Filter By Year

1945 2024


Reset

Found 25,139 documents
Search Information

 2506   2507   2508   2509   2510 
NAÏVE BAYES SENTIMENT ACCURACY WITH CHI-SQUARE AND INFORMATION GAIN Muhamad Fahrurozi; Dian Ade Kurnia; Yudhistira Arie Wijaya; Puji Pramudya Marta; Khaerul Anam
Antivirus : Jurnal Ilmiah Teknik Informatika Vol 20 No 1 (2026): Mei 2026
Publisher : Universitas Islam Balitar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35457/1nmksc45

Abstract

This study aims to evaluate the effectiveness of the Chi-Square and Information Gain feature selection techniques in improving the accuracy of sentiment classification on application reviews using the Naive Bayes algorithm. The main issue addressed in this research is the high dimensionality of features in Indonesian-language text data, which may potentially affect model performance. To address this, the study applies a text preprocessing pipeline consisting of sentiment labeling, normalization, and feature extraction using TF-IDF with an initial 5000 features. The dataset contains 225,043 Gojek application reviews, which were reduced to 220,860 valid entries after cleaning, and subsequently divided into training and testing sets using a stratified split. Experimental results show that Chi-Square achieved the highest accuracy of 0.877864 with 3000 features, while Information Gain reached an accuracy of 0.877751 with 4000 features. Both values are slightly lower than the model without feature selection, which achieved an accuracy of 0.878045. These findings indicate that feature reduction does not improve the performance of Naive Bayes, as the algorithm performs more effectively when retaining a broader distribution of words and more complete contextual representations. In conclusion, feature selection for probabilistic models should be applied cautiously, especially on Indonesian-language review data that are informal and exhibit high variation in expression.
Design and Development of a Web-Based Student Discipline Evaluation Information System Using a Research and Development Approach Hendra Parsaulian; Donny Maulana; Annisa Maulana
Journal of Information System Research (JOSH) Vol 7 No 4 (2026): July 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i4.10469

Abstract

Student discipline management is an essential component of educational administration that supports the creation of a conducive learning environment. However, disciplinary management at SMA Negeri 2 Cikarang Selatan was previously conducted manually using notebooks and spreadsheet applications, resulting in data redundancy, inaccurate calculation of violation points, delays in report generation, and difficulties in monitoring students' disciplinary records. This study aims to design and develop a Web-Based Student Discipline Evaluation Information System to improve the efficiency, accuracy, and transparency of disciplinary management. The study employed the Research and Development (R&D) approach, which consisted of needs analysis, system design, system development, implementation, and system evaluation. The proposed application was developed using PHP and MySQL and integrated several functional modules, including user authentication, student data management, violation recording, automatic point calculation, report generation, and user management. Functional evaluation was conducted using the Black-Box Testing method to verify that each module operated according to the specified requirements. The evaluation results indicated that all functional modules performed successfully without significant errors, demonstrating that the developed system satisfied the identified functional requirements. Compared with the previous manual procedure, the proposed system improved administrative efficiency, enhanced data accuracy through automated point calculation, facilitated faster report generation, and increased accessibility to disciplinary information through a centralized web-based platform. The developed system also strengthened communication among administrators, teachers, guidance counselors, and student guardians by providing accurate and timely disciplinary information. Therefore, the proposed Web-Based Student Discipline Evaluation Information System can serve as an effective digital solution for modernizing student discipline management and supporting evidence-based decision-making in educational institutions.
Employee Attendance at Getasan District Head Office Information System Governance Design Using the COBIT 2019 Framework Purcristhian Echy Candra; Melkior N. N. Sitokdana
Journal of Computer and Information Systems Ampera Vol. 6 No. 1 (2025): Journal of Computer and Information Systems Ampera
Publisher : APTIKOM SUMSEL

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The Getasan sub-district office is a community service office, especially in the Getasan area, which still uses a manual attendance system starting from employee attendance, employee home attendance and employee attendance reports. So, during the recording process, errors may occur, or reports may be less accurate and there may be delays in finding the required data. The research method used is the prototype method. This employee attendance information system is a web-based system. By using this system, the attendance information system will run better than the manual system so that it can run more effectively and efficiently and the system will also be more conducive and improved when compared to the previous system. Apart from that, the best solution is to use a computerized system that can solve the problems that exist in this office, to achieve activities that support office activities.
Design of A Service Landscape for an ICU Nursing Care Information System Based on Trauma Assessment and SBAR Using an Enterprise Architecture Planning Approach Ramandhita Aulia Wardany; Faiza Renaldi; Irma Santikarama
Jurnal Impresi Indonesia Vol. 5 No. 7 (2026): Jurnal Impresi Indonesia
Publisher : Riviera Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58344/jii.v5i7.7966

Abstract

The increasing complexity of healthcare services requires information systems capable of integrating clinical processes, data, and applications in a structured and sustainable manner. In Intensive Care Units (ICUs), fragmented documentation and limited alignment between nursing services and information systems remain challenges that may affect information accessibility and continuity of patient care. This study aimed to design a Service Landscape for an ICU nursing care information system using the Enterprise Architecture Planning (EAP) approach integrated with The Open Group Architecture Framework Architecture Development Method (TOGAF ADM) up to Phase C. This research employed a qualitative case study method conducted in the ICU of Oto Iskandar Hospital, Nata Soreang. Data were collected through observation, interviews, document analysis, and shadowing of nursing care processes. The proposed architecture was developed by identifying business services, data requirements, and application components based on Trauma Assessment and SBAR (Situation, Background, Assessment, Recommendation) information structures. The results produced five core business services, namely Admission Service, Monitoring Service, Assessment Service, Handover Service, and Transfer Service, which were mapped into Business Architecture, Data Architecture, Application Architecture, and a Service Landscape blueprint. Validation using the TOGAF Architecture Capability Maturity Model (ACMM) obtained an average score of 4.03, categorized as Level 4 (Managed). The findings indicated that the proposed Service Landscape provided consistent traceability among services, data entities, and application modules. This research concluded that the developed blueprint could serve as a conceptual reference for designing integrated and adaptable ICU nursing information systems.
Digital Layering in the Family Information System (SIGA): Evidence from the BKKBN Representative Office of Bengkulu Province Laurensius Dwi Juniansyah; Jatmiko Yogopriyatno; Abdul Aziz Zulhakim
Journal of Social and Policy Issues Volume 6, No. 2 (2026): April- June
Publisher : Pencerah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58835/jspi.v6i2.740

Abstract

This study analyzes the phenomenon of digital layering in the use of the Family Information System (Sistem Informasi Keluarga/SIGA) at Kemendukbangga/BKKBN Representative Office of Bengkulu Province, focusing on how the gradual accumulation of digital systems shapes frontline bureaucratic work. Design/methodology/approach – A descriptive qualitative design was employed; data were collected through semi-structured in-depth interviews with purposively selected informants, observation, and documentation, and analyzed thematically using three dimensions of digital layering: complexity, fragmentation, and instability.  Findings/results – SIGA operates within a stack of more than twenty digital systems and nine layered regulations. Digital layering manifests in complexity, as officials operate multiple interconnected systems simultaneously; fragmentation, as non-integrated data demand repeated entry and additional coordination; and instability, as system disruptions force officials to perform workarounds and digital repair work. Although SIGA attains full formal realization—managed in all ten districts/cities (100 percent, LAKIP 2023) with complete TI-network coverage—this uniform compliance conceals a substantial operational burden at the frontline, including server downtime, limited system literacy among field officers, and manual workarounds; the gap between formal achievement and operational reality thus reflects differences in organizational capacity to manage layered digital activities rather than technical failure. Research limitations/implications – As a single-case qualitative study, the findings are not statistically generalizable. Originality/value – This study is among the first to apply the digital layering concept to a developing-country public organization, showing that digitalization does not necessarily simplify bureaucratic work but may generate new layers of administrative burden.
Bridging Centralized Design and Local Realities: Implementation Strategies for the Family Information System (SIGA) in Bengkulu Province Rian Firnanda Irsyadani; Jatmiko Yogopriyatno; Abdul Aziz Zulhakim
Journal of Social and Policy Issues Volume 6, No. 2 (2026): April- June
Publisher : Pencerah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58835/jspi.v6i2.745

Abstract

This study examines how the Provincial Office of the National Population and Family Development Agency (Perwakilan BKKBN) of Bengkulu bridges the distance between the centrally designed Family Information System (SIGA) and the conditions under which it is actually run at the local level. Drawing on a qualitative descriptive case study, the research relied on in-depth interviews with four key informants who manage SIGA at the provincial office, supported by limited observation and documentation of official performance reports for 2023 to 2025, strategic plans, and budget records. A total of 202 coded interview units were analyzed through content analysis along the seven ITPOSMO dimensions of Heeks within the Design-Reality Gap framework. The analysis shows that the gap does not lie in the application itself but in the information and management dimensions, which together account for 57.4 percent of the coded evidence. The sharpest tension appears between the central demand for accurate, real-time, by name by address data and the uneven validation capacity, operator turnover, server instability, and limited operational budget found in the regions. Rather than redesigning the system, the office narrows this gap through tiered data verification, intensive mentoring and capacity building, and a combination of formal agreements and informal coordination. The study contributes to e-government research in Indonesia by applying the Design-Reality Gap to a vertical central-government unit running a national family data system, a setting that has rarely been studied, and by reading implementation success as a matter of organizational bridging rather than technical compliance.
Evaluating LLM-Based Institutional Information Chatbot Responses Using a Preliminary Human-Scored Analytic Rubric and Automatic Metrics Rosni Lumbantoruan; Arnaldo Marulitua Sinaga; Markus Pardianto Hutagalung; Priskila Christine Natalia Parapat; Mutiara Teccalonica Simanjuntak
Elinvo (Electronics, Informatics, and Vocational Education) Vol. 11 No. 1 (2026): May 2026
Publisher : Department of Electronic and Informatic Engineering Education, Faculty of Engineering, UNY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/elinvo.v11i1.91571

Abstract

Large language models (LLMs) are increasingly used for answering institutional information enquiries in higher education, yet the quality of responses is not straightforward to evaluate, as factual accuracy alone does not account for interactive qualities such as clarity, conversational flow, error handling and personalisation. This pilot study developed, preliminary examined a human-scored analytic rubric for assessing ChatGPT responses in a higher-education institutional-information setting and explored the alignment of selected rubric scores with reference-based automatic metrics. We designed a literature-informed rubric comprising 15 criteria across five conceptual domains. Of these, 14 criteria were operationalised through 42 rubric questions, and system usability was rated separately using the System Usability Scale. Seventy-five qualified students from one higher-education institution rated the chatbot responses using a four-point scale. Preliminary evidence at the item level was provided by item-total correlations and Cronbach’s alpha, while Pearson and Spearman correlations were used to investigate the alignment between human scores and reference-based metrics namely ROUGE-1, ROUGE-2, ROUGE-L and SacreBLEU for four content-oriented criteria. The results showed positive but partial agreement between human ratings and referenced-based metrics, with stronger agreement for clarity and up-to-date response than for accuracy and relevance. These findings suggest that reference-based metrics can complement, but not replace, human evaluation for insitutional information chatbot assessment. The study was confined to one institution and did not incorporate inter-rater reliability, expert validation or factor analysis. Thus, the rubric should be seen as a preliminary evaluation instrument rather than a fully validated scale.
Implementation of 4D Buiding Information Modelling in The Steel Structure Workflow of The Paraqouai Sao Paulo Building Lospalos Using Navisworks Manage Merci Hosang; Fardi Kalumata
Rekayasa Vol 19, No 2: May - August 2026 (In Progress)
Publisher : Universitas Trunodjoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/rekayasa.v19i2.33440

Abstract

Steel structure construction necessitates high precision in planning and execution to ensure structural stability and operational efficiency. The Paraqouai Sao Paulo building project in Lospalos presents complex geometry and tight scheduling constraints, necessitating advanced construction management techniques. This paper demonstrates the application of 4D Building Information Modeling (BIM) using Navisworks Manage to optimize the steel structure workflow. The study integrates 3D models developed in Revit with construction schedules from Microsoft Project to create a dynamic 4D simulation that adheres to Level of Development (LOD) 350 standards. The methodology focuses on visualizing the erection sequence, identifying temporal clashes, and optimizing logistics planning for crane operations. The results indicate that 4D BIM significantly enhances constructability by detecting potential spatial conflicts prior to on-site work and improving communication among stakeholders. The simulation facilitated an optimized erection sequence, reducing the estimated project duration by 15.5% (from 90 days to 76 days). This study concludes that implementing Navisworks Manage is a strategic approach for managing complex steel structures in remote areas like Lospalos, ensuring timely and cost-effective project delivery.
Flood Hazard Analysis and Adaptive Mitigation in Coastal Semarang Using a Geographic Information System Approach Alif Lombardoaji Sidiq; Muhammad Farhan Rizqi; Fredi Dwi Purnama; Pipit Skriptianata Putra Pranida
Greenation International Journal of Engineering Science Vol. 4 No. 2 (2026): (GIJES) Greenation International Journal of Engineering Science (June - August
Publisher : Greenation Research & Yayasan Global Resarch National

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38035/gijes.v4i2.1205

Abstract

The coastal area of Semarang City is divided administratively based on sub-districts of Tugu‚ West Semarang‚ East Semarang‚ North Semarang‚ and Genuk․ The area is highly vulnerable to inundation and wide-ranging flooding due to excess rainfall‚ low elevation‚ and hydrological impacts caused by reclamation activities in the city of Semarang․ The aim of this study was to spatially identify this hazard and suggest appropriate mitigation strategies‚ based on a four-factor quantitative GIS model․ The factors used were slope‚ average annual rainfall‚ land use and soil type․ The four were combined using overlay and weighting․ The resulting model revealed that 5‚364․45 hectares (66․40%) of the study area is Highly Vulnerable․ Another 33․26% (2‚687․42 hectares) was determined to be Moderately Vulnerable and 0․33% (27․07 hectares) Slightly Vulnerable․ No land was determined to be completely safe․ In light of this distribution‚ the recommendations made here are weighted towards structural measures (where risk is highest)‚ such as hardening the seawalls and normalizing the polder system․ It will lower the risk of future disasters in the long run․
A Systematic Review on Hybrid Feature Selection in Recommendation Systems: Future Perspectives for PCA and Mutual Information Integration I Wayan Dodi Putra Artawan; I Gede Aris Gunadi; I Made Gede Sunarya
Greenation International Journal of Engineering Science Vol. 4 No. 2 (2026): (GIJES) Greenation International Journal of Engineering Science (June - August
Publisher : Greenation Research & Yayasan Global Resarch National

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38035/gijes.v4i2.1207

Abstract

Recommendation systems increasingly employ hybrid learning pipelines to address data sparsity, cold-start problems, high-dimensional user-item features, and unstable preference signals. Feature selection is essential because irrelevant and redundant variables reduce prediction accuracy, increase computational cost, and limit model interpretability. Although Principal Component Analysis (PCA) and Mutual Information (MI) are widely applied for dimensionality reduction and feature relevance evaluation, their combined role in recommendation systems remains underexplored. This systematic review synthesized evidence on hybrid feature-selection approaches and the potential integration of PCA and MI in recommendation pipelines following the PRISMA 2020 guidelines. A PRISMA-based screening process identified 552 records, removed 147 duplicates, screened 405 titles and 169 abstracts, assessed 74 full-text articles, and included 30 studies for qualitative synthesis. Three dominant themes emerged: hybrid recommender models integrating collaborative and content-based filtering, hybrid feature-selection frameworks combining filter and wrapper methods, and PCA-MI pipelines for high-dimensional classification. Although direct PCA-MI applications in recommendation systems remain limited, existing evidence supports a two-stage framework in which PCA extracts stable latent representations and MI ranks features based on predictive relevance. Integrating PCA, MI, and wrapper or metaheuristic optimization offers a promising strategy to improve recommendation accuracy, scalability, and explainability across diverse application domains.

Page 2508 of 2514 | Total Record : 25139

 2506   2507   2508   2509   2510