Article Per Year (5 Year)
p-Index From 2021 - 2026
0.817
P-Index
This Author published in this journals
All Journal JITK (Jurnal Ilmu Pengetahuan dan Komputer) SKANIKA: Sistem Komputer dan Teknik Informatika Jurnal Informatika Teknologi dan Sains (Jinteks)
Risca Lusiana Pratiwi
Universitas Nusa Mandiri
Computer Science & IT Control & Systems Engineering Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
APPLICATION OF THE K-NEAREST NEIGHBOR (KNN) ALGORITHM IN SENTIMENT ANALYSIS OF THE OVO E-WALLET APPLICATION Siti Masturoh; Risca Lusiana Pratiwi; M Rangga Ramadhan Saelan; Ummu Radiyah
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 8 No. 2 (2023): JITK Issue February 2023
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (630.107 KB) | DOI: 10.33480/jitk.v8i2.3997

Abstract

Abstract— The OVO application can be downloaded on the Android platform via Google Play, Google play has a review feature on the application product to be downloaded, so that the review can be viewed or accessed by anyone, With these reviews, potential users of the application will see how important it is to consider using an application, problems regarding reviews or sentiment analysis of applications processed using text mining. The purpose of this study is to provide information to prospective OVO application users before using the application which can be seen from the results of giving reviews based on rating or stars (*) in the OVO application review column on Google Play and the authors categorize them into 3 classes, the first class ( 1 to 5 stars, second class (1 and 5 stars) third class by providing labeling grouping (1&2 stars are negative labels, 3 stars are neutral labels and 4&5 stars are positive labels) testing using the k-nearest neighbor method by finding the value of k from the k value of 1-10 to get the highest accuracy value, in order to obtain the highest accuracy value of 84.86% in the 2nd class test and giving a value of k 1 which means that the 1st and 5th star tests get positive values so that they can give a good impression to prospective application users OVO
ANALISIS KANKER PARU-PARU MENGGUNAKAN ALGORITMA LOGISTIC REGESSION DAN RANDOM FOREST Zulia Imami Alfianti; Ginabila Ginabila; Ahmad Fauzi; Risca Lusiana Pratiwi
Jurnal Informatika Teknologi dan Sains (Jinteks) Vol 8 No 1 (2026): EDISI 27
Publisher : Program Studi Informatika Universitas Teknologi Sumbawa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51401/jinteks.v8i1.7063

Abstract

Kanker paru-paru merupakan salah satu jenis kanker dengan tingkat kematian tertinggi di dunia, yang disebabkan oleh faktor gaya hidup seperti merokok dan konsumsi alkohol, serta faktor genetik. Mengingat deteksi dini konvensional memerlukan waktu dan biaya besar, penelitian ini mengusulkan pendekatan Machine Learning yang lebih efisien untuk memprediksi risiko penyakit. Menggunakan algoritma Logistic Regression dan Random Forest pada dataset Survey Lung Cancer yang berisi 309 responden dengan 16 variabel gaya hidup dan kesehatan , penelitian ini melibatkan tahapan data understanding, data preparation (termasuk encoding dan scaling), modeling, dan evaluation. Hasil analisis menunjukkan performa yang sangat baik untuk kedua algoritma dengan nilai Akurasi 96,77% dan nilai Presisi, Recall, serta F1-score mencapai 0,9833. Meskipun metrik utama identik, perbandingan kurva ROC menunjukkan bahwa model Random Forest (AUC = 0,958) sedikit lebih unggul dari Logistic Regression (AUC = 0,917). Berdasarkan analisis, faktor usia (AGE) teridentifikasi sebagai variabel paling berpengaruh terhadap risiko kanker paru-paru, diikuti oleh konsumsi alkohol, alergi, dan tekanan sosial7. Hasil ini diharapkan menjadi referensi dalam pengembangan sistem prediksi dan deteksi dini berbasis Machine Learning.
Penerapan Algoritma Naive Bayes dan SVM untuk Analisis Sentimen terhadap Penggunaan True Wireless Stereo (TWS) Risca Lusiana Pratiwi; Zulia Imami Alfianti; Ahmad Fauzi; Ginabila Ginabila
SKANIKA: Sistem Komputer dan Teknik Informatika Vol 8 No 2 (2025): Jurnal SKANIKA Juli 2025
Publisher : Universitas Budi Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36080/skanika.v8i2.3535

Abstract

The use of wireless audio devices such as True Wireless Stereo (TWS) has become increasingly popular among Indonesian society as a solution to the limitations of wired earphones. As TWS usage continues to grow, understanding public sentiment toward these devices becomes essential to support product development and assist consumers in making informed purchasing decisions. This study aims to analyze user sentiment toward TWS on the social media platform X using the Naive Bayes and Support Vector Machine (SVM) algorithms. To improve classification performance, the Synthetic Minority Oversampling Technique (SMOTE) is applied to handle imbalanced data, while Particle Swarm Optimization (PSO) is used to optimize the model. The results show that the SVM algorithm outperforms Naive Bayes, achieving an accuracy of 80.46% and an AUC score of 0.854, with more balanced precision and recall values across both classes. Meanwhile, Naive Bayes demonstrated strength in detecting negative sentiment but with a lower accuracy of 78.00% and an AUC of 0.780
PENANGANAN EXTREME CLASS IMBALANCE PADA ANALISIS SENTIMEN ULASAN PROVIDER INTERNET MENGGUNAKAN PENDEKATAN SMOTE DENGAN ALGORITMA RANDOM FOREST DAN SVM Risca Lusiana Pratiwi; Ginabila; Zulia Imami Alfianti
Jurnal Informatika Teknologi dan Sains (Jinteks) Vol 8 No 2 (2026): EDISI 28
Publisher : Program Studi Informatika Universitas Teknologi Sumbawa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51401/jinteks.v8i2.7974

Abstract

Ketimpangan distribusi kelas yang ekstrem pada data ulasan pelanggan menjadi tantangan utama yang memicu bias prediksi pada model pembelajaran mesin. Penelitian ini bertujuan untuk menguji efektivitas penanganan extreme class imbalance pada ulasan penyedia jasa internet menggunakan pendekatan Synthetic Minority Over-sampling Technique (SMOTE) yang dikombinasikan dengan algoritma Random Forest dan Support Vector Machine (SVM). Dataset berjumlah 699 rekaman ulasan diolah melalui rangkaian pra-pemrosesan teks, ekstraksi fitur Term Frequency-Inverse Document Frequency (TF-IDF), serta diuji menggunakan skema Cross Validation. Hasil evaluasi memperlihatkan bahwa kombinasi SMOTE dan SVM mencatatkan akurasi sebesar 91,56%, nilai Area Under Curve (AUC) 0,769, presisi kelas positif 100,00%, dan recall kelas positif sebesar 4,84%. Di sisi lain, skema SMOTE dan Random Forest memperoleh akurasi 91,13%, nilai AUC 0,740, serta presisi dan recall kelas positif sebesar 0,00%. Penelitian ini menyimpulkan bahwa batas pemisah linier pada SVM lebih responsif memanfaatkan sampel sintetis SMOTE dalam ruang fitur berdimensi tinggi, serta mengonfirmasi bahwa kedua algoritma memiliki kecenderungan prediktif yang dominan dalam mengenali sampel kelas mayoritas.
Co-Authors Ahmad Fauzi Ginabila M. Rangga Ramadhan Saelan Siti Masturoh Ummu Radiyah Zulia Imami Alfianti