ATHALLA, RAFFI ZAIDAN (2026) ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI GOJEK MENGGUNAKAN ALGORITMA NAIVE BAYES DAN K-NEAREST NEIGHBOR. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
COVER.pdf Download (746kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
BAB 1.pdf Restricted to Registered users only Download (144kB) |
|
|
Text (BAB II)
BAB 2.pdf Restricted to Registered users only Download (1MB) |
|
|
Text (BAB III)
BAB 3.pdf Restricted to Registered users only Download (191kB) |
|
|
Text (BAB IV)
BAB 4.pdf Restricted to Registered users only Download (246kB) |
|
|
Text (BAB V)
BAB 5.pdf Restricted to Registered users only Download (94kB) |
|
|
Text (DAFTAR PUSTAKA)
DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (138kB) |
|
|
Text (LAMPIRAN)
LAMPIRAN.pdf Restricted to Registered users only Download (558kB) |
Abstract
This study aims to compare the performance of the Naive Bayes and K-Nearest Neighbor (KNN) algorithms in sentiment analysis of Gojek user reviewsobtained from Google Play Store, consisting of 20,000 data entries. Each reviewunderwent several text preprocessing stages including case folding, tokenizing, stopword removal, stemming, and weighting using the Term Frequency–InverseDocument Frequency (TF-IDF) method. Both algorithms were tested using asupervised learning approach with an 80:20 ratio for training and testing data. Model performance was evaluated using accuracy, precision, recall, and F1- score metrics. The experimental results indicate that the Naive Bayes algorithmachieved superior performance with an accuracy of 93%, while K-Nearest Neighbor (KNN) reached 69%. Naive Bayes also demonstrated higher stabilityin identifying positive and negative sentiments and provided bettercomputational efficiency. Conversely, KNN was more sensitive to unbalanceddata distribution and required longer computation time. Based on these findings, it can be concluded that Naive Bayes is more suitable for large-scale sentiment classification of Gojek user reviews, whereas KNN serves as an alternative forsmaller and more balanced datasets. Keywords: Naive Bayes, K-Nearest Neighbor, Sentiment Analysis, GojekReviews, Machine Learning, TF-IDF. Penelitian ini bertujuan untuk membandingkan kinerja algoritma Naive Bayesdan K-Nearest Neighbor (KNN) dalam menganalisis sentimen ulasan penggunaaplikasi Gojek yang diambil dari Google Play Store sebanyak 20.000 data ulasan. Setiap ulasan diproses melalui tahapan text preprocessing yang meliputi casefolding, tokenizing,stopword removal, stemming, serta pembobotanmenggunakan metode Term Frequency–Inverse Document Frequency (TF-IDF). Kedua algoritma diuji dengan pendekatan supervised learning menggunakanrasio pembagian data 80% untuk pelatihan dan 20% untuk pengujian. Evaluasi performa dilakukan menggunakan metrik akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa algoritma Naive Bayes menghasilkanperforma yang lebih baik dengan akurasi mencapai 89%, sedangkan K-Nearest Neighbor (KNN) hanya mencapai 69%. Naive Bayes juga lebih stabil dalammengenali sentimen positif dan negatif serta memiliki efisiensi komputasi yanglebih tinggi. Sebaliknya, KNN lebih sensitif terhadap distribusi data yang tidakseimbang dan membutuhkan waktu komputasi yang lebih lama. Berdasarkanhasil tersebut, dapat disimpulkan bahwa algoritma Naive Bayes lebih unggul dansesuai untuk digunakan dalam klasifikasi sentimen ulasan pengguna Gojekberskala besar, sementara KNN dapat menjadi alternatif untuk dataset yang lebihkecil dan seimbang. Kata kunci: Naive Bayes, K-Nearest Neighbor, Analisis Sentimen, UlasanGojek, Machine Learning, TF-IDF.
Actions (login required)
 |
View Item |
