Claim Missing Document
Check
Articles

Found 6 Documents
Search

Evaluasi Media Sosial Sebagai CRM Pada Universitas dengan Information Systems Success Model Herti Yani; Beny Beny
Jurnal Ilmiah Media Sisfo Vol 17 No 1 (2023): Jurnal Ilmiah Media Sisfo
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/mediasisfo.2023.17.1.717

Abstract

Social CRM memberikan kerangka kerja konseptual dan struktural baru yang berbasis pada Web 2.0 dan Media Sosial untuk mengarahkan kegiatan institusi pendidikan dalam menarik dan mempertahankan customer. Penelitian ini mengevaluasi pengukuran kesuksesan adopsi Social CRM pada Universitas Dinamika Bangsa dengan mengintegrasikan Critical Success Factors  dan DeLone and McLean Information System Success Model. Evaluasi kesuksesan adopsi Social CRM pada perguruan tinggi dilakukan dengan menggunakan DeLone and McLean Information Systems Success Model dengan kriteria-kriteria komponen information quality, system quality dan service quality yang dirumuskan dari pengklasifikasian terhadap critical success factors. Hasil penelitian menunjukan variabel Information Quality berpengaruh terhadap variabel Use dengan tingkat signifikansi yaitu 0.000 (<0.05), variabel System Quality berpengaruh terhadap variabel Use secara signifikan dengan tingkat signifikansi 0.030 (<0.05), variabel System Quality berpengaruh terhadap User Satisfaction tingkat signifikansi 0.000 (<0.05), variabel Service Quality berpengaruh terhadap variabel Use dengan tingkat signifikansi 0.000 (<0.05), dan variabel Use berpengaruh terhadap variabel Net Benefit dengan tingkat signifikansi 0.000 (<0.05).
Perancangan Aplikasi Pembelajaran Dasar Bahasa Jepang Berbasis Android Dengan Implementasi Algoritma Fisher-Yates Shuffle Reyca Liani Chandra; Beny Beny; Agus Nugroho
Jurnal Informatika Dan Rekayasa Komputer(JAKAKOM) Vol 3 No 1 (2023): JAKAKOM Vol 3 No 1 APRIL 2023
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (849.214 KB) | DOI: 10.33998/jakakom.2023.3.1.718

Abstract

The ability of a foreign language is a distinct advantage for an individual. One of the most popular foreign languages is Japanese. Based on a questionnaire that has been conducted to 44 respondents, 65.9% have an interest in learning Japanese for various reasons. Then 93.8% stated that the Japanese language learning media was not enough. This application contains basic Japanese material such as katakana, hiragana, kanji, and grammar material that is equipped with questions that can be done by the user. This application is made by implementing the Fisher-Yates Shuffle algorithm which is used to randomize the questions contained in this application. So that users can work on questions repeatedly.
Evaluasi Usability Aplikasi PeduliLindungi Menggunakan Metode Usability Testing dan System Usability Scale (SUS) Arine Lupita Dyayu; Beny Beny; Herti Yani
Jurnal Manajemen Teknologi Dan Sistem Informasi (JMS) Vol 3 No 1 (2023): JMS Vol 3 No 1 Maret 2023
Publisher : LPPM STIKOM Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (560.568 KB) | DOI: 10.33998/jms.2023.3.1.720

Abstract

PeduliLindungi adalah aplikasi hasil kolaborasi oleh Kementrian Komunikasi dan Informatika (KOMINFO), Kementrian Kesehatan (Kemenkes), Kementrian BUMN, Badan Nasional Penanggulangan Bencana (BNPB), dan Komite Penanganan Covid-19 dan Pemulihan Ekonomi Nasional (KPCPEN) untuk membantu instansi pemerintah terkait dalam melakukan pelacakan untuk menghentikan penyebaran Coronavirus Diseases (COVID-19). Metode yang digunakan dalam penelitian ini adalah Usability Testing dan System Usability Scale (SUS). Usability Testing merupakan pengukuran tentang seberapa mudah sistem saat digunakan dan kendala yang ditemukan saat penggunaannya untuk dapat dievaluasi dan menghasilkan data yang relevan terkait pengujian yang dilaksanakan. Sedangkan System Usability Scale (SUS) merupakan alat pengujian yang dikembangkan oleh John Brooke dengan menerapkan sepuluh pertanyaan yang memberikan pandangan global secara subjektif mengenai ketergunaan. Terdapat 4 metrik yang diukur dalam usability testing yaitu learnability, time based efficiency, error rate dan satisfaction atau hasil kuesioner system usability scale. Usability testing memiliki 6 task scenario yang diujikan kepada 5 partisipan. Hasil dari pengujian akan dianalisis secara kualitatif dan kuantitatif, pada metrik learnability didapatkan persentase sebesar 68% yang menyatakan bahwa aplikasi PeduliLindungi masih berada dibawah rata-rata dalam segi keberhasilan pengguna. Lalu, pada metrik efficiency didapatkan nilai sebesar 0,03 goals/sec dimana hanya 3% dari tugas yang dapat dilakukan dalam waktu 1 detik. Metrik error didapatkan hasil sebesar 29% atau 0,29 dimana persentase tersebut menyatakan bahwa tingkat error aplikasi PeduliLindungi berada dibawah rata-rata. Dan pada metrik satisfaction hasil rata-rata skor yang didapatkan adalah 56, dimana hasil pengujian kuesioner SUS masih berada dibawah rata-rata. Dari permasalahan yang ditemukan, terdapat 3 rekomendasi perbaikan yang disarankan.
Perencanaan Enterprise Architecture Sistem Informasi Pada Kantor Lurah Selamat Kota Jambi Menggunakan Framework Togaf-Adm Reski Febrianti Siregar; Herti Yani; Beny Beny
Jurnal Manajemen Teknologi Dan Sistem Informasi (JMS) Vol 3 No 1 (2023): JMS Vol 3 No 1 Maret 2023
Publisher : LPPM STIKOM Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (703.473 KB) | DOI: 10.33998/jms.2023.3.1.774

Abstract

Kantor Kelurahan Selamat adalah salah satu instansi dibawah pemerintah Kota Jambi berada di Kecamatan Danau Sipin Kota Jambi. Saat ini Kantor Kelurahan Selamat sudah menerapkan teknologi informasi sebagai pusat layanan informasi dengan hanya menggunakan whatsapp tetapi belum mempunyai sistem informasi yang terintegrasi pada lingkungan kantor. Pada penelitian ini bertujuan untuk merancang arsitektur enterprise pada Kantor Lurah Selamat agar dapat meningkatkan pelayanan informasi dan administrasi kepada pihak eksternal maupun internal organisasi agar terus berkembang sesuai dengan kebutuhan masyarakat dan pengurus pada Kantor Lurah Selamat. Membuat perencanaan enterprise architecture untuk menciptakan keselarasan dan efisensi antara pelayanan dan teknologi informasi bagi kebutuhan sebuah instansi dengan didukung sistem informasi yang terintegrasi berbasis enterprise architecture. Metodologi penelitian yang digunakan yaitu wawancara, observasi, studi pustaka, tinjauan pustaka, dengan menggunakan framework Togaf Adm dalam perancangan arsitektur. Hasil dari penelitian ini berupa blueprint arsitektur Sistem Informasi Kantor Lurah Selamat yang dapat dijadikan sebagai landasan untuk membangun suatu Sistem Informasi dalam menunjang kegiatan atau proses layanan yang terdapat pada Kantor Lurah Selamat Kota Jambi khususnya pada bagian pelayanan masyarakat secara umum, serta mampu menyelesaikan permasalahan sistem informasi yang masih belum terintergasi.
Comparative Analysis of Support Vector Machine and IndoBERT Algorithms in Stance Detection on Political Issues in Social Media X: A Case Study of BPI Danantara Dhammananda Taniputra; Beny Beny; Lidwina Demai Lucia; Rachel Velysha
Telematika Vol 18, No 2: August (2025)
Publisher : Universitas Amikom Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35671/telematika.v18i2.3219

Abstract

Stance detection is an NLP task aimed at identifying and classifying a writer’s attitude toward a topic as supportive, opposing, or neutral based on text analysis, providing deeper insights into public opinion and supporting data-driven decision-making. This study focuses on Indonesian society’s stance toward the National Investment Management Agency (BPI Danantara), which has received positive responses for its economic potential as well as negative reactions due to concerns over governance and corruption risks. In this research, a machine learning approach using the Support Vector Machine algorithm and a deep learning approach using the IndoBERT model were applied to detect pro, contra, and neutral stances in posts from the X social media platform. A total of 6,805 tweets were collected through scraping and manually labeled by three annotators. The dataset was then processed through cleaning, undersampling, and modeling, and evaluated using accuracy, precision, recall, F1-score, and ROC-AUC metrics. Experiments were conducted across various scenarios, including binary and three-class classification as well as balanced and imbalanced datasets, to assess the effectiveness of each model. The results indicate that IndoBERT consistently outperforms SVM across all scenarios, particularly in capturing nuanced stances in Indonesian text. However, statistical evaluation using the paired t-test and the Wilcoxon signed-rank test reveals that the performance differences between the two models are generally not statistically significant, except in the three-class classification scenario with undersampling, where IndoBERT shows a significant advantage in handling balanced multi-class stance detection. These findings demonstrate the advantage of Transformer-based approaches for complex stance detection tasks and highlight their potential for developing automated public opinion monitoring systems. Nevertheless, this study has limitations, including the relatively small dataset, the focus on a single social media platform, and the methods applied. Future research could explore larger and more diverse datasets, incorporate multiple social media platforms, and employ other Transformer-based models to enhance generalization and improve stance detection accuracy.
Heart Disease Prediction using Cost-sensitive Random Forest and SHAP Arya Chova Pratama; Eko Arip Winanto; Beny Beny
SISTEMASI Vol 15, No 9 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i9.6482

Abstract

Machine learning–based studies on heart disease prediction often report high predictive accuracy; however, most rely on relatively small and nearly balanced datasets, such as the Cleveland UCI dataset. Such datasets do not adequately reflect real-world population distributions, where class imbalance is substantial and the consequences of misclassification are asymmetric. Missing a positive case may forfeit the opportunity for early intervention, whereas a false positive can generally be resolved through subsequent clinical assessment. This study proposes a methodological evaluation framework for classifying self-reported cardiovascular risk profiles by integrating Cost-Sensitive Random Forest (CSRF) with SHapley Additive exPlanations (SHAP). The analysis uses the 2022 Behavioral Risk Factor Surveillance System (BRFSS) no_nans dataset released by the Centers for Disease Control and Prevention (CDC) and curated by Pytlak, comprising 246,022 respondents, 39 predictor variables, and a class imbalance ratio of 1:17.31. Eight model configurations were evaluated under an identical hyperparameter tuning budget, including a baseline Random Forest, cost-sensitive variants, resampling approaches, and gradient boosting models as robustness benchmarks. Model performance was assessed using cross-validation, bootstrap confidence intervals, leave-one-state-out validation, cost matrix–based threshold optimization, and calibration and fairness audits. On a test set of 49,205 respondents, the CSRF model with a 1:3 cost ratio reduced false negatives from 2,117 to 1,360, achieving a recall of 49.4% (95% CI: 47.5–51.2%) and an F1-score of 0.483. This F1-score was the highest among the Random Forest and resampling approaches, while Cost-Sensitive XGBoost and Cost-Sensitive LightGBM achieved slightly higher F1-scores, providing additional evidence of model robustness. SHAP analysis identified HadAngina and ChestScan as the most influential predictors. Because these variables are clinically closely related to the target outcome, the model's performance should be interpreted primarily as capturing cross-sectional associations derived from self-reported data rather than as a purely prospective clinical prediction model.