Article Per Year (5 Year)
p-Index From 2021 - 2026
1.671
P-Index
This Author published in this journals
All Journal Jurnal Simetris Sistemasi: Jurnal Sistem Informasi Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) JITK (Jurnal Ilmu Pengetahuan dan Komputer) International Journal of New Media Technology JITTER (Jurnal Ilmiah Teknologi Informasi Terapan) ILKOM Jurnal Ilmiah Jurnal Manajemen Informatika Al-MIKRAJ: Jurnal studi Islam dan Humaniora Journal of Computing Theories and Applications Integrated System and Management Technology Computer Architecture and Signal Processing Big Data Analytics and Data Science Cyber Security and Network Management
Agus Nursikuwagus
Universitas Komputer Indonesia
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mechanical Engineering Social Sciences

Published : 18 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 18 Documents
Search

 1   2 
SUPPORT VECTOR MACHINE TO CLASSIFY SENTIMENT REVIEWS ON GOOGLE PLAY STORE Agus Nursikuwagus; Suherman; Heri Purwanto; Tono Hartono
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 3 (2026): JITK Issue February 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i3.7282

Abstract

This research addresses the "rating-content discrepancy" on the Google Play Store, where numerical star ratings often conflict with the actual sentiment of textual reviews. Utilizing the CRISP-DM   framework, the study evaluates the effectiveness of machine learning in resolving these inconsistencies by classifying Instagram user reviews into positive and negative categories. Two primary algorithms were compared using a dataset of 600 reviews. The Support Vector Machine (SVM) model demonstrated high efficacy with an accuracy of 0.84. In contrast, the K-Nearest Neighbors (KNN) model performed poorly, achieving an accuracy of only 0.48. This significant performance gap highlights SVM's superior ability to handle high-dimensional text data through optimal hyperplane separation. The research further integrated the Streamlit library to create an interactive web interface for real-time sentiment prediction and result visualization. Ultimately, this study confirms that a structured CRISP-DM approach combined with SVM provides a robust solution for automated opinion mining, offering a reliable methodology for future data science applications in social media analysis
Open Government Data Analytics of Tourist Visits In West Java 2014–2024: A Data Science and Philosophy of Science Perspective Ucu Nugraha; Hernalom Sitorus; Sri Titi Handayani; Agus Nursikuwagus; Usep Mohamad Ishaq; Andrias Darmayadi
Sistemasi: Jurnal Sistem Informasi Vol 15, No 4 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i4.6175

Abstract

Open Government Data (OGD) in tourism provides opportunities for data-driven analytics to support destination management policies. In policy practice, tourism OGD is often accepted at face value as a direct representation of real-world conditions, even though such data are constructed through definitions, recording procedures, and measurement choices. Therefore, a philosophy of science perspective is essential in data governance. This article analyzes an Open Data Jabar dataset on the number of tourist visits by visitor type and district/city in West Java Province for the period 2014–2024 (n = 565; 27 districts/cities; two visitor categories: domestic and international). The data science approach includes data quality auditing (completeness and consistency), time-series aggregation, spatial concentration measurement using the Gini coefficient, and a comparison of shock–recovery patterns in tourist visits before and after the pandemic. The results indicate a decline in total visits of -50.6% in 2020 compared to 2019, with international visits experiencing the sharpest drop (-82.8%). By 2024, total visits reached 64,517,298, dominated by domestic tourists (63,963,443; international share 0.9%). Spatial concentration in 2024 is reflected by a Gini coefficient of 0.429, with the top five regions accounting for 44.2% of total visits. The discussion emphasizes that visitor counts are epistemic representations shaped by definitions, reporting practices, and data cleaning processes. Therefore, policy recommendations should be accompanied by data provenance, metadata, and explicit uncertainty annotations to avoid the reification of indicators.
Epistemologi Artificial Intelligence: Kebenaran, Validitas, dan Otoritas Algoritmik Sri Nurhayati; Diana Effendi; Agus Nursikuwagus; Usep Mohamad Ishaq; Andrias Darmayadi
AL-MIKRAJ Jurnal Studi Islam dan Humaniora (E-ISSN 2745-4584) Vol. 6 No. 1: Al-Mikraj, Jurnal Studi Islam dan Humaniora
Publisher : Pascasarjana Institut Agama Islam Sunan Giri Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37680/almikraj.v6i1.8530

Abstract

The development of artificial intelligence (AI) has brought fundamental changes in the way knowledge is produced, validated, and accepted in various sectors of life. Algorithmic models, especially deep learning, generate predictions and recommendations that are often treated as operational truths even though the inference process is not fully explainable. This study analyzes how AI changes the understanding of truth, validity, and epistemic authority from the perspective of the philosophy of science, and links it to the ontological and axiological dimensions in modern knowledge production. A qualitative approach based on philosophical analysis is used to integrate the thoughts of Popper, Kuhn, Lakatos, Van Fraassen, and Floridi. The results show that AI shifts knowledge from rational justification to performative and statistical validity, and challenges the position of humans as the primary epistemic agents. This study asserts that the epistemic transformation triggered by AI requires ontological and axiological reflection so that the development of knowledge remains in line with humanitarian principles and ethical responsibility
Epistomologi Sains di Era Kecerdasan Buatan: Menimbang Kebenaran Prediktif Popon Dauni; Rizal Rachman; Sri Erina Damayanti; Agus Nursikuwagus; Usep Mohamad Ishaq; Andrias Darmayadi
AL-MIKRAJ Jurnal Studi Islam dan Humaniora (E-ISSN 2745-4584) Vol. 6 No. 1: Al-Mikraj, Jurnal Studi Islam dan Humaniora
Publisher : Pascasarjana Institut Agama Islam Sunan Giri Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37680/almikraj.v6i1.8879

Abstract

The development of artificial intelligence (AI), particularly machine learning and deep learning, has brought significant changes to contemporary scientific practices. AI no longer functions solely as a computational tool, but plays an active role in the production, validation, and evaluation of scientific knowledge through data modelling and probabilistic inference. This development raises fundamental questions in the philosophy of science, particularly regarding the shift in the concept of scientific truth from the paradigm of empirical verification and causal explanation towards an approach based on prediction, mathematical approximation, and the management of uncertainty. This research aims to re-evaluate the status of scientific truth in the age of AI by philosophically analysing the relationship between uncertainty, computational knowledge, and scientific truth claims generated by AI models. The research method used is a qualitative study based on literature review and conceptual analysis of contemporary science and technology philosophy literature. The study results indicate that the integration of AI into scientific practice is driving a shift in the epistemology of science from a verifiative orientation towards a predictive epistemology that emphasises model reliability and instrumental validity. This research concludes that scientific truth in the AI era is more contextual and pragmatic, thus demanding an adaptive, reflective, and interdisciplinary framework for the epistemology of science. Theoretically, scientific truth in the age of artificial intelligence is more contextual, thus requiring an adaptive, reflective, and interdisciplinary framework for the epistemology of science as its main theoretical contribution.
Integrated and Spatiotemporal Predictive Data-Driven Narcotics Intelligence Ecosystem: Governance, Interoperability, and Analytics Pipeline for Evidence-Based Policy : Case Study: BNNP West Java, Indonesia Luki Ishwara; Agus Nursikuwagus; Ednawati Rainarli; Zainal Arifin Hasibuan; Sri Supatmi
Integrated System and Management Technology Vol. 1 No. 2 (2026): July: Integrated System and Management Technology
Publisher : Asosiasi Pengelola Jurnal Informatika dan Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66472/ismat.v1i2.436

Abstract

Across BNN, police, health, corrections, and local government, Indonesia's crossagen cynarcotics control produces a lot of data yet fragmented, limiting timely identification of abuse patterns,hotspots, and resource requirements. It aims to bridge the gap between international breakthroughson the use of machine-learning–based monitoring and optimization under uncertainty and underdeveloped provincial integration of governance, interoperability, and predictive analytics in the public sector. It is about designing and assessing an integrated spatiotemporal predictive, datadriven narcotics intelligence ecosystem for BNNP West Java. The approach combines iterative information systems engineering with an embedded case study and a mixed-methods evaluation covering seven phases: requirements structuring; data governance and quality; federated/hybrid interoperability and Privacy-Preserving Record Linkage; spatiotemporal predictive pipelines with both baseline and advanced models and anomaly detection; hotspot and risk mapping; early warning and situational dashboards linked to operational protocols; and implementation assessment with institutional learning.Evaluation utilizes quantitative measurements for data quality and model performance (including lead time and false-alarm considerations) and qualitative findings evaluating governance readiness and usability. Expected outputs can comprise a four-pillar framework bridging governance and policy impact, replicable artefacts to be deployed at the provincial level, and implications for evidence-based narcotics policy under national digital-government agendas, with considerations for data-access andprivacy limitations.
Data-Driven Learning Analytics Conceptual Framework for Automated Competency Mapping in Outcome-Based Education: A Design Science Research Approach Hasbu Naim Syaddad; Zainal Arifin Hasibuan; Bobi Kurniawan S; Sri Supatmi; Agus Nursikuwagus; Citra Noviyasari
Computer Architecture and Signal Processing Vol. 1 No. 2 (2026): June: Computer Architecture and Signal Processing
Publisher : Asosiasi Pengelola Jurnal Informatika dan Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66472/casp.v1i2.396

Abstract

The implementation of Outcome-Based Education (OBE) in higher education demands precise measurement of Graduate Learning Outcomes (CPL) and Course Learning Outcomes (CPMK). However, current conventional Learning Management Systems (LMS) remain static and centered on final performance metrics (grades), thus failing to map student academic profiles into sub-competencies in a real-time and granular manner. This study proposes a conceptual artifact in the form of an Intelligent Tutoring System (ITS) architecture based on Learning Analytics (LA) and Knowledge Graphs to automate competency mapping. Through the Design Science Research Methodology (DSRM) approach, this framework designs a data fusion pipeline that integrates high-resolution academic log data with curriculum ontologies. The proposed architecture consists of three main layers: data acquisition, predictive modeling using Machine Learning, and a recommendation engine based on Explainable AI (XAI). This conceptual framework provides a blueprint for higher education institutions to transform from reactive curriculum evaluation into precise and auditable adaptive learning governance.
Classification, Prediction, and Prescription of Digital Government Governance Maturity Levels: Leveraging SPBE Index Data (2019–2024) for Evidence-Based Regional Digital Government Architecture Planning in Indonesia Andi Agus Salim; Zainal Arifin Hasibuan; Agus Nursikuwagus; Sri Supatmi
Big Data Analytics and Data Science Vol. 1 No. 2 (2026): June: Big Data Analytics and Data Science
Publisher : Asosiasi Pengelola Jurnal Informatika dan Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66472/bdas.v1i2.409

Abstract

Indonesia's transition from the SPBE evaluation framework to the 2025–2029 Pemdi (Digital Government) Index marks a strategic shift toward comprehensive governance maturity. However, regional governments face significant challenges in strategic planning due to the absence of empirical models linking historical SPBE performance to future Pemdi trajectories and a lack of data-driven guidance for prioritizing governance interventions. This research aims to develop an integrated Classification-Prediction-Prescription (CPP) framework to classify, forecast, and prescribe regional digital government governance maturity levels. The proposed methodology employs machine learning algorithms (Random Forest and Gradient Boosting) to conduct multi-class classification (five maturity levels) and regression (continuous score prediction) using longitudinal SPBE data (2019–2024) from 548 Indonesian regional governments. This quantitative approach is complemented by feature importance analysis and scenario-based simulations to generate actionable insights. The models are projected to achieve over 85% classification accuracy and a regression RMSE of under 0.5. The synthesis of main findings reveals that indicators within the policy and architecture planning domains are the strongest predictors driving maturity progression. Furthermore, the study segments regional governments into four distinct trajectory clusters and formulates a tailored prescriptive recommendation matrix across multiple planning horizons. In conclusion, the CPP framework effectively translates national evaluation data into actionable intelligence, empowering regional governments to optimize resource allocation, prioritize high-impact interventions, and systematically align their digital transformation pathways with formal planning documents such as the RPJMD and Regional Action Plans.
Predictive decision support for underutilization risk in public sector tourism: Evidence mapping and a design science roadmap Ucu Nugraha; Zainal Arifin Hasibuan; Bobi Kurniawan S; Sri Supatmi; Agus Nursikuwagus; Citra Noviyasari
Cyber Security and Network Management Vol. 1 No. 2 (2026): May: Cyber Security and Network Management
Publisher : Asosiasi Pengelola Jurnal Informatika dan Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66472/cybernet.v1i2.440

Abstract

Publicly funded tourism assets can become stranded when utilization persistently falls below a reasonable level relative to capacity or policy-defined potential. Yet tourism analytics research largely forecasts demand or composite performance and seldom formalizes underutilization as a governance outcome, nor evaluates decision quality within planning and budgeting workflows. This study (i) maps recent evidence and research gaps and (ii) proposes a conceptual artefact in the form of a policy-ready methodology and roadmap for developing a predictive decision support system (DSS) to mitigate underutilization risk. An evidence-mapping review of 117 Scopus-indexed studies (2021–2026) reveals a critical gap: 0% of the analyzed studies explicitly formalize "underutilization" as a policy outcome in their titles. Furthermore, evaluation procedures remain opaque, with 79.5% of studies failing to clearly specify their methodologies. In response, we outline a design-science roadmap for an auditable predictive DSS that operationalizes underutilization through two complementary metrics: the Underutilization Gap (UG) and the Utilization Ratio (UR). The proposed architecture integrates heterogeneous tourism, spatial, and socio economic data while providing traceable audit trails via Explainable AI (XAI) to ensure scores are logically defensible in public budgeting. Crucially, the framework introduces a two-layer evaluation that couples technical predictive performance (E1) with decision-utility metrics (E2), such as rank agreement and allocation efficiency. This methodology equips local governments with a practical, theoretically grounded instrument to justify prioritization, optimize resource allocation, and reduce the likelihood of underutilization-related policy failure.
Co-Authors Ahmad Sugiyarta Andi Agus Salim Andrias Darmayadi Bobi Kurniawan S Citra Noviyasari Diana Effendi Ednawati Rainarli Fahmi Reza Ferdiansyah Hasbu Naim Syaddad Heri Purwanto Heri Purwanto Hernalom Sitorus Indah Komala Irsyad Djamaludin Iskandar Ikbal Luki Ishwara Masayu Leylia Khodra Myrna Dwi Rahmatya Popon Dauni Qidir Maulana Binu Soesanto R Rizal Isnanto Rinaldi Munir Rizal Rachman Sri Erina Damayanti Sri Nurhayati Sri Supatmi Sri Titi Handayani Suherman Suherman Suherman Syahrul Mauluddin Syahrul Mauluddin Tono Hartono Ucu Nugraha Usep Mohamad Ishaq Zainal Arifin Hasibuan