Huda, Mochammad (2025) ANALISIS SENTIMEN ULASAN PENGGUNAAN SHOPEEPAY MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBORS(K-NN). S1 thesis, Universitas Mercu Buana Jakarta.
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (HAL COVER)
01 COVER.pdf Download (604kB) |
|
Text (BAB I)
02 BAB 1.pdf Restricted to Registered users only Download (72kB) |
|
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (225kB) |
|
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (199kB) |
|
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (320kB) |
|
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (68kB) |
|
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (127kB) |
|
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (279kB) |
Abstract
ShopeePay is one of the most popular digital wallet services in Indonesia, used by millions of users for both online and offline transactions. The large volume of user reviews presents an opportunity to analyze their sentiments toward the service. This study aims to perform sentiment analysis on ShopeePay user reviews using the K-Nearest Neighbors(K-NN) algorithm, an effective machine learning method for text classification. The user review data were obtained from the Kaggle platform. The analysis process involves several stages, including data preprocessing (text cleaning, tokenization, stopword removal, and stemming), sentiment labeling based on star ratings (positive, neutral, negative), and feature extraction using the Term Frequency-Inverse Document Frequency (TF-IDF) method. The K-NN algorithm is then used to build a sentiment classification model, with performance evaluation conducted using metrics such as accuracy, precision, recall, and F1-score. The results show that the K-NN algorithm is capable of classifying user sentiment with a high level of accuracy. Most reviews reflect a positive sentiment toward ShopeePay, particularly regarding ease of use and attractive promotions, although there are some complaints related to transaction failures and customer service. This study provides valuable insights for ShopeePay developers to improve their services based on user perceptions and experiences. The implementation of K-NN in sentiment analysis also proves its effectiveness as a tool for text processing in the fintech domain. Keywords: ShopeePay, Sentiment Analysis, K-Nearest Neighbors(K-NN), TF-IDF, User Reviews. ShopeePay adalah salah satu layanan dompet digital yang populer di Indonesia, digunakan oleh jutaan pengguna untuk transaksi online dan offline. Tingginya jumlah ulasan dari pengguna memberikan peluang untuk menganalisis sentimen mereka terhadap layanan ini. Penelitian ini bertujuan untuk menganalisis sentimen ulasan pengguna ShopeePay dengan menggunakan algoritma K-Nearest Neighbors(K-NN), sebuah metode pembelajaran mesin yang efektif untuk klasifikasi teks. Data ulasan pengguna ShopeePay diambil dari platform Kaggle. Proses analisis melibatkan beberapa tahapan, termasuk preprocessing data (pembersihan teks, tokenisasi, stopword removal, dan stemming), pelabelan sentimen berdasarkan skor bintang (positif, netral, negatif), dan ekstraksi fitur menggunakan metode Term Frequency-Inverse Document Frequency (TF-IDF). Algoritma K-NN kemudian digunakan untuk membangun model klasifikasi sentimen, dengan evaluasi kinerja dilakukan menggunakan metrik seperti akurasi, presisi, recall, dan F1- score. Hasil penelitian menunjukkan bahwa algoritma K-NN mampu mengklasifikasikan sentimen ulasan pengguna dengan tingkat akurasi yang tinggi. Sebagian besar ulasan mencerminkan sentimen positif terhadap layanan ShopeePay, terutama terkait kemudahan penggunaan dan promosi menarik, meskipun terdapat beberapa keluhan tentang kegagalan transaksi dan layanan pelanggan. Penelitian ini memberikan wawasan berharga bagi pengembang ShopeePay untuk meningkatkan layanan mereka berdasarkan persepsi dan pengalaman pengguna. Implementasi KNN dalam analisis sentimen juga membuktikan keefektifannya sebagai alat dalam pengolahan teks di bidang fintech. Kata kunci: ShopeePay, Analisis Sentimen, K-Nearest Neighbors (K-NN), TF-IDF, Ulasan Pengguna.
Actions (login required)
 |
View Item |
