Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal bit-Tech Jurnal Komputer, Informasi dan Teknologi
Herri Setiawan
Indo Global Mandiri University
Computer Science & IT Education Languange, Linguistic, Communication & Media

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

Found 3 Documents
Search

 1 
Classification Of Eligibility For Assistance Recipients Program Indonesia Pintar Using The Naïve Bayes Method Via Kris Savitri; Herri Setiawan; Zaid Romegar Mair
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.3002

Abstract

The manual process of determining student eligibility for the Indonesia Pintar Program (PIP) often results in inefficiencies and inaccuracies. Schools are required to evaluate large volumes of socioeconomic data, and errors in judgment may lead to misallocation, where eligible students are excluded and ineligible students are included. Such inefficiencies highlight the need for objective, data-driven approaches. This study aims to evaluate the performance of the Naïve Bayes classification algorithm in classifying PIP eligibility, with a particular focus on attribute selection and its effect on classification accuracy. Historical student data from a primary school (SDN 1 Sindang Marga), which has rarely been examined in previous works and the analysis of attribute selection strategies, showing that fewer but more relevant attributes can yield better results. A dataset of 172 students was pre-processed and divided into training (80%) and testing (20%) subsets. Model evaluation was conducted using confusion matrices to calculate accuracy, precision, recall, and F1-score. The results demonstrate that using four attributes parental occupation, parental income, KPS ownership, and KIP ownership achieved the highest performance, with 85.3% accuracy, 92.0% precision, 88.5% recall, and a 90.2% F1-score. By contrast, using all seven attributes resulted in slightly lower accuracy (82.4%). These findings highlight that selective attribute use improves model efficiency and accuracy. Beyond methodological contributions, this research provides practical implications by demonstrating how machine learning can enhance fairness, transparency, and objectivity in educational aid distribution.
Decision Support System For Selecting Smart Indonesia Card Candidates Using Preference Selection Index Method M. Reza Fhalepi; Herri Setiawan; Nazori Suhandi
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.3068

Abstract

The Kartu Indonesia Pintar (KIP) program is a government initiative designed to ensure equal access to higher education for students from low-income families. However, the selection process remains challenging due to the large number of applicants, diverse evaluation criteria, and reliance on manual judgment, which can lead to inefficiency and bias. This study develops a decision support system (DSS) using the Preference Selection Index (PSI) method to improve transparency and objectivity in selecting KIP recipients at Universitas Indo Global Mandiri. Data were obtained through observation, structured interviews, documentation, and secondary records from the BKABK finance division. Five main criteria were used in the evaluation process: parents’ occupation, housing condition, number of siblings, academic achievements, and interview performance. The PSI method was implemented through data normalization, calculation of mean and deviation, automatic weight generation, and computation of each applicant’s final PSI score. A total of 270 valid applicants were processed, with most achieving scores between 0.80 and 0.90 (mean = 0.86; SD = 0.04), reflecting a high level of competition. The top five candidates scored between 0.8787 and 0.9179, led by Christopher Nathan Tanugraha and Kiagus Deru Cahyadi. These results demonstrate that PSI can reduce subjectivity in weight assignment, increase efficiency, and minimize human error, while ensuring fair scholarship distribution. More broadly, the proposed PSI-based DSS can be applied in other universities and scholarship programs, offering a scalable solution for equitable and data-driven decision-making in higher education.
Sentiment Analysis of Public Reviews on the Internet for Gelora Sriwijaya International Stadium in Palembang Using Random Forest Classifier Title Yoga Seprana; Herri Setiawan; Zaid Romegar Mair
Jurnal Komputer, Informasi dan Teknologi Vol. 5 No. 2 (2025): Desember
Publisher : Penerbit Jurnal Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53697/jkomitek.v5i2.3036

Abstract

This study was conducted with the aim of analyzing the sentiments contained in public reviews of the Gelora Sriwijaya International Stadium in Palembang. The analysis utilized the Random Forest Classifier algorithm as the main method for the classification process. The data source was obtained from Google Maps through web scraping using the Instant Data Scraper tool, resulting in a total of 1,000 reviews written between 2019 and 2025. These reviews then went through a series of preprocessing stages, including data cleaning to remove irrelevant information, case folding to standardize letter formats, stemming to return words to their root form, stopword removal to eliminate common words with little semantic value, and tokenization to split the text into individual word units. Subsequently, the text data was transformed into a numerical representation using the Term Frequency–Inverse Document Frequency (TF-IDF) method to make it suitable for processing by the classification algorithm. Sentiment classification was carried out by categorizing reviews into two main classes: positive sentiment and negative sentiment. The evaluation results showed that the model achieved an accuracy of 89% when tested using the K-Fold Cross Validation technique, which was higher than the 84% accuracy obtained without validation. These findings demonstrate that the Random Forest Classifier algorithm is highly capable of performing sentiment analysis and has the potential to serve as a useful tool for stadium management to understand public perceptions and improve the quality of facility management.
Co-Authors M. Reza Fhalepi Nazori Suhandi Via Kris Savitri Yoga Seprana Zaid Romegar Mair