Sentiment Analysis of Bali Calendar Application Reviews using K-Nearest Neighbour

Rosaliaarum Kumalasanti; Ni Made Dina Aprilianti

doi:10.46923/ijets.v6i1.339

Rosaliaarum Kumalasanti Universitas Sanata Dharma, Yogyakarta, Indonesia
Ni Made Dina Aprilianti Universitas Sanata Dharma, Yogyakarta, Indonesia

DOI: https://doi.org/10.46923/ijets.v6i1.339

Keywords: Balinese Calendar, Sentiment Analysis, K-Nearest Neighbour, Imbalance Dataset, Tomek Links

Abstract

This study evaluates user sentiment towards the Bali Calendar application, analysing both positive feedback and negative critiques. The research employs the K-Nearest Neighbour (KNN) algorithm to classify sentiments as either positive or negative, aiming to assess overall public satisfaction with the app. To improve classification performance, the Tomek Links technique is applied in conjunction with KNN. The study categorizes data into pre- and post-COVID periods to address the observed increase in negative reviews following app updates during the pandemic. In the pre-COVID phase, KNN achieved accuracy rates of 93.7% and 94.3% with and without Tomek Links, respectively, using parameter values K=5 and K=3. In the post-COVID period, accuracy rates were 86.0% and 87.2% with and without Tomek Links, respectively, using parameter K=9. The application of Tomek Links resulted in a notable accuracy improvement of 1.2% in the post-COVID data compared to a 0.6% increase in the pre-COVID data. This finding highlights the significant role of Tomek Links in enhancing KNN accuracy, particularly when dealing with unbalanced datasets. The study demonstrates that while KNN performs robustly, Tomek Links can provide a substantial boost in classification accuracy, especially in scenarios with skewed data distributions.

References

Alhaqq, R.I., Putra, I.M.K. and Ruldeviyani, Y. (2022) ‘Analisis Sentimen terhadap Penggunaan Aplikasi MySAPK BKN di Google Play Store’, Jurnal Nasional Teknik Elektro dan Teknologi Informasi, 11(2), pp. 105–113. Available at: https://doi.org/10.22146/jnteti.v11i2.3528.

Alitmd (2021) Kalender Bali. Available at: https://play.google.com/store/apps/details?id=com.alitmd.kalenderbali&hl=id&gl=US (Accessed: 23 May 2023).

Aprilianti, N.M.D. et al. (2023) ‘Analisis Perbandingan Algoritma KNN, Gaussian Naive Bayes, Random Forest Untuk Data Tidak Seimbang Dan Data Yang Diseimbangkan Dengan Metode Tomek Link Undersampling Pada Dataset LCMS Tanaman Keladi Tikus’, 13(1), pp. 156–160.

Astuti, P. and Nuris, N. (2022) ‘Penerapan Algoritma KNN Pada Analisis Sentimen Review Aplikasi Peduli Lindungi’, Computer Science (CO-SCIENCE), 2(2), pp. 137–142. Available at: https://doi.org/10.31294/coscience.v2i2.1258.

Badan Pusat Statistik (2019) Proporsi Individu Yang Menggunakan Internet Menurut Provinsi. Available at: https://www.bps.go.id/indicator/27/1225/1/proporsi-individu-yang-menggunakan-internet-menurutprovinsi.html (Accessed: 28 November 2023).

Barus, S.G. (2022) ‘Klasifikasi Sentimen Data Tidak Seimbang Menggunakan Algoritma Smote Dan KNearest Neighbor Pada Ulasan Pengguna Aplikasi Pedulilindungi’, Senamika, pp. 162–173.

Cholil, S.R. et al. (2021) ‘IJCIT (Indonesian Journal on Computer and Information Technology) Implementasi Algoritma Klasifikasi K-Nearest Neighbor (KNN) Untuk Klasifikasi Seleksi Penerima Beasiswa’, IJCIT (Indonesian Journal on Computer and Information Technology), 6(2), pp. 118–127.

Denes, I.M. et al. (1997) Kamus Bahasa Indonesia-Bali A-K. Jakarta: Pusat Pembinaan dan Pengembangan Bahasa.

Dewi, I.A.M.C., Dharmendra, I.K. and Setiasih, N.W. (2023) ‘Analisis Sentimen Review Aplikasi Satu Sehat Mobile Menggunakan Model Sampling Tomek Links’, pp. 2–8. Available at: https://jurnal.undhirabali.ac.id/index.php/jutik/article/view/2644/3309.

Erawan, L. (2015) ‘Pedoman Praktikum Standar Web’, Pemrograman Web, pp. 1–109.

Iwandini, I., Triayudi, A. and Soepriyono, G. (2023) ‘Analisa Sentimen Pengguna Transportasi Jakarta Terhadap Transjakarta Menggunakan Metode Naives Bayes dan K-Nearest Neighbor’, Journal of Information System Research (JOSH), 4(2), pp. 543–550. Available at: https://doi.org/10.47065/josh.v4i2.2937.

Liu, B. (2015) Sentiment Analysis: Mining Opinions, Sentiments, and Emotions. Available at: https://doi.org/10.1017/CBO9781139084789.

Mitchell, R. (2018) Ryan Mitchell Web Scraping with Python. Available at: www.allitebooks.com.

Mondal, S. et al. (2023) ‘Machine Learning-based maternal health risk prediction model for IoMT framework’, International Journal of Experimental Research and Review, 32, pp. 145–159. Available at: https://doi.org/10.52756/ijerr.2023.v32.012.

Purbo, O.W. (2019) Text Mining, Analisis Medsos, Kekuatan Brand dan Intelijen di Internet. ANDI.

Python (2016) Sastrawi, Python. Available at: https://pypi.org/project/Sastrawi/ (Accessed: 27 November 2023).

Python (2023) Google-Play-Scraper, Python. Available at: https://pypi.org/project/google-play-scraper/ (Accessed: 27 November 2023).

Supono, R.A. and Suprayogi, M.A. (2021) ‘Perbandingan Metode TF-ABS dan TF-IDF Pada Klasifikasi Teks Helpdesk Menggunakan K-Nearest Neighbor’, Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 5(5), pp. 911–918. Available at: https://doi.org/10.29207/resti.v5i5.3403.

Utami, H. (2022) ‘Analisis Sentimen dari Aplikasi Shopee Indonesia Menggunakan Metode Recurrent Neural Network’, Indonesian Journal of Applied Statistics, 5(1), p. 31. Available at: https://doi.org/10.13057/ijas.v5i1.56825.

Veluchamy, A. et al. (2018) ‘Comparative Study cobagantiii of Sentiment Analysis with Product Reviews Using Machine Learning and Lexicon-Based Approaches’, SMU Data Science Review, 1(4), pp. 1–22. Available at: https://scholar.smu.edu/cgi/viewcontent.cgi?article=1051&context=datasciencereview.