Analisis Sentimen Aplikasi E-Government pada Google Play Menggunakan Algoritma Naïve Bayes

  • Artanti Inez Tanggraeni Universitas Kristen Satya Wacana
  • Melkior N. N. Sitokdana Universitas Kristen Satya Wacana
Keywords: E-Gov, Sentuh Tanahku, Review, Sentiment Analysis, Naïve Bayes

Abstract

E-gov is a digital innovation created by the government to create more effective and efficient business processes to meet the needs of the community. As a manifestation of this innovation in the land sector, the government makes an application called Sentuh Tanahku. Sentuh Tanahku is distributed on Google Play and generates a lot of reviews from users. The results of these reviews have an impact on the use and development of the application. However, with the large amount of review data, it will be difficult to process manually. Therefore, a method is needed to automatically see the user's tendency towards the application, whether it is positive or negative. The method that will be used is sentiment analysis. The stages are collecting review data on Google Play, manually labeling to get positive and negative review data, data preprocessing, TF-IDF weighting, classification using the Naïve Bayes algorithm, and evaluation. The labeling process shows that Sentuh Tanahku application gets positive response from users with a comparison of 407 positive reviews and 235 negative reviews. And from the results of sentiment analysis testing using the Naïve Bayes algorithm with TF-IDF weighting, it produces an accuracy of 89%, precision of 83%, and recall of 87%.

References

[1] S. A. Aaputra, Didi Rosiyadi, Windu Gata, and Syepry Maulana Husain, “Sentiment Analysis Analysis of E-Wallet Sentiments on Google Play Using the Naive Bayes Algorithm Based on Particle Swarm Optimization,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 3, no. 3, pp. 377–382, Dec. 2019, doi: https://doi.org/10.29207/resti.v3i3.1118.
[2] T. W. A. Nugroho, “Analisis E-Government Terhadap Pelayanan Publik Di Kementerian Hukum Dan Ham (Analysis Of E-Government To Public Services In The Ministry Of Law And Human Rights),” J. Ilm. Kebijak. Huk., vol. 10, no. 3, pp. 279–296, 2016.
[3] “Pendahuluan - Sentuh Tanahku.” https://docs.atrbpn.go.id/sentuhtanahku/ (accessed Sep. 06, 2021).
[4] F. Zamachsari, G. V. Saragih, Susafa’ati, and W. Gata, “Analisis Sentimen Pemindahan Ibu Kota Negara dengan Feature Selection Algoritma Naive Bayes dan Support Vector Machine,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 4, no. 3, pp. 504–512, 2020, doi: https://doi.org/10.29207/resti.v4i3.1942.
[5] M. K. R. M. N Faisal Kharie, “Evaluasi Usability Aplikasi Sentuh Tanahku Menggunakan Metode Heuristic,” IJIS-Indonesia J. Inf. Syst., vol. 5, no. 1, pp. 34–43, 2020, doi: https://doi.org/10.36549/ijis.v5i1.63.
[6] L. Ardiani, H. Sujaini, and Tursina, “Implementasi Sentiment Analysis Tanggapan Masyarakat Terhadap Pembangunan di Kota Pontianak,” J. Sist. dan Teknol. Inf., vol. 8, no. 2, pp. 183–190, 2020, doi: 10.26418/justin.v8i2.36776.
[7] D. Pratmanto, R. Rousyati, F. F. Wati, A. E. Widodo, S. Suleman, and R. Wijianto, “App Review Sentiment Analysis Shopee Application in Google Play Store Using Naive Bayes Algorithm,” J. Phys. Conf. Ser., vol. 1641, no. 1, pp. 1–7, 2020, doi: https://doi.org/10.1088/1742-6596/1641/1/012043.
[8] Nurdin, M. Hutomi, M. Qamal, and B. Bustami, “Sistem Pengecekan Toko Online Asli atau Dropship pada Shopee Menggunakan Algoritma Breadth First Search,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 4, no. 6, pp. 1117–1123, Dec. 2020, doi: https://doi.org/10.29207/resti.v4i6.2514.
[9] J. A. Septian, T. M. Fahrudin, and A. Nugroho, “Analisis Sentimen Pengguna Twitter Terhadap Polemik Persepakbolaan Indonesia Menggunakan Pembobotan TF-IDF dan K-Nearest Neighbor,” J. Intell. Syst. Comput., pp. 43–49, 2019, doi: https://doi.org/10.52985/insyst.v1i1.36.
[10] C. H. Yutika, A. Adiwijaya, and S. Al Faraby, “Analisis Sentimen Berbasis Aspek pada Review Female Daily Menggunakan TF-IDF dan Naïve Bayes,” J. Media Inform. Budidarma, vol. 5, no. 2, pp. 422–430, 2021, doi: https://doi.org/10.30865/mib.v5i2.2845.
[11] L. M. Chaira, N. Hidayat, I. L. Wibowo, and I. Mukhlash, “Pemilihan Jenis Asuransi Berdasarkan Demografi Calon Pemegang Polis dengan Metode Naive Bayes Classifier,” J. Math. Its Appl., vol. 13, pp. 11–20, 2016, doi: https://doi.org/10.12962/j1829605X.v13i2.1931.
[12] R. Watrianthos, S. Suryadi, D. Irmayani, M. Nasution, and E. F. S. Simanjorang, “Sentiment Analysis of Traveloka App Using Naïve Bayes Classifier Method,” Int. J. Sci. Technol. Res., vol. 8, no. 7, pp. 786–788, 2019, doi: https://doi.org/10.31227/osf.io/2dbe4.
[13] N. Herlinawati, Y. Yuliani, S. Faizah, and W. Gata, “Analisis Sentimen ZOOM Cloud Meetings di Play Store Menggunakan Naïve Bayes dan Support Vector Machine,” vol. 5, no. 2, pp. 293–298, 2020, doi: https://doi.org/10.24114/cess.v5i2.18186.
[14] R. N. Devita et al., “Perbandingan Kinerja Metode Naïve Bayes dan K-Nearest Neighbor untuk Klasifikasi Artikel Berbahasa Indonesia,” vol. 5, no. 4, pp. 427–434, 2018, doi: https://doi.org/10.25126/jtiik.201854773.
Published
2022-06-09