Analisis Sentimen Kepuasan Pelanggan Perusahaan Telekomunikasi Seluler Telkomsel di Twitter
DOI:
https://doi.org/10.30989/teknomatika.v15i2.1117Keywords:
Telkomsel, Naive Bayes Classification, WebApp, Sentiment Analysis, Python, FlaskAbstract
Telkomsel, the largest operator in Indonesia with the most users, collects a significant amount of tweet data on Twitter, containing both positive and negative feedback about their internet service. Analyzing this data can provide valuable insights and accurate information about Telkomsel's internet services based on user tweets, retweets, and comments. The aim is to build a sentiment analysis model to extract relevant information from Telkomsel users' tweets on Twitter, serving as feedback for service evaluation and an educational tool for users. The sentiment analysis process involves data retrieval, preprocessing, training, testing, classification, and visualization using Python programming with the Flask framework. Analysis of customer satisfaction sentiment reveals that Telkomsel has a negative sentiment, with an accuracy of 81.7% for training data and 84% for testing data. The sentiment analysis model was built using the Naive Bayes Classification method.
References
[2] R. Pahlevi, “Pengguna Internet di Dunia Capai 4,95 Miliar Orang Per Januari 2022. ,” https://databoks.katadata.co.id/datapublish/2022/02/07/pengguna-internet-di-dunia-capai-495-miliar-orang-per-januari-2022, Jan. 2022.
[3] I. Asror, E. Darwiyanto, and A. Nisa, “Analisis Sentimen Menggunakan Naive Bayes Classifier dengan Chi-Square Feature Selection Terhadap Penyedia Layanan Telekomunikasi,” vol. 6 No.2, pp. 8650–8659, 2019.
[4] H. Abubakar, A. M. A. Khaidar, and N. Siskawati, “Pengaruh Kualitas Layanan Terhadap Kepuasan Pelanggan Pada PT Telekomunikasi Selular Indonesia Grapari Telkomsel Makassar (Studi Kasus: Aplikasi My Telkomsel). ,” Economics Bosowa, vol. 4 No.1, pp. 56–56, 2018.
[5] R. Kurniawan And A. Apriliani, “Analisis Sentimen Masyarakat Terhadap Virus Corona Berdasarkan Opini Dari Twitter Berbasis Web Scraper,” Jurnal INSTEK (Informatika Sains dan Teknologi), vol. 5, no. 1, p. 67, Apr. 2020, doi: 10.24252/instek.v5i1.13686.
[6] B. Gunawan, H. S. Pratiwi, and E. E. Pratama, “Sistem Analisis Sentimen pada Ulasan Produk Menggunakan Metode Naive Bayes,” Jurnal Edukasi dan Penelitian Informatika (JEPIN), vol. 4, no. 2, p. 113, Dec. 2018, doi: 10.26418/jp.v4i2.27526.
[7] Kevin Perdana, Titania Pricillia, and Z. Zulfachmi, “Optimasi Textblob Menggunakan Support Vector Machine Untuk Analisis Sentimen (Studi Kasus Layanan Telkomsel),” Jurnal Bangkit Indonesia, vol. 10, no. 1, pp. 13–15, Mar. 2021, doi: 10.52771/bangkitindonesia.v10i1.120.
[8] S. Samsir, A. Ambiyar, U. Verawardina, F. Edi, And R. Watrianthos, “Analisis Sentimen Pembelajaran Daring Pada Twitter Di Masa Pandemi Covid-19 Menggunakan Metode Naïve Bayes,” Jurnal Media Informatika Budidarma, Vol. 5, No. 1, P. 157, Jan. 2021, doi: 10.30865/mib.v5i1.2580.
[9] N. P. G. Naraswati, R. Nooraeni, D. C. Rosmilda, D. Desinta, F. Khairi, and R. Damaiyanti, “Analisis Sentimen Publik dari Twitter Tentang Kebijakan Penanganan Covid-19 di Indonesia dengan Naive Bayes Classification,” SISTEMASI, vol. 10, no. 1, p. 222, Jan. 2021, doi: 10.32520/stmsi.v10i1.1179.
[10] R. N. Devita, H. W. Herwanto, and A. P. Wibawa, “Perbandingan Kinerja Metode Naive Bayes dan K-Nearest Neighbor untuk Klasifikasi Artikel Berbahasa indonesia,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 5, no. 4, p. 427, Oct. 2018, doi: 10.25126/jtiik.201854773.
