[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122564-id":3,"doc-seo-122564-113":31,"detail-sidebar-cat-0-id-113":85},{"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},122564,962084925290,"Ophelia","https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",54,"Penelitian & Laporan","Fitur Word Embedding untuk Meningkatkan Kinerja Machine Learning pada Analisis Sentimen Game Honor of Kings - Evaluasi Word2Vec, GloVe, dan FastText","Perkembangan media sosial mendorong meningkatnya kebutuhan analisis sentimen untuk memahami persepsi dan opini publik. Penelitian ini mengevaluasi kinerja algoritma Naïve Bayes, K-Nearest Neighbor (KNN), dan Random Forest dalam mengklasifikasikan sentimen ulasan pengguna Game Honor of Kings. Data dikumpulkan dari Google Play Store (900 ulasan) dengan tahapan prapemrosesan cleaning, case folding, tokenization, stopword removal, stemming, serta pelabelan sentimen positif dan negatif. Tiga word embedding (Word2Vec, GloVe, FastText) diuji pada tiap algoritma, menunjukkan fitur embedding meningkatkan akurasi. KNN dengan FastText mencapai 87,55%, sedangkan kombinasi lain menghasilkan performa lebih rendah. FastText unggul karena representasi sub-kata untuk kata langka dan data skala besar.","Sistemasi: Jurnal Sistem Informasi ISSN:2302-8149  \nVolume 15, Nomor 2, 2026: 522-533 e-ISSN:2540-9719  \nFitur Word Embedding untuk meningkatkan Kinerja Machine Learning pada Analisis Sentimen Game Honor ofKings  \nWord Embedding Features to Improve Machine Learning Performance in Sentiment Analysis of the Honor ofKings Game  \n1Abdul Harris*, 2Agus Nugroho, 3Yudi Novianto, 4Jasmir Jasmir, 5Dhea Fatma  \n1,2,3,5Program Studi Teknik Informatika, Fakultas Ilmu Komputer, Universitas Dinamika Bangsa 4Program Studi Sistem Komputer, Fakultas Ilmu Komputer Universitas Dinamika Bangsa  \n1,2,3,4,5Jl. Jendral Sudirman, Tehok, Jambi Selatan, Kota Jambi, Indonesia  \n*e-mail: [abdulharris@stikom-db.ac.id](abdulharris@stikom-db.ac.id)  \n(received: 13 November 2025, revised: 13 December 2025, accepted: 10 January 2026)  \nAbstrak  \nPerkembangan media sosial mendorong semakin banyak penelitian mengenai analisis sentimen untuk memahami persepsi dan opini masyarakat. Penelitian ini bertujuan mengevaluasi kinerja algoritma machine learning Naïve Bayes, K-Nearest Neighbor (KNN), dan Random Forest dalam mengklasifikasikan sentimen ulasan pengguna terhadap Game Honor of Kings. Data penelitian diperoleh dari Google Play Store dengan total 900 ulasan, kemudian melalui tahapan prapemrosesan meliputi cleaning, case folding, tokenization, stopword removal, stemming, serta pelabelan sentimen positif dan negatif. Selanjutnya, tiga teknik word embedding digunakan, yaitu Word2Vec, GloVe, dan FastText, yang masing-masing diuji terhadap tiga algoritma machine learning. Hasil eksperimen menunjukkan bahwa penggunaan fitur word embedding secara signifikan meningkatkan akurasiklasifikasi dibandingkan tanpa fitur. KNN dengan FastText menghasilkan performa terbaik denganakurasi 87,55%, sedangkan Random Forest dengan FastText memberikan akurasi terendah. FastText terbukti unggul karena kemampuannya merepresentasikan kata melalui sub-kata, sehingga lebih efektif dalam menangani kosakata langka maupun data berskala besar. Penelitian ini menegaskan bahwa kombinasi metode klasifikasi dengan fitur word embedding berperan penting dalam meningkatkan performa analisis sentimen. Ke depan, penelitian lanjutan dapat diarahkan pada optimasi hiperparameter, penerapan teknik prapemrosesan lanjutan, serta perluasan dataset agar model lebih tangguh dan mampu melakukan generalisasi yang lebih baik.  \nKata kunci: analisis sentiment, fasttext, glove, machine learning, word2vec  \nAbstract  \nThe rapid growth of social media has encouraged an increasing number of studies on sentiment analysis to better understand public perceptions and opinions. This study aims to evaluate the performance of three machine learning algorithms—Naïve Bayes, K-Nearest Neighbor (KNN), and Random Forest—in classifying user review sentiments toward the game Honor of Kings. The dataset was collected from the Google Play Store, consisting of 900 reviews. The data then underwent preprocessing steps including cleaning, case folding, tokenization, stopword removal, stemming, and sentiment labeling into positive and negative classes. Furthermore, three word embedding techniques were applied, namely Word2Vec, GloVe, and FastText, each of which was tested across the three machine learning algorithms. The experimental results indicate that the use of word embedding features significantly improves classification accuracy compared to models without embedding features. KNN combined with FastText achieved the best performance, reaching an accuracy of 87.55%, while Random Forest combined with FastText produced the lowest accuracy. FastText demonstrated superior performance due to its ability to represent words through subword information, making it more effective in handling rare vocabulary and large-scale datasets. This study confirms that combining machine learning classification methods with word embedding features plays a crucial role in improving sentiment analysis performance. Future research may focus on hyperparameter op","cbCainGc7NG79nrL","https://ap.wps.com/l/cbCainGc7NG79nrL","pdf",371770,7,1,12,"Indonesian","id",113,"# Pendahuluan\n## Analisis sentimen dan NLP dalam media sosial\n## Klasifikasi teks dengan machine learning\n## Keterbatasan BoW dan TF-IDF serta kebutuhan word embedding\n## Karakteristik Word2Vec, GloVe, dan FastText","[{\"question\":\"Word embedding mana yang menghasilkan performa terbaik dan mengapa?\",\"answer\":\"KNN dengan FastText menghasilkan performa terbaik dengan akurasi 87,55%. FastText unggul karena merepresentasikan kata melalui sub-kata sehingga efektif menghadapi kosakata langka dan data berskala besar.\"}]","Fitur Word Embedding untuk Meningkatkan Kinerja Machine Learning pada Analisis Sentimen Game Honor of Kings - Evaluasi Word2Vec, GloVe, dan FastText | PDF",1785811340,18,{"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":80,"head_meta":82,"extra_data":84,"updated_unix":29},"word-embedding-features-to-improve-machine-learning-performance-in-sentiment-analysis-of-the-honor-of-kings-game-evaluation-of-word2vec-glove-and-fasttext","",{"@graph":37,"@context":79},[38,55,70],{"@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":54},"https://docshare.wps.com/id/document/word-embedding-features-to-improve-machine-learning-performance-in-sentiment-analysis-of-the-honor-of-kings-game-evaluation-of-word2vec-glove-and-fasttext/122564/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-17","2026-08-04",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73],{"name":74,"@type":75,"acceptedAnswer":76},"Word embedding mana yang menghasilkan performa terbaik dan mengapa?","Question",{"text":77,"@type":78},"KNN dengan FastText menghasilkan performa terbaik dengan akurasi 87,55%. FastText unggul karena merepresentasikan kata melalui sub-kata sehingga efektif menghadapi kosakata langka dan data berskala besar.","Answer","https://schema.org",{"og:url":53,"og:type":81,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":83,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":86},[87,92,96,100,104,108,110,114,118,122,126],{"id":88,"doc_module":4,"doc_module_name":47,"category_name":89,"show_sort_weight":90,"slug":91},55,"Agama & Spiritualitas",60,"religion-spirituality",{"id":93,"doc_module":4,"doc_module_name":47,"category_name":94,"show_sort_weight":90,"slug":95},48,"Cerita & Novel","story-novel",{"id":97,"doc_module":4,"doc_module_name":47,"category_name":98,"show_sort_weight":90,"slug":99},56,"Gaya Hidup","lifestyle",{"id":101,"doc_module":4,"doc_module_name":47,"category_name":102,"show_sort_weight":90,"slug":103},51,"Komik","comic",{"id":105,"doc_module":4,"doc_module_name":47,"category_name":106,"show_sort_weight":90,"slug":107},53,"Layanan Kesehatan","healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":90,"slug":109},"research-report",{"id":111,"doc_module":4,"doc_module_name":47,"category_name":112,"show_sort_weight":90,"slug":113},49,"Sastra","literature",{"id":115,"doc_module":4,"doc_module_name":47,"category_name":116,"show_sort_weight":90,"slug":117},52,"Teknologi","technology",{"id":119,"doc_module":4,"doc_module_name":47,"category_name":120,"show_sort_weight":90,"slug":121},50,"Ujian","exam",{"id":123,"doc_module":4,"doc_module_name":47,"category_name":124,"show_sort_weight":90,"slug":125},57,"Umum","general",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":128,"show_sort_weight":4,"slug":129},181,"Formulir","formulir"]