Journal of Information Systems and Informatics (Journal-ISI)
Not a member yet
580 research outputs found
Sort by
Social Media Management System for Educational Promotion
Full text linkEducational institutions, particularly tourism study programs, face significant challenges in managing fragmented and inefficient social media promotion strategies that hinder student recruitment and weaken institutional visibility. These problems arise from inconsistent content delivery, lack of stakeholder coordination, and limited performance monitoring and analytics capacity. To address these challenges, this research employs the Rapid Application Development (RAD) methodology through four stages: Requirements Planning, User Design, Construction, and Cutover. The requirement planning phase involved gathering aspirations from all stakeholders within the study program to ensure alignment in designing creative and effective promotional content. The resulting system integrates automated content workflows, scheduling algorithms, demographic-based audience targeting, and real-time performance analytics. The findings indicate substantial improvements in resource efficiency, precision of outreach, enrollment conversion rates, and institutional branding consistency. This research provides a comprehensive framework for transforming academic promotional practices through digital system integration, specifically tailored to the operational needs of educational institutions
Analysis of Community Sentiment Towards Free Nutrition Meal Programs on Twitter Using Naïve Bayes, Support Vector Machine, K-Nearest Neighbors, and Ensemble Methods
Full text linkMeal program free nutritious food that was planned government reap diverse response from society, especially on social media like Twitter. Research This aiming for analyze sentiment public to the program with utilize text mining and machine learning techniques. Data of 1500 tweets was collected through the scraping process using Python. The sentiment in the tweets is classified into three categories: positive, negative, and neutral. In this study, four classification algorithms were used: Naïve Bayes, Support Vector Machine (SVM), K-Nearest Neighbors (K-NN), and ensemble, to compare their performance in sentiment analysis. Additionally, a text weighting method, TF-IDF, was tested to examine its impact on classification accuracy. The analysis results show that the Support Vector Machine (SVM) algorithm, when combined with the TF-IDF weighting method, provides the highest accuracy of 95.05%. Other algorithms also showed varied performance, with Ensemble achieving 86.57%, K-Nearest Neighbors 77.03%, and Naïve Bayes 60.42% accuracy. It is expected from results study This can give description general to perception public about the meal program free nutritious a
Measuring Tiktok Shop Service Quality Using The E-ServQual Method And Importance Performance Analysis (IPA) Method
Full text linkUtilizing online shop services is an example of applying technology that aims to increase product sales, one of which is TikTok Shop. This research aims to measure the quality of service provided by TikTok Shop in order to offer appropriate recommendations for improving service features and other aspects. The method used is e-servqual, which includes variables such as efficiency, compliance, reliability, privacy, responsiveness, compensation, and contact which are used to identify service quality factors that require repair, maintenance, or improvement. The Importance Performance Analysis (IPA) method is used to assess the performance of services provided to consumers compared to desired expectations. The results of measurement research using the e-ServQual method show a satisfaction index of 0.925274, which means TikTok Shop users are very satisfied, because the service quality score is close to 1. Measurements using the IPA method reveal three attributes that require performance improvement. These three attributes have the highest priority for improved to increase user satisfaction. Additionally, seven attributes can be retained because their performance exceeds the user's importance level. It is hoped that the results of this research can provide valuable contributions or insights for relevant stakeholders
Integration of Hash Encoding Technique with Machine Learning for Employee Turnover Prediction
Full text linkEmployee turnover refers to the replacement of employees within an organization, which can lead to losses such as recruitment costs and decreased productivity. Predicting turnover is crucial for companies to anticipate and take appropriate actions to retain potential employees. This study aims to optimize the employee turnover prediction model by integrating hash encoding techniques and machine learning. The dataset used in this study is an open-source dataset obtained from Kaggle dataset. It consists of 14,994 rows and 10 columns (features) representing employee-related information such as satisfaction level, evaluation score, number of projects, average monthly hours, and whether the employee left the company. Among these features, some are of object data type. Since machine learning algorithms generally cannot work directly with object-type features, the use of hash encoding is proposed. This technique converts object-type data into numerical data. It is part of the preprocessing stage, aiming to reduce memory usage, speed up data preprocessing, and improve model performance. After preprocessing is completed, the prediction model is trained using the Random Forest algorithm to predict employee turnover. The evaluation is conducted using accuracy, recall, precision, and F1-score metrics, which yielded results of 0.988, 0.961, 0.988, and 0.974, respectively. These results indicate that the integration of hash encoding techniques and machine learning can produce a well-performing model for predicting employee turnover
Gender Motivations for TikTok Content Creation: A Comparative Study of Male and Female Students’ University Students
Full text linkTikTok has rapidly become a leading platform for youth self-expression and digital participation, yet little is known about how gender influences motivations for content creation. This study explores gender-based differences among South African university students, addressing a key gap in the literature. Using a mixed-methods design, 100 students (50 male, 50 female) were surveyed and focus groups with 25 participants were conducted to examine content types and motivational drivers, over a three-month period. Findings reveal clear distinctions: female students are primarily motivated by self-expression, social connection, and stress relief, favoring fashion, lifestyle, and dance content. Male students, by contrast, focus on entertainment, follower growth, and raising awareness, often creating comedy and educational videos. These patterns reflect broader social norms and platform dynamics, emphasizing different gratifications by gender. The study is guided by the Uses and Gratifications Theory in understanding these gendered motivations is essential for fostering more inclusive and responsive social media environments. It offers practical insights for educators designing digital literacy interventions, as well as for platform developers aiming to enhance inclusivity and user engagement
Customer Continuance Usage of Digital Banking: A Systematic Review of Influencing Factors
Full text linkCustomer loyalty plays a crucial role in sustaining banking revenue and long-term growth. This study presents a systematic review that aims to provide insights for future studies about the trends of digital banking continuance usage intention. Using Population-Intervention-Comparison-Outcome-Time-Question (PICOTQ) Framework, this research focuses on journal articles published between 2020 and 2025, written in English, featuring a conceptualized research model, and published in peer-reviewed journals. Twenty-nine relevant articles were selected. The Preferred Reporting Items for Systematic Review (PRISMA) Framework guided the review process, revealing 56 variables used in related models. Among these, satisfaction, privacy and security, user experience, ease of use, and customer service and support were the most frequently significant factors influencing continuance usage. Most studies were conducted in Indonesia, India, and Korea, reflecting a variety of country income levels. The findings confirm that digital banking continuance usage intention remains a promising and prospective area for future investigation. Further exploration using diverse moderating variables and alternative analytical methods is encouraged to enrich understanding. Practically, this research offers valuable insights for digital banking stakeholders to strengthen customer loyalty by improving service quality, particularly by enhancing user satisfaction, strengthening data privacy and security, improving interface usability, and delivering responsive customer support
Mapping the Global ICT Research Trends in the Construction Sector
Full text linkInformation and communication technology (ICT) has not been widely adopted in the construction sector, despite its promise to improve productivity, safety, communication, efficiency, and sustainability. Prior research has made clear that further research and development in this field are required to improve its application for project delivery and organisational performance, particularly in developing countries. To determine the area of focus of earlier studies, this paper reviewed ICT in fields relevant to construction. Utilising a bibliometric methodology, the data for this study were taken from the Scopus database. Keyword searches were used to search the database, such as “Information communication technology/technologies”, “Information communication”, “Communication technology”, and “Construction or Construction industry”, to obtain pertinent papers. The papers analysed were 96 in number from 2014-2024. Using VOSviewer, a network and overlay visualisation map of the co-occurrence keywords was produced based on the gathered bibliographic data. The findings indicated that earlier research in ICT gave priority to information and data management, project design, sustainable project management, power transmission and smart grids, construction project communication, and safety management and training. Furthermore, research in this area is currently concentrating on big data applications, smart city applications, and sustainable development applications. The results highlight a knowledge vacuum in which South American and African nations might investigate to enhance construction project delivery and organisational performance. This work adds to the conversation around ICT, which has not gotten much attention in recent scientometric and bibliometric research
Enhancing Hate Speech Detection: Leveraging Emoji Preprocessing with BI-LSTM Model
Full text linkMicroblogging platforms like Twitter enable users to rapidly share opinions, information, and viewpoints. However, the vast volume of daily user-generated content poses challenges in ensuring the platform remains safe and inclusive. One key concern is the prevalence of hate speech, which must be addressed to foster a respectful and open environment. This study explores the effectiveness of the Emoji Description Method (EMJ DESC), which enhances tweet classification by converting emojis into descriptive text or sentences. These descriptions are then encoded into numerical vector matrices that capture the meaning and emotional tone of each emoji. Integrated into a basic text classification model, these vectors help improve detection performance. The research examines how different emoji preprocessing strategies affect the performance of a BI-LSTM model for hate speech classification. Results show that removing emojis significantly reduces accuracy (68%) and weakens the model’s ability to distinguish between hate and non-hate speech, due to the loss of valuable semantic context. In contrast, retaining emoji semantics either through textual descriptions or embeddings boosts classification accuracy to 93% and 94%, respectively. The highest performance is achieved through emoji embedding, highlighting its ability to capture subtle non-verbal cues critically for accurate hate speech detection. Overall, the findings emphasize the importance of incorporating emoji-aware preprocessing techniques to enhance the effectiveness of social media content classification
Enhancing Hazard Detection and Risk Severity Assessment in Construction through Multinomial Naive Bayes and Regression
Full text linkThis research delves into the crucial area of hazard detection and risk severity assessment within the construction industry, using machine learning techniques. The dataset utilized is from the Chinese Construction Company (CCECC), Uyo, Nigeria. Comprising over 100,000 instances, it captures various hazard categories prevalent in construction sites, providing a comprehensive foundation for predictive analysis. In the first phase of the study, the system is designed to detect hazards present in construction sites. Leveraging these data, the machine learning models are trained to predict potential hazards based on the information provided. Through TF-IDF vectorization, a feature extraction technique, the textual data is transformed into numerical representations. Multinomial Naive Bayes is employed for hazard classification due to its efficacy in handling text data, and with it, an accuracy of 0.99 was obtained. Subsequently, the trained model was evaluated to assess its performance and the severity of identified hazards are evaluated. The system quantifies the potential risk posed by each hazard using the risk severity attribute. Using the Linear Regression algorithm, the model predicts the severity of risks based on textual descriptions of a hazard. In practical application, the research stresses the significance of risk management strategies in the construction industry to mitigate potential harm to personnel and infrastructure. This research contributes to advancing safety protocols within the construction sector, advocating for a culture of vigilance and precaution to address risks effectively
Revolutionizing Nursing and Midwifery Informatics Curriculum Evaluation in Ghana: A Data-Driven Machine Learning Approach
Full text linkThe field of Nursing and Midwifery Informatics (NMI) aims to equip healthcare professionals with the skills to efficiently use emerging technologies in their practice. This research assessed NMI educational programs in Ghana using machine learning techniques to analyze key factors influencing student performance, engagement, and satisfaction. Data was gathered from 1,500 students across C.K. Tedam University of Technology and Applied Sciences, Bolgatanga Nursing and Midwifery Training College, Regentropfen University College, Tamale Nursing and Midwifery Training College, and University for Development Studies. The study employed Random Forest, Gradient Boosting, Support Vector Machine, K-Nearest Neighbor, and Logistic Regression algorithms, evaluated using standard performance metrics, including accuracy, precision, and recall. The Gradient Boosting model achieved the highest predictive accuracy at 95%, identifying student engagement and curriculum satisfaction as the most influential predictors of academic success. Additionally, multiple regression analysis revealed that institutional differences significantly influenced academic outcomes, with students at Tamale Nursing and Midwifery Training College outperforming their counterparts at C.K. Tedam University of Technology and Applied Sciences (β = 3.85, p = 0.021), likely due to better alignment between their curriculum and instructional methods. These findings offer actionable insights for curriculum development and healthcare policy planning in resource-constrained settings, advocating for the integration of machine learning tools into academic evaluations. The study presents a scalable predictive model that can be adapted to enhance digital health education in similar low-resource settings worldwide, offering a pathway to more effective and inclusive healthcare education systems