Algoritma Bidirectional Long Short Term Memory untuk Analisis Sentimen Berbasis Aspek pada Aplikasi Belanja Online dengan Cicilan

  • Edy Subowo Universitas Muhammadiyah Pekajangan Pekalongan
  • Fenilinas Adi Artanto
  • Isna Putri
  • Wahyu Umaedi
https://doi.org/10.37859/jf.v12i2.3759
Keywords: BiLSTM, SVM, Trend Visualization

Abstract

Penelitian ini bertujuan untuk menganalisis sentimen berbasis aspek dalam review aplikasi. Penjualan barang dengan cara mencicil untuk mengetahui kelebihan dan kekurangan dari waktu ke waktu menurut pemakai sehingga dapat dijadikan sebagai bahan evaluasi peningkatan kualitas. Kombinasi pendekatan Bidirectional Long Short Term Memory dan klasifikasi aspek menggunakan Support Vector Machine diterapkan untuk menganalisis sentimen pada perusahaan online yang menyediakan Layanan Belanja dengan Cicilan seperti Kredivo, Akulaku, Indodana, dan BRI Ceria. Jumlah review 1000 review di google play store dengan aspek yang digunakan adalah customer service, tampilan aplikasi dan produk yang ditawarkan. Corpus Text digunakan untuk autolabelling sehingga akurasi sentimen 81% dan akurasi aspek 78%. Hasil visualisasi tren triwulanan pada aspek yang harus ditingkatkan untuk setiap aplikasi juga disajikan dalam penelitian ini.

Downloads

Download data is not yet available.

References

n Menerapkan Recurrent Neural Network dengan Algoritma Training Extended Kalman Filter.,” J. Ilm. ILMU Komput., vol. X, no. 1, pp. 7–18, 2017.
[2] E. Subowo, I. Rosyadi, and H. H. Kusumawardhani, “Twitter Data as Decision Tree Parameter for Analysis of Tourism Potential Policies,” vol. 436, pp. 474–478, 2020, doi: 10.2991/assehr.k.200529.099.
[3] E. Subowo, E. Sediyono, and Farikhin, “Ant Colony Algorithm for Determining Dynamic Travel Routes Based on Traffic Information from Twitter,” E3S Web Conf., vol. 125, no. 201 9, 2019, doi: 10.1051/e3sconf/201912523012.
[4] J. Song, “Aspect-Based Sentiment Analysis on Mobile Game Reviews Using Deep Learning,” Grad. Sch. Comput. Inf. Sci. Hosei Univ., 2020.
[5] Y. Ma, H. Peng, and E. Cambria, “Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM,” 32nd AAAI Conf. Artif. Intell. AAAI 2018, pp. 5876–5883, 2018.
[6] Y. Achmad, R. C. Wihandika, and C. Dewi, “Klasifikasi emosi berdasarkan ciri wajah wenggunakan convolutional neural network,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 3, no. 11, pp. 10595–10604, 2019.
[7] E. Subowo, T. R. Soeprobowati, and A. P. Widodo, “Prediction Meaning of Words with Word2Vec on Whatsapp Data for Disaster Topic,” E3S Web Conf., vol. 317, p. 05020, 2021, doi: 10.1051/e3sconf/202131705020.
[8] A. S. Balantimuhe, S. H. Pramono, and H. Suyono, “Konsolidasi Beban Kerja Kluster Web server Dinamis dengan Pendekatan Backpropagation Neural Network,” Eeccis, vol. 12, no. 2, pp. 72–77, 2018.
[9] H. F. Fadli and A. F. Hidayatullah, “Identifikasi Cyberbullying Pada Media Sosial Twitter Menggunakan Metode Klasifikasi Random Forest,” 2019.
[10] M. Tomas, “Recurrent neural network based language model ´ s Mikolov Introduction Comparison and model combination Future work,” Elev. Annu. Conf. Int. speech Commun. Assoc., no. September, pp. 1–24, 2010.
Published
2022-08-25
Issue
Vol 12 No 2 (2022): Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer)
Section
Articles

Copyright (c) 2022 Edy Subowo, Fenilinas Adi Artanto, Isna Putri, Wahyu Umaedi (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Copyright Notice

An author who publishes in the Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) agrees to the following terms:

  • Author retains the copyright and grants the journal the right of first publication of the work simultaneously licensed under the Creative Commons Attribution-ShareAlike 4.0 License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal
  • Author is able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book) with the acknowledgement of its initial publication in this journal.
  • Author is  permitted and encouraged to post his/her  work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of the published work (See The Effect of Open Access).

Read more about the Creative Commons Attribution-ShareAlike 4.0 Licence here: https://creativecommons.org/licenses/by-sa/4.0/.

Abstract views: 558 , PDF downloads: 773