Analisis Sentimen dengan Logistic Regression untuk Deteksi Kata pada Livin’ by Mandiri

Authors

  • Ni Made Gita Satviki Nirmala Universitas Udayana Author
  • Ngurah Agus Sanjaya ER Universitas Udayana Author

DOI:

https://doi.org/10.24843/JNATIA.2024.v02.i04.p25

Keywords:

Livin by Mandiri, Logistic Regression, Mobile Banking, Sentiment Analysis, TF-IDF, Word Detection

Abstract

Livin by Mandiri is one of the most frequently used mobile banking. To find out the quality of the application, you can carry out sentiment analysis from reviews. The data taken from the Google Play Store was 6334 data from January 2022 to December 2022. The training data and test data used had a ratio of 80:20. This data goes through preprocessing and then TF-IDF weighting is carried out. After that, the analysis used logistic regression which produced 91.5% with C = 0.75. As well as getting negative sentiment results, namely precision 89%, recall 95%, f1-score 92%. Meanwhile, positive sentiment produces 94% precision, 88% recall, 91% f1-score. There is a word detection program that can help search for keywords including positive sentiment or negative sentiment from the Livin by Mandiri application. 

Downloads

Published

2024-08-02

How to Cite

[1]
Ni Made Gita Satviki Nirmala and Ngurah Agus Sanjaya ER, “Analisis Sentimen dengan Logistic Regression untuk Deteksi Kata pada Livin’ by Mandiri”, Jnatia, vol. 2, no. 4, pp. 869–878, Aug. 2024, doi: 10.24843/JNATIA.2024.v02.i04.p25.

Most read articles by the same author(s)

1 2 > >> 

Similar Articles

1-10 of 147

You may also start an advanced similarity search for this article.