Article Per Year (5 Year)
p-Index From 2020 - 2025
0.562
P-Index
This Author published in this journals
All Journal JOURNAL OF APPLIED INFORMATICS AND COMPUTING Zonasi: Jurnal Sistem Informasi JATI (Jurnal Mahasiswa Teknik Informatika)
Sasmita, Ruth Mei
Unknown Affiliation
Humanities Computer Science & IT Decision Sciences, Operations Research & Management Environmental Science Languange, Linguistic, Communication & Media

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
PERBANDINGAN METODE NAÏVE BAYES DAN K-NEAREST NEIGHBOR TERHADAP ANALISIS SENTIMEN ULASAN PROGRAM MAKAN SIANG GRATIS DI INDONESIA Fathoni, Fathoni; Maretta, Aulia Pinkan; Kusuma, Aisha Nuraini; Sasmita, Ruth Mei; Rizkyllah, Anabel Fiorenza; Ibrahim, Ali
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 9 No. 4 (2025): JATI Vol. 9 No. 4
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v9i4.14084

Abstract

Program Makan Siang Gratis di Indonesia sebagai kebijakan kontroversial memicu respons beragam di media sosial, sehingga analisis sentimen diperlukan untuk memahami persepsi publik secara komprehensif. Permasalahan utama terletak pada keterbatasan metode klasifikasi dalam menangani data teks informal, yang berpotensi membuat akurasi identifikasi menurun. Penelitian ini bertujuan membandingkan kinerja algoritma Naïve Bayes dan K-Nearest Neighbor (K-NN) dalam mengklasifikasikan sentimen ulasan masyarakat terhadap program tersebut. Sebanyak 2.080 komentar dari X (Twitter) dan YouTube dikumpulkan melalui web scraping, kemudian diproses dengan tahapan cleaning (penghapusan mention, URL), penghapusan stopwords, tokenisasi, dan transformasi fitur menggunakan TF-IDF. Dataset dibagi dengan rasio 60:40 untuk training dan testing, lalu dievaluasi menggunakan metrik akurasi, precision, recall, dan F1-score. Hasil penelitian menunjukkan Naïve Bayes mencapai akurasi tertinggi (87,75%), lebih unggul dari K-NN (86,67%). Kedua algoritma mencatat precision sempurna (100%), namun memiliki kelemahan dalam recall (NB: 18,4%; K-NN: 11,2%) dan F1-score (NB: 31%; K-NN: 20,1%), yang mengindikasikan kesulitan dalam mengidentifikasi sentimen positif. Penelitian ini membuktikan keunggulan Naïve Bayes dalam analisis sentimen kebijakan publik berbasis teks informal
PERBANDINGAN METODE NAÏVE BAYES, DECISION TREE, DAN KNN DALAM ANALISIS SENTIMEN APLIKASI GOJEK DI PLAYSTORE Maretta, Aulia Pinkan; Anadia, Qothrunnada Wafi; Sasmita, Ruth Mei; Epriyanti, Nadia; Rizkyllah, Anabel Fiorenza; Mariska, Inneke Via; Tania, Ken Ditha; Meiriza, Allsela
ZONAsi: Jurnal Sistem Informasi Vol. 7 No. 2 (2025): Publikasi artikel ZONAsi: Jurnal Sistem Informasi Periode Mei 2025
Publisher : Universitas Lancang Kuning

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31849/zjf8x279

Abstract

Sentiment analysis on user evaluation of Gojek application services on Play Store is important to understand user opinions on the services provided. This study compares three machine learning methods, namely Naïve Bayes, Decision Tree, and K-Nearest Neighbors (KNN) when categorizing user sentiment on Google Play Store as positive, negative, or neutral. The data processed comes from the Gojek user review dataset obtained from Kaggle. The analysis process involves data preprocessing (cleaning, stopword removal, tokenization, and split data), data transformation, and implementation of classification algorithms. The evaluation was carried out using accuracy, precision, recall, and F1-score metrics. The results of the study prove that Naïve Bayes has the best performance with an accuracy of 89%, followed by KNN (86%) and Decision Tree (84%). This study provides good insight for application developers in choosing the best method to understand user opinions and improve service quality.
An Ensemble Learning Approach for Sentiment Analysis of Maxim Application Reviews Using SVM, KNN, and Random Forest Sasmita, Ruth Mei; Meiriza, Allsela; Novianti, Hardini
Journal of Applied Informatics and Computing Vol. 9 No. 6 (2025): December 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i6.11447

Abstract

The development of online transportation applications such as Maxim has increased the need for sentiment analysis to understand user opinions from reviews on the Google Play Store. The main challenges in this analysis are language diversity, variations in writing style, and data imbalance, which affect model accuracy. This study aims to evaluate the performance of the Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Random Forest (RF) algorithms, as well as ensemble approaches through the Voting Classifier and Combined Classifier, in sentiment analysis of Maxim app reviews. The dataset consists of 2,851 Indonesian-language reviews collected through web scraping from the Google Play Store in 2025. Sentiment labels were automatically determined based on user ratings, where ratings of 4–5 were categorized as positive and ratings below 4 as negative, with an initial distribution of 2,295 positive and 556 negative reviews before balancing using SMOTE–Tomek Links. Preprocessing steps included case folding, tokenization, stopword removal, and stemming using Sastrawi, while feature weighting was performed with unigram TF-IDF. The Combined Classifier merged the probability scores from the SVM, KNN, and RF models to produce the final prediction. Evaluation was conducted using 5-Fold Cross Validation with accuracy, precision, recall, F1-score, and ROC-AUC as evaluation metrics. The results show that RF and the Combined Classifier achieved the best performance with 85% accuracy, 87% precision, 85% recall, 86% F1-score, and 0.91 ROC-AUC, while SVM and the Voting Classifier ranked in the middle and KNN ranked the lowest. These findings confirm that ensemble learning, particularly the Combined Classifier, effectively improves the accuracy and stability of review classification compared to individual methods.
Co-Authors Ali Ibrahim Allsela Meiriza, Allsela Anadia, Qothrunnada Wafi Epriyanti, Nadia Fathoni Fathoni Hardini Novianti Ken Ditha Tania Kusuma, Aisha Nuraini Maretta, Aulia Pinkan Mariska, Inneke Via Rizkyllah, Anabel Fiorenza