International Journal of artificial intelligence research (IJAIR)
Not a member yet
271 research outputs found
Sort by
Data-Driven Insights Into Underdeveloped Regencies: SHAP-Based Explainable Artificial Intelligence Approach
Full text linkClassification analysis in high-dimensional data presents significant challenges, particularly due to the presence of complex non-linear patterns that traditional methods, such as logistic regression, fail to capture effectively. This limitation is often reflected in relatively low model accuracy. One approach to addressing this issue is through machine learning-based classification methods, such as Random Forest and Support Vector Machine (SVM). While these models generally achieve higher accuracy than logistic regression, their black-box nature limits interpretability, making it difficult to explain their classification decisions. As machine learning models continue to advance, interpretability has become a crucial concern, especially in data-driven decision-making. Post-hoc explainable artificial intelligence (XAI) techniques offer a viable solution to enhance model transparency. This study applies SHAP to machine learning models to gain insights into the underdevelopment status of regencies in Indonesia. The results indicate that SVM outperforms both logistic regression and Random Forest. SHAP values estimated from SVM, using various permuted variable subsets, exhibit stability. Clustering analysis identifies five optimal clusters of underdeveloped regencies. Based on average SHAP values, underdevelopment alleviation strategies should focus on social factors (Cluster 1), infrastructure (Cluster 2), accessibility (Cluster 3), and a combination of infrastructure, accessibility, education, and healthcare (Cluster 4), while Cluster 5 requires improvements in accessibility and economic conditions
The Influence of Organizational Culture, Self-Confidence, and Gender on Employee Performance with Employee Involvement as a Mediator
Full text linkThis study investigates the impact of organizational culture, self-confidence, and gender on employee performance, with employee engagement serving as a mediating variable. The research employs a quantitative approach, collecting data through questionnaires distributed to employees of financing companies registered with the Financial Services Authority (OJK) in Purwakarta Regency, resulting in a sample of 257 respondents. Path analysis is used to examine the direct and indirect relationships between variables. The findings reveal that organizational culture has a significant positive impact on both employee performance and employee engagement. A robust organizational culture fosters a supportive work environment, enhancing motivation, a sense of community, and engagement through effective communication and shared positive values. Self-confidence also positively influences employee performance; however, it does not directly affect employee engagement, highlighting the role of other factors like organizational culture and workplace relationships. Gender positively impacts both performance and engagement, showcasing the benefits of diverse perspectives, collaboration, and inclusivity in the workplace. Furthermore, employee engagement significantly enhances employee performance, as emotionally and professionally engaged employees tend to perform at higher levels. As a mediating variable, employee engagement strengthens the influence of organizational culture, self-confidence, and gender on employee performance, underscoring the critical role of fostering diversity, motivation, and workplace support to drive better outcomes
An Evaluation of SMOTE Effectiveness in Handling Class Imbalance in Public Opinion Data on the MBG Program
Full text linkThe “Makan Bergizi Gratis” (MBG) Program is one of the strategic policies of the Government of Indonesia that reaps various opinions from the public, especially through social media. This study aims to classify public sentiment towards the MBG program with an ensemble learning-based machine learning approach, as well as evaluate the effectiveness of the SMOTE algorithm in dealing with class imbalance in opinion data. The dataset was collected from platform X (formerly Twitter) for the January–April 2025 period, totaling 4,374 tweets with label distributions: 1,783 positive, 1,634 negative, and 957 neutral. The preprocessing process includes data cleansing, normalization, stemming, and vectorization with TF-IDF. Five ensemble algorithms were used, namely Random Forest, AdaBoost, Bagging, Stacking, and Voting, tested in two scenarios: with and without the implementation of SMOTE. The results of the experiments showed that Random Forest provided the best and most consistent performance, with the F1-score increasing from 72.03% to 72.66% after the implementation of SMOTE. However, not all models benefit from SMOTE, such as Voting which experienced a drop in F1-score. These findings suggest that SMOTE is effective in increasing the sensitivity of the model to minority classes, but its success depends on the characteristics of the algorithm used. This study suggests the selective selection of balancing methods as well as the development of a more adaptive approach to handle unstructured opinion data
The Philosophy of Nias Megalithic Stones for Catholic Youth in Gunungsitoli
No full textThis study examines the philosophy of the Nias megalithic stones and their relevance for Catholic Youth (OMK) in the city of Gunungsitoli through a qualitative-ethnographic approach. Data were collected through in-depth interviews with traditional elders, community leaders, and Catholic youth; participatory observation in customary activities and religious devotions; as well as archival documentation, photographs, and field notes. Thematic analysis identified three clusters of values: resilience (perseverance, discipline, hope), community (mutual cooperation, deliberation, communio), and spirituality (awareness of Christ’s presence in cultural history). The findings show that megalithic stones continue to function as cultural archives, centers of social interaction, and pedagogical symbols for the character formation of Catholic youth. Within the framework of inculturation, these values are reinterpreted in catechesis, culturally rooted liturgy, and social action, without contradicting the Church’s teaching. The study concludes that faith-culture integration strengthens the dual identity of Catholic youth and encourages their role as agents of change in preserving the megalithic heritage and in pastoral ministry. Recommendations include digital documentation of sites, culturally based youth training, and ongoing collaboration between parishes, schools, and traditional leaders in the region
Sentiment Analysis And Topic Extraction Related To The 2024 Indonesian Presidential And Vice Presisdential Election Using Deep Learning Methods
Full text linkThis research examines public sentiment and discourse surrounding the 2024 Indonesian Presidential and Vice Presidential Election through analysis of YouTube comments. Using a combination of deep learning techniques, specifically Long Short-Term Memory (LSTM) networks for sentiment analysis and Latent Dirichlet Allocation (LDA) for topic extraction, we analyzed public responses to the three presidential candidates. The LSTM model achieved varying accuracy rates across candidates: 58% for Anies Baswedan, 61% for Prabowo Subianto, and 71% for Ganjar Pranowo, with consistently high recall rates of 100% across all candidates. Topic extraction through LDA revealed distinct themes in public discourse, including leadership qualities, policy implementations, and campaign promises. The research methodology involved web scraping YouTube comments from January to October 2023, followed by comprehensive text preprocessing and analysis. Our findings provide valuable insights into public opinion dynamics and key discussion topics during the election period, contributing to the understanding of social media's role in Indonesian political discourse. This study demonstrates the effectiveness of combining deep learning approaches for analyzing large-scale social media data in the context of political communication
AI-Assisted Bibliometric Mapping of Global Research on Technology-Based Training for Enhancing School Principals' Managerial Competence in the Digital Transformation Era
No full textDigital transformation demands that school principals possess technology-based managerial competencies to lead innovation, improve organizational effectiveness, and create inclusive learning environments in the dynamic era of global education. This article describes trends, thematic focuses, and global collaborations in technology-based educational leadership research to strengthen principals' managerial competencies in facing the challenges of digital transformation and inclusive education. The research methodology uses an artificial intelligence (AI)-assisted bibliometric approach with quantitative-descriptive analysis, including Scopus data extraction, cleaning, normalization, visualization, and validation of results through NLP and clustering topic modeling. The analysis shows significant publication growth since 2010 with a peak in the 2024–2025 period, driven by the accelerated adoption of educational technology after the COVID-19 pandemic. The rate of publication increase reached 6.63% per year, with an average of 11.74 citations per document. Dominant themes include educational leadership, school principals, instructional leadership, and professional development, while new topics such as digital leadership, gender equality, and policy innovation began to strengthen post-2020. Affiliation mapping shows the dominance of universities from Spain, South Africa, and Israel, followed by an increase in contributions from Asian institutions (Indonesia and Malaysia) since 2016. The most productive author is ARAR KH (8 publications), followed by DOR-HAIM P. and HALLINGER P., who are the main nodes of the global network. Cross-country collaboration has been shown to increase the number of citations and strengthen the research network. The study highlights the shift in principal leadership from traditional models to data-driven digital ones, emphasizing technology integration, global collaboration, ethics, and managerial competencies in facing the challenges of digital-era education
Analysis of Pedestrian Facilities in Tambak Market Area, Cikande Banten Province
No full textPedestrian lanes or sidewalks are a place for pedestrians to carry out activities to provide services to pedestrians to feel safe, comfortable and avoid the risk of motor traffic. This study aims to maintain the characteristics of pedestrian movement, find out the level of pedestrian services on Cikande Pond Road, find out efforts that can be made to improve pedestrian road services on Cikande Pond Road. The method used was based on the 1995 Highway guidelines and the distribution of questionnaires to obtain respondent preferences. Results are obtained. Flow on the right side is 8.33 pedestrians/m/min while on the left side is 5.20 pedestrians/m/min, pedestrian speed is 37.62 m/min, Average Space Speed (Vs) is 3.322 m/min, density on the right side is 2.508 pedestrians/m2 while on the left side is 1.565 pedestrians/m2, space (Space) on the right side is 0.399 m2/ped while on the left side is 0.639 m2/ped, the pedestrian ratio on the right side is 0.111 while on the left side is 0.069, the service level (LOS) includes the "C" level. so that improvement efforts can be carried out, including the arrangement of street vendors, the repair of pedestrian paths that are potholes or obstructed by illegal parking and the painting of longitudinal lines in the direction of the sidewalk so that it is easier for pedestrians to travel on the road
Internet of Things (IoT) Platform Using Web Services-Based The Laravel Framework in Wind Turbines
Full text linkThe increasing need for sustainable electrical energy has driven the development of various renewable energy sources, one of which is wind power plants (wind turbines). The development of the Internet of Things (IoT) is a solution for monitoring and managing wind power plants remotely, in real time so that it is more efficient and centralized. The integration method on the Internet of Things (IoT) platform is to build a sensor system installed on the wind turbine output so that it can send operational data in real time. The background of this study will design and implement a power monitoring system on a wind turbine using an Internet of Things-based web service platform. The development of an Internet of Things-based power monitoring system on web services will be built using the Laravel framework which will be integrated with the power output of the wind power plant. This platform is expected to simplify the process of monitoring, controlling, and analyzing wind turbine performance in real time, so that it can increase operational efficiency and support the development of sustainable renewable energy.
Does Competitive Advantage Mediate Innovation Capability and Organizational Ambidexterity-Organizational Performance Relationship?
Full text linkThis study aims to describe innovation capability, organizational ambidexterity, competitive advantage, and organizational performance and investigate the effects of innovation capability and organizational ambidexterity on organizational performance as mediated by competitive advantage. Owners of small and medium-sized enterprises in Bekasi Municipality, West Java Province, Indonesia are the unit of study. This study employs quantitative methodologies. The research population comprised 2,186 SME businesses registered with the Government Office of Small and Medium Enterprises of Bekasi municipality, West Java Province, Indonesia. The respondents consisted of 100 SME business owners, and the sampling technique was simple random sampling. The analysis of the data using the Partial Least Square approach. The results show that innovation capability and organizational ambidexterity have positive effects on competitive advantage; innovation capability and organizational ambidexterity also have a positive direct impact on organizational performance; competitive advantage mediates the innovation capability and organizational performance relationship and also organizational ambidexterity and organizational performance relationship. SMEs owners must implement innovation capability and organizational ambidexterity to improve their competitive advantage and performance
Reward Strategy, Employee Development Towards Employee Retention Through Job Satisfaction as an Intervening Variable and SOPs as a Mediation Variable in Line with SDGs No.10 to Reduce Inequality
No full textIt examined the relationship between objective rewards and development methodologies and employee retention, mediation of job satisfaction, and mediation by standard operating procedures (SOP). This study specifically relates to Sustainable Development Goal (SDG) No. 10, which seeks to reduce inequality whereby just and fair retention practices create an environment inclusive and fair work. The methodology for this research was quantitative - surveys were used as the main instrument for the collection of data. The data were collected from 92 respondents at the Asam-Asam PLTU in Tanah Laut Regency, South Kalimantan. Path analysis was used for testing the formulated hypotheses. Performance appraisal results revealed that employee rewards and development methodologies influence job satisfaction and employee retention. Job satisfaction is a major encroaching variable because higher job satisfaction increases the likelihood that employees will stay in the organization. Furthermore, the implementation of transparent and equitable SOPs mediated the relationship between management strategies and employee retention, thereby ensuring that organizational practices were coherent and minimizing disparities among employees. These results imply that effective employee retention depends not only on financial incentives but also on perceptions of fairness and equal opportunity, which are facilitated by robust SOP. In summary, it recommends that for the organizations to attain higher employee retention rates, they'll have to measure accordance with SDG 10 by instituting systematic reward and development strategies under transparent SOPs, targeted at comprehensive job satisfaction improvement