Claim Missing Document
Check
Articles

Found 35 Documents
Search

ANALISIS PERBANDINGAN ALGORITMA NAIVE BAYES DAN KNN UNTUK ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI VIDIO DI GOOGLE PLAY STORE Pratmanto, Dany; Widayanto, Aprih; Kristania, Yustina Meisella; Ubaidillah , Ubaidillah; Wijianto, Ragil
CONTEN : Computer and Network Technology Vol. 4 No. 2 (2024): Desember 2024
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/conten.v4i2.6891

Abstract

Penelitian ini mengkaji efektivitas algoritma Naive Bayes (NB) dan K-Nearest Neighbors (KNN) dalam analisis sentimen ulasan pengguna aplikasi Vidio di Google Play Store. Evaluasi kinerja kedua model dilakukan menggunakan berbagai metrik, termasuk akurasi, precision, recall, dan Area Under Curve (AUC). Hasil penelitian menunjukkan bahwa KNN mengungguli Naive Bayes dalam beberapa aspek penting. KNN mencapai akurasi 74.92% dibandingkan dengan Naive Bayes sebesar 71.32%. Dalam hal precision, KNN juga menunjukkan performa yang lebih baik dengan nilai 76.52%, sementara Naive Bayes mencapai 71.61%. Meskipun demikian, kedua model menunjukkan kinerja yang sebanding dalam hal recall, dengan KNN mencapai 72.54% dan Naive Bayes 71.46%. Yang menarik, kedua model memiliki nilai AUC yang sangat tinggi dan hampir setara, yaitu 90.10% untuk KNN dan 90.00% untuk Naive Bayes, menunjukkan kemampuan yang sangat baik dalam membedakan sentimen positif dan negatif. Berdasarkan hasil evaluasi secara keseluruhan, algoritma KNN lebih direkomendasikan untuk implementasi analisis sentimen pada ulasan pengguna aplikasi Vidio.
Sistem Informasi Pemesanan Menu Kafe Menggunakan QR-Code Andrian Eko Widodo; Fanny Fatma Wati; Aprih Widayanto
J-INTECH ( Journal of Information and Technology) Vol 11 No 1 (2023): J-Intech : Journal of Information and Technology
Publisher : LPPM STIKI MALANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32664/j-intech.v11i1.865

Abstract

During this pandemic, to reduce the spread of COVID-19, it is necessary to implement health protocols in community activities, including in the culinary business. By utilizing the QR-Code the cafe owner can realize the use of a digital menu that can be accessed from a cafe visitor's smart device. The use of digital menu lists is intended to prevent Covid-19 transmission through manual lists or menu books, which are usually used interchangeably by many visitors. By scanning the QR-Code placed on the cafe table, visitors can select a menu and place an order by minimizing contact with manual menu lists and cafe employees. Through this application, cafe owners can also manage sales at their cafes, including sales statistics, receipt printing, menu updates, etc.
Strategi Digital Marketing dalam Memperluas Jangkauan Pasar Produk Sale Pisang UMKM Desa Karangkemojing Aprih Widayanto; Fadlilah, Nuzul Imam; Saifudin, Saifudin; Hellyana, Corie Mei
Journal of Entrepreneurship and Community Innovations Vol 4 No 2 (2026): FEBRUARI 2026
Publisher : Lembaga Penelitian Universitas YARSI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33476/jeci.v4i2.442

Abstract

UMKM Sale Pisang di Desa Karangkemojing memiliki potensi ekonomi besar namun terkendala pemasaran konvensional, rendahnya literasi digital, dan ketergantungan pada tengkulak yang membatasi jangkauan pasar. Pengabdian masyarakat ini bertujuan meningkatkan pengetahuan dan keterampilan digital pelaku UMKM melalui penguatan strategi digital marketing. Metode pelaksanaan yang digunakan meliputi penyampaian materi secara klasikal, tutorial penggunaan media promosi, serta simulasi pembuatan konten kreatif menggunakan aplikasi  Instagram, dan Facebook Pro. Temuan penting menunjukkan adanya peningkatan kesadaran mitra serta kemampuan teknis dalam memproduksi aset visual dan narasi promosi secara mandiri. Hasil kegiatan membuktikan bahwa adopsi teknologi mampu memperluas jangkauan pasar mitra hingga ke tingkat nasional. Kesimpulannya, pend  ampingan digital terpadu efektif mentransformasi strategi pemasaran UMKM dari tradisional ke digital, yang berdampak pada peningkatan kemandirian ekonomi dan optimalisasi potensi ekonomi lokal Desa Karangkemojing secara berkelanjutan
Evaluasi Metode Naive Bayes dan K-Nearest Neighbors untuk Analisis Sentimen pada Review Aplikasi Duolingo Joko Dwi Mulyanto; Dany Pratmanto; Aprih Widayanto; Pijar Sukma Prayogo; Andi Yoko Satrio
Evolusi : Jurnal Sains dan Manajemen Vol. 13 No. 2 (2025): Periode September 2025
Publisher : LPPM Universitas Bina Sarana Informatika Kampus Kabupaten Banyumas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/evolusi.v13i2.9937

Abstract

Sentiment analysis is a valuable method for understanding user opinions on digital applications. This study evaluates the performance of the Naive Bayes and K-Nearest Neighbors (KNN) algorithms in classifying sentiments from user reviews of the Duolingo application obtained from the Google Play Store. The dataset consists of 2,000 reviews, comprising 1,000 negative (1-star) and 1,000 positive (5-star) reviews. Preprocessing was conducted in RapidMiner through several stages, including case transformation, tokenization, stopword removal, and stemming, with features represented using TF-IDF. The experimental results show that Naive Bayes achieved an accuracy of 79.96%, recall of 87.76%, precision of 77.21%, and an AUC of 96.40%. Meanwhile, KNN achieved an accuracy of 78.34%, recall of 75.32%, precision of 81.06%, and an AUC of 92.20%. These findings suggest that Naive Bayes outperforms KNN overall, particularly in sensitivity and class separation, while KNN produces more precise positive predictions. Therefore, the choice of algorithm should depend on analysis objectives, whether emphasizing broader sentiment detection or higher precision in positive sentiment classification.
Implementation of Zero-Shot DeBERTa and IndoBERT for Aspect-Based Sentiment Analysis on Reviews of Five LLM Applications Fabriyan Fandi Dwi Imaniawan; Ragil Wijianto; Vadlya Maarif; Joko Dwi Mulyanto; Mustofa Mustofa; Aprih Widayanto
Reputasi: Jurnal Rekayasa Perangkat Lunak Vol. 7 No. 1 (2026): Mei 2026
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/reputasi.v7i1.12790

Abstract

Large Language Model (LLM) applications such as ChatGPT, Gemini, Copilot, Claude, and Perplexity have been massively adopted in Indonesia, yet user experience evaluation remains largely limited to global sentiment analysis. This study implements Aspect-Based Sentiment Analysis (ABSA) using a dual-Transformer approach: DeBERTa zero-shot for aspect extraction and IndoBERT for sentiment classification on 5,000 Indonesian-language reviews from the Google Play Store across four aspect categories. Manual validation by two annotators on 300 samples yielded Cohen’s Kappa of  (aspect) and  (sentiment), both Moderate. Evaluation against the gold standard showed aspect accuracy of 37.5% (weighted F1 = 0.42) and sentiment accuracy of 64.7% (weighted F1 = 0.61). Sensitivity analysis across five hypothesis templates revealed inter-template Kappa of 0.19–0.63, confirming template selection impact on predictions. Comparative analysis reveals Copilot achieves the highest satisfaction (mean score 4.67), while Claude records the most complaints (36.9% negative). This study contributes a validated comparative ABSA framework for Indonesian-language LLM applications