Analisis Sentimen Pengguna terhadap Aplikasi ChatGPT di Google Play Store: Penerapan Algoritma Support Vector Machine

  • Angga Ardiansyah Universitas Bina Sarana Informatika
  • Suleman Suleman Universitas Bina Sarana Informatika
  • Eva Argarini Pratama Universitas Bina Sarana Informatika
  • Nuzul Imam Fadlilah Universitas Bina Sarana Informatika
Keywords: sentiment, scraping, accuracy, SVM

Abstract

Sentiment analysis is the process of identifying attitudes, opinions, or feelings towards data or objects. The results of sentiment analysis can be categorized into two types, namely positive and negative sentiment. This research utilizes the Google Play Store which is used by the public as an object for sentiment analysis. Data was collected. Data collection was carried out using the scraping technique, then processed in RapidMine. The process for analyzing this sentiment uses the Support Vector Machine algorithm using 300 data. Next, testing was carried out using the Confusion Matrix to evaluate the performance of the classification results. From testing, accuracy was obtained at 88.74%, precision at 96.54%, recall at 83.23%, and AUC at 98.7%. Of the total 300 review data, 144 positive review data were predicted correctly, 28 negative review data were included in the positive prediction, 6 positive data were included in the negative prediction, and 122 negative data were in accordance with the negative prediction

References

[1] Mukrodin and N. Mega Sasmita, “Artificial Inteligence Dalam Apilkasi Chatbot Sebagai Helpdesk Obyek Wisata Dengan Permodelan Natural Language Processing (Studi Kasus: Kabupaten Cilacap),” Smart Comp Jurnalnya Orang Pint. Komput., vol. 10, no. 1, pp. 7–14, 2021, doi: 10.30591/smartcomp.v10i1.2135.
[2] A. Faiz and I. Kurniawaty, “Tantangan Penggunaan ChatGPT dalam Pendidikan Ditinjau dari Sudut Pandang Moral,” Edukatif J. Ilmu Pendidik., vol. 5, no. 1, pp. 456–463, 2023, doi: 10.31004/edukatif.v5i1.4779.
[3] A. Nurian, “Analisis Sentimen Ulasan Pengguna Aplikasi Google Play Menggunakan Naïve Bayes,” J. Inform. dan Tek. Elektro Terap., vol. 11, no. 3s1, pp. 829–835, 2023, doi: 10.23960/jitet.v11i3s1.3348.
[4] M. P. Dwi Cahyo, Widodo, and B. Prasetya Adhi, “Kinerja Algoritma Support Vector Machine dalam MenentukanKebenaran Informasi Banjir di Twitter,” PINTER J. Pendidik. Tek. Inform. dan Komput., vol. 3, no. 2, pp. 116–121, 2019, doi: 10.21009/pinter.3.2.5.
[5] B. Wahyudi, “Prediksi Peringkat Aplikasi di Google Play Menggunakan Metode Random Forest,” J. Nas. Teknol. Komput., vol. 2, no. 1, pp. 38–47, 2022, doi: 10.61306/jnastek.v2i1.25.
[6] E. Suryati, Styawati, and A. A. Aldino, “Analisis Sentimen Transportasi Online Menggunakan Ekstraksi Fitur Model Word2vec Text Embedding Dan Algoritma Support Vector Machine (SVM),” J. Teknol. Dan Sist. Inf., vol. 4, no. 1, pp. 96–106, 2023, [Online]. Available: https://doi.org/10.33365/jtsi.v4i1.2445.
[7] M. A. Adli and L. Firgia, “Rancang Bangun Web Scraping Pada Media Online Berita Nasional,” J. ENTER, vol. 1, pp. 118–128, 2018.
[8] I. B. A. P. Manuaba, Y. No, and C. C. Wu, “The effectiveness of problem based learning in improving critical thinking, problem-solving and self-directed learning in first-year medical students: A meta-analysis,” PLoS One, vol. 17, no. 11 November, pp. 1–12, 2022, doi: 10.1371/journal.pone.0277339.
[9] M. Deffry, A. Ardiansyah, M. Falah Fadhilah, U. Negeri Jakarta, and J. Rawamangun Muka No, “Analisis Wilayah Rawan Banjir Dengan Menggunakan Metode Skoring dan Overlay di Kecamatan Makasar,” J. Sains Geogr., vol. 1, no. 2, p. 2023, 2022, doi: 10.2210/jsg.vx1ix.xxx.
[10] F. V. Sari and A. Wibowo, “Analisis Sentimen Pelanggan Toko Online Jd.Id Menggunakan Metode Naïve Bayes Classifier Berbasis Konversi Ikon Emosi,” J. SIMETRIS, vol. 10, no. 2, pp. 681–686, 2019.
Published
2024-06-10