Article Per Year (5 Year)
p-Index From 2021 - 2026
3.108
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Informatika Komputer Jurnal Riset Informatika Jurnal Mantik Jusikom: Jurnal Sistem Informasi Ilmu Komputer INTI Nusa Mandiri SKANIKA: Sistem Komputer dan Teknik Informatika Profitabilitas Jurnal Informatika Teknologi dan Sains (Jinteks) Jurnal Teknik Komputer dan Informatika (JTeKI)
Zulia Imami Alfianti
Universitas Bina Sarana Informatika
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media

Published : 15 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 15 Documents
Search

 1   2 
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.
SENTIMENT ANALYSIS OF COSMETIC REVIEW USING NAIVE BAYES AND SUPPORT VECTOR MACHINE METHOD BASED ON PARTICLE SWARM OPTIMIZATION Zulia Imami Alfianti; Deni Gunawan; Ahmad Fikri Amin
Jurnal Riset Informatika Vol. 2 No. 3 (2020): June 2020 Edition
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34288/jri.v2i3.113

Abstract

Sentiment analysis is an area of ​​approach that solves problems by using reviews from various relevant scientific perspectives. Reading a review before buying a product is very important to know the advantages and disadvantages of the products we will use, besides reading a cosmetic review can find out the quality of the cosmetic brand is feasible or not be used. Before consumers decide to buy cosmetics, consumers should know in detail the products to be purchased, this can be learned from the testimonials or the results of reviews from consumers who have bought and used the previous product. The number of reviews is certainly very much making consumers reluctant to read reviews. Eventually, the reviews become useless. For this reason, the authors classify based on positive and negative classes, so consumers can find product comparisons quickly and precisely. The implementation of Particle Swarm Optimization (PSO) optimization can improve the accuracy of the Support Vector Machine (SVM) and Naïve Bayes (NB) algorithm can improve accuracy and provide solutions to the review classification problem to be more accurate and optimal. Comparison of accuracy resulting from testing this data is an SVM algorithm of 89.20% and AUC of 0.973, then compared to SVM based on PSO with an accuracy of 94.60% and AUC of 0.985. The results of testing the data for the NB algorithm are 88.50% accuracy and AUC is 0.536, then the accuracy is compared with the PSO based NB for 0.692. In these calculations prove that the application of PSO optimization can improve accuracy and provide more accurate and optimal solutions.
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.
ANALISIS SENTIMEN PERKEMBANGAN MOTOR LISTRIK MENGGUNAKAN SUPPORT VECTOR MACHINE DAN OPTIMASI PARTICLE SWARM OPTIMIZATION Ginabila Ginabila; Ahmad Fauzi; Risca Lusiana Pratiwi; Siti Fauziah; Zulia Imami Alfianti
INTI Nusa Mandiri Vol. 19 No. 1 (2024): INTI Periode Agustus 2024
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v19i1.5579

Abstract

Innovation in electric motor technology such as increased range, speed, and battery endurance can attract interest from individuals fascinated by the latest advancements. Sentiment analysis enables a profound understanding of consumer perceptions towards electric motors. In this study, Support Vector Machine (SVM) is employed as a classification tool to evaluate opinions on current developments in electric motors. SVM seeks an optimal hyperplane that maximizes the distance between sentiment categories. The development of sentiment analysis methods utilizes SVM with Particle Swarm Optimization (PSO) to successfully achieve an accuracy of 80.33% and obtain a Good Classification category based on ROC Curve results. This research provides insights into consumer perceptions of electric motor technology, offering valuable feedback for manufacturers in the development of superior electric motor products. Leveraging sentiment analysis, manufacturers can enhance product improvements, increase quality, and expand functionality to meet the evolving market demands.
Co-Authors Ahmad Fauzi Ahmad Fauzi Ahmad Fikri Amin Dede Mustomi Deni Gunawan Eko Yulianto Fauzi Ahmad Muda Ginabila KOMALASARI, YULI Laetussaadah, Lela Mochammad Abdul Azis Pratiwi, Risca Lusiana Risca Lusiana Pratiwi Risca Lusiana Pratiwi Siti Fauziah Siti Fauziah Sugiono