi penelitian terdahulu dalam penelitian ini?","Question",{"text":76,"@type":77},"Penelitian terdahulu digunakan sebagai pedoman untuk mengidentifikasi latar belakang masalah, mencegah duplikasi, serta membangun fondasi penelitian terbaru.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Metode apa yang paling sering digunakan dalam sentiment analysis pada penelitian terdahulu?",{"text":81,"@type":77},"Sentiment analysis menggunakan kombinasi machine learning seperti SVM, Naïve Bayes, dan KNN, dengan tambahan feature selection untuk meningkatkan performa model.",{"name":83,"@type":74,"acceptedAnswer":84},"Bagaimana peran feature selection dan optimasi parameter berbasis swarm intelligence?",{"text":85,"@type":77},"Penerapan feature selection dan optimasi parameter berbasis swarm intelligence seperti PSO, ACO, dan CSO menunjukkan hasil model yang lebih baik dibanding pemodelan dengan algoritma machine learning tunggal.",{"name":87,"@type":74,"acceptedAnswer":88},"Mengapa digunakan oversampling SMOTE pada beberapa penelitian terdahulu?",{"text":89,"@type":77},"SMOTE digunakan untuk mengatasi permasalahan data tidak seimbang sehingga model menghasilkan pemodelan yang lebih baik.","https://schema.org",{"og:url":53,"og:type":92,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":94,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":97},[98,103,107,111,115,119,121,125,129,133,137],{"id":99,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},55,"Agama & Spiritualitas",60,"religion-spirituality",{"id":104,"doc_module":4,"doc_module_name":47,"category_name":105,"show_sort_weight":101,"slug":106},48,"Cerita & Novel","story-novel",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":101,"slug":110},56,"Gaya Hidup","lifestyle",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":101,"slug":114},51,"Komik","comic",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":101,"slug":118},53,"Layanan Kesehatan","healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":101,"slug":120},"research-report",{"id":122,"doc_module":4,"doc_module_name":47,"category_name":123,"show_sort_weight":101,"slug":124},49,"Sastra","literature",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":127,"show_sort_weight":101,"slug":128},52,"Teknologi","technology",{"id":130,"doc_module":4,"doc_module_name":47,"category_name":131,"show_sort_weight":101,"slug":132},50,"Ujian","exam",{"id":134,"doc_module":4,"doc_module_name":47,"category_name":135,"show_sort_weight":101,"slug":136},57,"Umum","general",{"id":138,"doc_module":4,"doc_module_name":47,"category_name":139,"show_sort_weight":4,"slug":140},181,"Formulir","formulir"]