Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal Journal of Computer System and Informatics (JoSYC) Jurnal Sistem Komputer dan Informatika (JSON)
Yusra Yusra
Universitas Islam Negeri Sultan Syarif Kasim, Pekanbaru
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Industrial & Manufacturing Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Penerapan Metode Naïve Bayes Classifier Pada Klasifikasi Sentimen Terhadap Anies Baswedan Sebagai Bakal Calon Presiden 2024 Mar`iy Romizzidi Amly; Yusra Yusra; Muhammad Fikry
Jurnal Sistem Komputer dan Informatika (JSON) Vol 4, No 4 (2023): Juni 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v4i4.6214

Abstract

Anies Baswedan is a political figure who has been declared as a 2024 presidential candidate. Public opinion is a valuable source of information to analyze sentiment towards Anies Baswedan as a 2024 presidential candidate. Limited human power, emotional instability, and the length of time required are difficulties in analyzing sentiment on large amounts of data manually. Machine learning is utilized to provide convenience in sentiment classification.  This research applies the Naïve Bayes Classifier method in the classification of sentiment towards Anies Baswedan as a 2024 presidential candidate. This study aims to determine the performance of the Naïve Bayes Classifier method in the classification of sentiment towards Anies Baswedan as a 2024 presidential candidate. The dataset used was 3,400 which were labeled by crowdsourcing resulting in 2,130 positive (62.65%) and 1,270 negative (37.35%). Tests were conducted using the 10-fold cross-validation and 5-fold cross-validation methods, each consisting of two experimental scenarios, namely using an unbalanced dataset and using a balanced dataset.The Naive Bayes Classifier method produces the best model in the 10-fold cross-validation test with an accuracy of 89.76%, precision of 89.92%, recall of 89.76%, and f1-score of 89.75% on the sixth fold by determining a threshold value of 13 in an experiment using a balanced dataset consisting of 1,270 positives and 1,270 negatives with an average accuracy rate of 79.88%.
Klasterisasi Peserta BPJS Berdasarkan Rekam Medis Menggunakan Algoritma K-Means Ana Fitri Khairani; Alwis Nazir; Teddie Darmizal; Yelfi Vitriani; Yusra Yusra
Journal of Computer System and Informatics (JoSYC) Vol 4 No 3 (2023): May 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v4i3.3442

Abstract

The history of the patient's medical examination with the BPJS (Social Security Administration Agency) at the Dumai City Hospital will be stored in the form of a medical record. The medical record is a file that contains patient identification information whether it contains the results of control, treatment and other services. The purpose of this research is to. to assist the Dumai Hospital in grouping BPJS participants based on medical records to find out the disease, gender and BPJS group that is most dominant in Dumai City BPJS participants. The results of grouping the disease will then be processed using data mining techniques. In this study, the focus was on BPJS PBI participants inpatient medical record data from January to December 2022, which were then processed using the K-Means Clustering algorithm with 3 clusters. Cluster 0 is dominated by disease types with code O342 (Maternal care due to uterine scar from previous surgery), female sex and age range 21-40 years. Cluster 1 is dominated by types of disease with code E119 (Diabetes mellitus without complications), female sex and age range 41-60 years and cluster 2 is dominated by disease types with code J180 (Bronchopneumonia, unspecified organism), female sex and age range 41-60 years.
Co-Authors Alwis Nazir Ana Fitri Khairani Mar`iy Romizzidi Amly Muhammad Fikry Teddie Darmizal Yelfi Vitriani