Journal of Information Systems and Informatics (Journal-ISI)
Not a member yet
580 research outputs found
Sort by
Indonesian Health Question Multi-Class Classification Based on Deep Learning
Get PDFThe health online forum is commonly used by Indonesian to ask questions related to diseases. A well-known example, Alodokter, has hundreds of thousands of health questions which are assigned to certain topics. Building a model to classify questions into a topic is important for better organization and faster response by relevant health professionals. This research experimented on 20 deep learning methods from RNN, CNN, and IndoBERT with different configurations to see the performance of each model when classifying questions into six different most common diseases that cause death in Indonesia. The results show the majority of the model can outperform the SVM as baseline. Bidirectional RNN such BiLSTM and BiGRU combined with CNN show a good metric score even though a certain version of the IndoBERT model generally outperforms all the other models
Evaluating the Impact of Agricultural Technology on Greenhouse Gas Emissions Using Machine Learning
Get PDFAgriculture is a significant contributor to global warming, primarily due to the release of greenhouse gases like methane (CH4) and nitrous oxide (N2O). These gases have a much higher global warming potential than carbon dioxide (CO2), necessitating targeted strategies for their reporting and reduction. This study applies machine learning models, specifically XGBoost and Support Vector Machine (SVM), to evaluate how technological advancements in agriculture influence greenhouse gas emissions. The dataset used includes emission data from various crops and farming technologies. Findings reveal that certain crops considerably elevate emissions, and in some cases, new technologies exacerbate the issue. XGBoost achieved 99.6% accuracy in predicting emission mitigation, proving its effectiveness in developing climate change mitigation plans for agriculture. Support Vector Machine also performed well, with an accuracy of 99.5%. This research underscores the need for precise approaches in managing greenhouse gas emissions through technology-driven policies
Requirements for a Technology-Supported Students’ Career Selection Model: Insights from Social Cognitive Career Theory
Get PDFInappropriate career choices at the secondary level contribute to challenges like high university dropout, delayed course completion, and frustration. While ICTs play a growing role in career guidance due to evolving technologies, many aspects of technology-supported systems remain under-researched. This study addresses the gap by investigating the requirements of a technology-supported career model for secondary school students basing on the Social Cognitive Career Theory. A mixed-methods approach was used, in line with the pragmatism paradigm. A survey was conducted on a random sample of 784 Ugandan students from 15 secondary schools and 1 university, while qualitative data was collected through interviews with 17 purposively selected key informants. SPSS and NVIVO softwares were used for data analysis. EFA and CFA confirmed the factor structure of instrument scores. Study results revealed that all the 7 variables under study were valid. Results indicate that career decisions are influenced by parental guidance, role models, financial constraints, media exposure, and self-efficacy, with students generally showing moderate confidence in their career choices but facing challenges related to external pressures and decision-making complexity. Therefore, requirements for the technology-supported model should include student personality assessment, digital internships, success stories, workshops, discussion forums and detailed information about career progression
Career Planning and Aspirations of Bangladeshi Graduates: Analyzing Quality Education and Economic Opportunities
Get PDFBangladesh is an overpopulated country with a significant portion of educated youth preparing to enter their career after graduation. Mentors, family, career councilors, and societal expectations play a significant role in shaping the future career paths of youth. To conduct the research, mixed-method approach was followed. Both quantitative and qualitative methods were accumulated, where structured questionnaires were used to collect qualitative data using simple random sampling method, and FGDs were used to collect qualitative data. The findings indicates that 29% preferred career is in the public sector, and the reasons behind it are the stability of job and reputation and social value. Based on the findings, the major challenges students face are economic downturns, work-life balance concerns, geographic constraints, fear of rejection, etc. The research recommended redesigning the courses and developing skill development programme for proper implication of policy and education system. The findings of this study will help policymakers, educators, and career counsellors determine how they can guide current fresh graduates in determining their career paths. Based on the differences in the economic characteristics of Bangladesh, these results will help graduates adopt career planning strategies more systematically
Seedling and Seed Ordering System: A PWA Prototype Implementation
Get PDFAir pollution in urban areas is a significant global challenge, and Jakarta is one of Southeast Asia's most polluted major cities. Efforts to address this problem are through the greening of urban areas. The Jakarta Special Region Seed and Plant Protection Development Center (PPBPT) is vital in providing and distributing plant seeds to the community. However, ordering manual seeds is still a significant obstacle to effective and efficient distribution. This research aims to develop a prototype application of Progressive Web Applications (PWA) based seed and seed ordering information system. Using the Extreme Programming (XP) method in this research, the PWA application provides a new perspective to accelerate the handling of urban environmental problems while providing reliable public digital services. The application development cycle with the XP method produces good software with faster turnaround time, lower costs, and responsiveness to user needs. The research results in an information system prototype application with various functions, such as user registration, identity verification, seedling ordering, stock management, and order history. The system proved to automate the seedling ordering process significantly, thus improving stock management efficiency and seedling distribution in 18 gardens under PPBPT. Indirectly, the results of this research support urban greening and contribute to improving air quality in Jakarta. Furthermore, the application can be developed by adding various forms of digital technology to help urban greening in different forms of support or other public service applications
Evaluating E-Administration Features on User Satisfaction Using the Kano Model: A Melung Village-Owned Enterprise Case Study
Get PDFThis research evaluates user satisfaction with the e-administration system at the Village-Owned Enterprises (BUMDes) Melung, focusing on identifying features that influence user satisfaction using the Kano model. A survey was conducted with 50 respondents who are active users of the system, analyzing 16 key features, including user registration, online payment, financial transparency, and service reporting. The results indicate that the Online Payment and Financial Transparency features are categorized as "Must-be," meaning these features are considered very important and must function optimally for users to remain satisfied. Meanwhile, the Tour Package Booking and Service Reporting features fall into the "One-dimensional" category, where improvements in the quality of these features directly correlate with increased user satisfaction. These findings suggest that fundamental features supporting reliability and accessibility are top priorities, while optimizing other features can further enhance overall user satisfaction. Development recommendations include improving performance on critical features to ensure a more responsive and efficient e-administration system
Enhancing Public Sector IT Governance through COBIT 2019: A Case Study on Service Continuity and Data Management in the Central Lombok
Get PDFThis study evaluates the IT governance maturity of the Central Lombok Civil Service Police Unit (Satpol PP) using the COBIT 2019 framework, focusing on improving service continuity and data security in a resource-constrained public sector context. The assessment, conducted across key domains such as service delivery, data security, and compliance, revealed that Satpol PP operates at Level 3 (Defined) maturity. While processes are documented and standardized, significant gaps remain in automation, proactive risk management, and real-time monitoring. These limitations hinder the organization's ability to optimize service continuity and safeguard sensitive data effectively. The study emphasizes the innovative application of COBIT 2019 in a resource-limited environment, demonstrating how the framework can be adapted to prioritize immediate needs while progressively advancing IT governance maturity. Key recommendations include automating monitoring systems, enhancing data security protocols, and implementing proactive risk management strategies. These findings contribute valuable insights into the challenges and solutions for IT governance in public institutions, providing a replicable model for similar organizations. Future research should explore the long-term impacts of these recommendations on IT governance maturity and service efficiency in other public sector contexts
Predictions of Criminal Tendency Through Facial Expression Using Convolutional Neural Network
Get PDFCriminal intention is a critical aspect of human interaction in the 21st-century digital age where insecurity is on the high side as a major global threat. Kidnapping, killings, molestation of all sorts, gender-based violence, terrorism, and banditry are the trends of criminality in our nation, as such, there is a need to effectively explore innovative means to identify and cope with this evil menace in our society. The facial positioning of humans can tell their evil intention even if they pretended to smile with the evil in their minds. In normal instances, it may be very difficult to predict the heart of man, but with the trending information technology like image processing, the state of a human face could be used as a means to read their tendencies. This paper proposes a deep learning model based on the FER2013 dataset through the implementation of a CNN model that predicts criminal tendencies with the help of facial expressions. With this goal in mind, we explore a new level of image processing to infer criminal tendency from facial images through a convolutional neural network (CNN) deep learning algorithm in other to discriminate between criminal and non-criminal facial images. It was observed that CNN was more consistent in learning to reach its best test accuracy of 90.6%, which contained 8 convolutional layers. To increase the accuracy of this model, several procedures were explored using Random Search from the Keras tuner library, testing out various numbers of convolutional layers and Adam optimizer. It was also noticed that applying the dissection and visualization of the convolutional layers in CNN reveals that the shape of the face, eyebrows, eyeball, pupils, nostrils, and lips are taken advantage of by CNN to classify the images
Analysis and Design of Marine Tourism Information System Using Rapid Application Development
Get PDFThe research addresses the growing need for efficient management of marine tourism activities in Indonesia, explicitly diving, snorkeling, and fishing. With the rapid expansion of marine tourism, there is a pressing need for innovative solutions to streamline information dissemination and enhance tourist experiences. This study proposes the development of a database and information system utilizing the Rapid Application Development (RAD) methodology to cater to the diverse needs of tourists engaging in marine activities. The Rapid Application Development approach comprises requirement planning, user design, construction, and cutover phases. Oracle Apex serves as the primary instrument for database design and system development. The findings suggest that implementing digital innovation in the form of information systems and databases significantly enhances the tourist experience in marine tourism destinations. Integrating GIS technology enables the visualization of location maps and valuable information, enriching the user experience and facilitating informed decision-making processes. Test results indicate that the application functions optimally and can be utilized effectively for destination management in Indonesia, emphasizing the practical implications of digital innovation in the tourism sector. In conclusion, designing and implementing a database and information system for marine tourism activities offer substantial benefits for destination management and tourist experiences in Indonesia. This research underscores the importance of technological advancements in optimizing destination management and fostering sustainable tourism development in coastal regions
Sentiment Analysis of Unemployment in Indonesia During and Post COVID-19 on X (Twitter) Using Naïve Bayes and Support Vector Machine
Get PDFThe COVID-19 pandemic has impacted health, economy, and society. Social distancing measures and quarantine policies have restricted economic activities, leading to downturns in COVID-19-affected regions and a subsequent rise in unemployment rates, particularly in urban areas. Concurrently, there has been a remarkable surge in the utilization of the X (Twitter) platform, with Indonesia ranking 6th globally in X (Twitter) users. This study aims to understand the diverse perspectives of society on unemployment and the factors influencing society's views on unemployment through sentiment analysis of X (Twitter) data. By analyzing 576,764 tweets from April 2020 to October 2023, tweets are categorized into positive, neutral, and negative classes. Classification model was built to classify tweet data by implementing TF-IDF for word weighting, and a pair of machine learning algorithms, Naïve Bayes and Support Vector Machine (SVM). Model evaluation yielded the highest accuracy of 81.5% using Naïve Bayes. The classification outcomes highlight prevalent negative perceptions of unemployment among Indonesians, totaling 50.03%. This research contributes to the literature by providing a large-scale analysis of social media data to uncover public sentiment trends and offering insights for policymakers to address unemployment and improve welfare