Cianata, Vincent (2025) Perbandingan analisis sentimen ulasan aplikasi Superbank menggunakan metode naïve bayes dan support vector machine. Bachelor thesis, Universitas Pelita Harapan.
![Title [thumbnail of Title]](http://repository.uph.edu/style/images/fileicons/text.png)
Title.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (139kB)
Preview
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (359kB) | Preview
Preview
ToC.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (525kB) | Preview
Preview
Chapter1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (540kB) | Preview
![Chapter2 [thumbnail of Chapter2]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (1MB)
![Chapter3 [thumbnail of Chapter3]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (1MB)
![Chapter4 [thumbnail of Chapter4]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (2MB)
![Chapter5 [thumbnail of Chapter5]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (358kB)
Preview
Bibliography.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (462kB) | Preview
![Appendices [thumbnail of Appendices]](http://repository.uph.edu/style/images/fileicons/text.png)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (1MB)
Abstract
Adanya perkembangan digital yang signifikan menyebabkan penggunaan layanan bank digital menjadi lebih tinggi melalui aplikasi mobile. Salah satu bank digital yang semakin sering dipakai adalah Superbank, Pada aplikasi Superbank, terdapat berbagai ulasan yang diberikan pengguna terhadap aplikasi, mulai dari pujian hingga keluhan masalah dalam beberapa aspek layanan aplikasi. Seluruh keluhan masalah ini dapat mempengaruhi calon pengguna untuk memakai aplikasi ini. Sehingga diperlukan untuk mengidentifikasi dan memahami sentimen pengguna melalui ulasan tersebut, yang dapat memberikan wawasan bagi perusahaan dalam meningkatkan layanan mereka. Metode yang sering digunakan adalah metode Naïve Bayes dan Support Vector Machine (SVM). Kedua metode ini digunakan untuk mencari metode yang lebih efektif dalam mengklasifikasi sentimen dalam ulasan pengguna. Dataset yang digunakan adalah ulasan dari aplikasi Superbank yang berjumlah sebanyak 13013 data, yang dikumpulkan dari rentang waktu tahun 2023 sampai dengan 2025. Proses pengolahan data yang dilalui meliputi preprocess data, transformasi TF-IDF, pembagian data testing dan data training, dan klasifikasi dengan metode Naïve Bayes dan SVM. Hasil evaluasi dari Naïve Bayes memiliki nilai accuracy sebesar 0,89, precision sebesar 0,90, recall sebesar 0,89, dan F1-score sebesar 0,87. Sedangkan hasil evaluasi dari SVM memiliki nilai accuracy sebesar 0,94, precision sebesar 0,94, recall sebesar 0,94, dan F1-score sebesar 0,92. Kesimpulan dari hasil yang diperoleh menunjukkan bahwa metode SVM lebih akurat daripada Naïve Bayes pada penelitian ini.
/
The significant development of digital technology has led to an increase in the use of digital banking services through mobile applications. One of the digital banks that is being used more frequently is Superbank. On the Superbank application, users provide various reviews, ranging from praise to complaints about different aspects of the application’s services. These complaints can influence potential users in deciding whether to use the application. Therefore, it is necessary to identify and understand user sentiment through these reviews, which can provide valuable insights for the company to improve its services. The commonly used methods are Naïve Bayes and Support Vector Machine (SVM). These methods are used to determine which one is more effective in classifying sentiment in user reviews. The dataset used consists of reviews from the Superbank application, totaling 13,013 data points collected from the years 2023 to 2025. The data processing steps include data preprocessing, TF-IDF transformation, data splitting into testing and training sets, and classification using the Naïve Bayes and SVM methods. The evaluation results show that Naïve Bayes achieved an accuracy of 0.89, a precision of 0.90, a recall of 0.89, and an F1-score of 0.87. Meanwhile, SVM achieved an accuracy of 0.94, a precision of 0.94, a recall of 0.94, and an F1-score of 0.92. The conclusion from these results indicates that the SVM method is more accurate than Naïve Bayes in this study.
Item Type: | Thesis (Bachelor) |
---|---|
Creators: | Creators NIM Email ORCID Cianata, Vincent NIM03082210042 vincentcianata27@gmail.com UNSPECIFIED |
Contributors: | Contribution Contributors NIDN/NIDK Email Thesis advisor Kusuma, Benz Edy NIDN0327058302 UNSPECIFIED |
Uncontrolled Keywords: | Naive Bayes; Naïve Bayes; Support Vector Machine; SVM; Analisis Sentimen; Superbank |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
Depositing User: | Vincent Cianata |
Date Deposited: | 18 Jul 2025 09:28 |
Last Modified: | 18 Jul 2025 09:28 |
URI: | http://repository.uph.edu/id/eprint/69658 |