Hardiartama, Rendi
Unknown Affiliation

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

Found 2 Documents
Search

Perancangan Sistem Informasi Pendataan Tahanan dan Narapidana Terintegrasi Antar Kepolisian, Kejaksaan, Lapas dan Bapas Kota Malang Menggunakan Iconix Proses Faridiana, Prihandini Daffa Nur Rizka; Salsabilla, Kharisma Agustya Zahra; Syahputra, Rafi Purwa; Hardiartama, Rendi; Kristana, Bangkit Putra; Fitri, Anindo Saka
EDUTIC Vol 11, No 1: November 2024
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/edutic.v11i1.18009

Abstract

Information technology is currently encouraging ease of data and information needs. The use of information technology is not only limited to industry, but government agencies also use it. However, not all institutions make optimal use of it. In the data collection system for detainees and convicts in Malang City, data collection is still carried out independently by each relevant institution, namely the Police, Prosecutors' Of ice, Correctional Institutions and Correctional Centers. This independent data collection causes data redundancy and inconsistency. This paper describes the stages of data collection, needs analysis and designing a web-based information system using the Iconix process. The stages of data collection were carried out through interviews and literature studies. The stages of system requirements analysis include depiction of the system flowchart and the formulation of functional and non-functional system requirements. The final stage is system design including GUI and interface design, domain models, use case diagrams, robustness diagrams, sequence diagrams and class diagrams.ABSTRAKTeknologi informasi saat ini mendorong kemudahan akan kebutuhan data dan informasi. Penggunaan teknologi informasi tidak hanya terbatas pada industri saja, melainkan lembaga-lembaga pemerintah juga turut menggunakannya. Namun, tidak semua lembaga memanfaatkannya secara optimal. Pada sistem pendataan tahanan dan narapidana di Kota Malang, pendataan masih dilaksanakan secara mandiri oleh masing-masing lembaga terkait, yakni Kepolisian, Kejaksaan, Lembaga Pemasyarakatan (Lapas) dan Balai pemasyarakatan (Bapas). Pendataan secara mandiri ini menyebabkan redundansi dan inkonsistensi data. Paper ini menjelaskan tahapan pengumpulan data, analisa kebutuhan dan perancangan sistem informasi berbasis web menggunakan Iconix proses. Tahapan pengumpulan data dilaksanakan melalui wawancara dan studi literatur. Tahapan analisa kebutuhan sistem meliputi penggambaran flowchart sistem dan perumusan kebutuhan fungsional dan non fungsional sistem. Tahapan terakhir yakni perancangan sistem meliputi perancangan GUI dan interface, domain model, diagram use case, diagram robustness, diagram sequence dan class diagram.
Application of Ensemble Machine Learning Methods for Aspect-Based Sentiment Analysis on User Reviews of the Wondr by BNI App Hardiartama, Rendi; Arifiyanti, Amalia Anjani; Ana Wati3, Seftin Fitri
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 1 (2025): Jurnal Teknologi dan Open Source, June 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i1.4297

Abstract

This study analyzes user perceptions of the Wondr by BNI app using Aspect-Based Sentiment Analysis (ABSA) and a stacking ensemble learning approach on user reviews. Data were collected from the Google Play Store and App Store through scraping, then processed and labeled. The study involves two classification stages: aspect identification and sentiment classification for each aspect. The stacking ensemble model without resampling showed the best performance, with F1-scores of 99.4% for UI (User Interface), 99.3% for Authentication, and 99% for Transaction. For sentiment classification, F1-scores reached 82.2% User Interface (UI), 87.8% (Authentication), and 92.4% (Transaction). The use of LIME (Local Interpretable Model-Agnostic Explanations) improved model interpretability by highlighting keywords influencing the classification results. The final output of this research is a website capable of performing aspect-based sentiment classification