ANALISIS SENTIMEN APLIKASI JASA KURIR DI PLAY STORE MENGGUNAKAN ALGORITMA NAIVE BAYES

Adhitia Erfina; Muhamad Fani Al-shufi

doi:10.47080/simika.v5i2.1789

Adhitia Erfina Universitas Nusa Putra
Muhamad Fani Al-shufi Universitas Nusa Putra

DOI: https://doi.org/10.47080/simika.v5i2.1789

Keywords: Naive Bayes, playstore, sentiment analysis

Abstract

Along with the passage of sales through the marketplace. The courier service industry has also experienced an increase. There are many choices of courier services to choose from, each courier service has different qualities depending on how the service provided by the courier service to customers. To find out the quality of courier services, this research was carried out, this research was conducted on courier service applications on Playstore, usually the best application predicate is for applications with a high number of downloads and ratings, while comments from users must also be considered to get results which is relevant. In this study, the Naïve Bayes algorithm is used because it has a high level of accuracy to determine the best courier service application. Based on the research that has been done, the highest accuracy value is obtained by the JNT application of 100% but has a positive sentiment of 50 reviews. The two JNE applications with an accuracy value of 98% with a positive sentiment of 46 reviews, the three ninjaxpres applications with an accuracy value of 97.87% with a positive sentiment of 49 reviews, the fourth by the Sicepat application with an accuracy value of 97.85% with a positive sentiment of 47 reviews and finally by the Idexpress application with an accuracy value of 94% with a positive sentiment of 49 reviews.

References

Adiwijaya, I. (2006). Text Mining dan Knowledge Discovery. Kolokium Bersama Komunitas Datamining Indonesia & Soft-Computing Indonesia, 1–9. http://web.ipb.ac.id/~ir- lab/pdf/tm (text summarization).pdf
Antinasari, P., Perdana, R. S., & Fauzi, M. A. (2017). Analisis Sentimen Tentang Opini Film Pada Dokumen Twitter Berbahasa Indonesia Menggunakan Naive Bayes Dengan Perbaikan Kata Tidak Baku. Jurnal Pengembangan Teknologi Informasi Dan Ilmu Komputer, 1(12), 1718– 1724. http://j-ptiik.ub.ac.id
Devita, R. N., Herwanto, H. W., & Wibawa, A. P. (2018). Perbandingan kinerja metode naive bayes dan k-nearest neighbor untuk klasifikasi artikel berbahasa indonesia. JTIIK (Jurnal Teknologi Informasi Dan Ilmu Komputer) Vol, 5.
Gustian, D., Suciati, I., & Saepudin, S. (n.d.). Sistem Pakar Dengan Algoritma Naive Bayes Untuk Prediksi Hasil Produksi Ayam Broiler Plasma (Studi Kasus: Pt. Sekawan Sinar Surya). no. Kalingara, N. I. P., Pratiwi, O. N., & Anggana, H. D. (2021). Analisis Sentimen Review Customer Terhadap Layanan Ekspedisi Jne Dan J\&t Express Menggunakan Metode NaÏve Bayes.
EProceedings of Engineering, 8(5).
Liu, B. (2012). Sentiment analysis and opinion mining. Synthesis Lectures on Human Language Technologies, 5(1), 1–167.
Lorosae, T. A., Prakoso, B. D., Saifudin, S., & Kusrin, K. (2018). Analisis Sentimen Berdasarkan Opini Masyarakat pada Twitter Menggunakan Naive Bayes. Semnasteknomedia Online, 6(1), 1–10.
Nugraha, M. W. A. (2014). Sentiment Analysis Pada Review Film Dengan Menggunakan Metode K-Nearest Neighbor. Universitas Widyatama.
Ratnawati, F. (2018). Implementasi Algoritma Naive Bayes Terhadap Analisis Sentimen Opini Film Pada Twitter. INOVTEK Polbeng - Seri Informatika, 3(1), 50. https://doi.org/10.35314/isi.v3i1.335
Rustiana, D., & Rahayu, N. (2017). Analisis Sentimen Pasar Otomotif Mobil: Tweet Twitter Menggunakan Naïve Bayes. Simetris: Jurnal Teknik Mesin, Elektro Dan Ilmu Komputer, 8(1), 113–120. https://doi.org/10.24176/simet.v8i1.841