cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Husni Teja Sukmana
Contact Email
husni@bright-journal.org
Phone
+62895422720524
Journal Mail Official
jads@bright-journal.org
Editorial Address
Gedung FST UIN Jakarta, Jl. Lkr. Kampus UIN, Cemp. Putih, Kec. Ciputat Tim., Kota Tangerang Selatan, Banten 15412
Location
Kota adm. jakarta pusat,
Dki jakarta
INDONESIA
Journal of Applied Data Sciences
Published by Bright Publisher
ISSN : -     EISSN : 27236471     DOI : doi.org/10.47738/jads
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management
One of the current hot topics in science is data: how can datasets be used in scientific and scholarly research in a more reliable, citable and accountable way? Data is of paramount importance to scientific progress, yet most research data remains private. Enhancing the transparency of the processes applied to collect, treat and analyze data will help to render scientific research results reproducible and thus more accountable. The datasets itself should also be accessible to other researchers, so that research publications, dataset descriptions, and the actual datasets can be linked. The journal Data provides a forum to publish methodical papers on processes applied to data collection, treatment and analysis, as well as for data descriptors publishing descriptions of a linked dataset.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 518 Documents
 31   32   33   34   35 
Structural Equation Modeling of Social Media Influences: How Visual Appeal and Product Information Shape Positive Word of Mouth Iswanto, Dedy; Premananto, Gancar Candra; Sudarnice, Sudarnice; Sangadji, Suwandi S.
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.584

Abstract

Social media has become an essential tool in contemporary marketing strategies, allowing brands to enhance consumer engagement and foster trust. This study examines the direct effects of visual appeal and product information on brand satisfaction and positive Word of Mouth (WOM) in the context of Samsung’s social media campaigns. The research aims to provide empirical insights into how specific content elements drive consumer satisfaction and WOM, which are critical factors in expanding a brand’s digital influence. Data were collected from 132 active social media users frequently exposed to Samsung’s advertisements. Structural Equation Modeling (SEM) using the Partial Least Squares (PLS) approach was employed to analyze the relationships between variables. The results indicate that visual appeal significantly impacts brand satisfaction (path coefficient = 0.419, T-statistic = 3.765, P-value = 0.000) and WOM (path coefficient = 0.221, T-statistic = 2.437, P-value = 0.015). Product information also shows a significant influence on brand satisfaction (path coefficient = 0.337, T-statistic = 3.126, P-value = 0.002) and WOM (path coefficient = 0.320, T-statistic = 3.795, P-value = 0.000). Additionally, brand satisfaction strongly contributes to positive WOM (path coefficient = 0.458, T-statistic = 7.191, P-value = 0.000). The findings emphasize the critical role of high-quality visual and informational content in fostering brand satisfaction and promoting WOM. The novelty of this research lies in its detailed examination of how visual appeal and product information independently influence consumer outcomes, offering actionable insights for marketers. This study contributes to the growing literature on digital marketing by providing evidence-based recommendations for optimizing social media strategies in highly competitive and digitally connected marketplaces.
Transforming Mathematics Learning: Students' Integrative Skills in Technology and Pedagogy Turmuzi, Muhammad; Hikmah, Nurul; Junaidi, Junaidi
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.482

Abstract

In the digital age, mastering the topic or developing pedagogical design skills alone is no longer sufficient for instructors or aspiring math educators. They also need to be able to make connections between the two. In addition, other specialized abilities are required, such as the ability to use technology for learning (technological skills). Technological Pedagogical and Content Knowledge (TPACK) is a common term for this skill. TPACK is a framework that helps educators integrate technology into learning effectively. TPACK covers three main types of knowledge-Technology, Pedagogy, and Content, and how the combination of these three elements creates a more meaningful learning experience for students. This study aims to assess the TPACK teaching abilities of aspiring mathematics teachers in the Microteaching course. This research uses a qualitative descriptive method, which describes the object of research in its original form without quantitative measurement or manipulation of variables but focuses on describing the observed phenomena. In this instance, the study provides a general picture of how well math education students comprehend and utilize their TPACK. A Likert scale measures an individual's or group's attitudes, views, and perceptions concerning social phenomena to ascertain their understanding of TPACK. Twenty University of Mataram students enrolled in the Microteaching course in Mathematics Education served as the research subjects. Based on the findings of the research and discussion, it can be said that students applying TPACK to learning have an average score of 3.88 medium categories for technological pedagogical knowledge, 3.82 medium categories for pedagogical knowledge, and 3.63 medium categories for content knowledge. Since most students are already familiar with the TPACK instrument, their total TPACK ability has an average score of 3.89, which is considered to be medium.
Evaluating Usability and Clustering of SILCARE System for MSME Shipping: A Data-Driven Approach Using SUS and User Behavior Analysis Permatasari, Ririt Dwiputri; Bora, M Ansyar; Hernando, Luki; Saputra, Tommy; Fauzan, Haidil; Shilah, Nur; Salsabila, Tia Andini
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.590

Abstract

The SILCARE system is a digital logistics platform designed to optimize shipping operations for Micro, Small, and Medium Enterprises (MSMEs). This study evaluates its usability and user behavior patterns through System Usability Scale (SUS) assessments and clustering analysis. The research involved 100 SME users performing key system tasks such as registration, product management, and order confirmation. The SUS results showed a significant usability improvement, with the pre-test score of 74.5 (B grade) increasing to 90.25 (A grade) in the post-test, indicating enhanced user experience. User interaction data analysis revealed that registration took an average of 7.11 minutes, product addition 8.91 minutes, and order confirmation 5.15 minutes. Clustering using DBSCAN identified four distinct user groups, highlighting behavioral differences, where 37% of users struggled with complex tasks while 25% displayed balanced engagement. These findings inform targeted system improvements, such as simplifying workflows for new users and enhancing features for power users. The novelty of this study lies in integrating usability testing with behavior-driven clustering to refine a logistics platform tailored to MSMEs. By leveraging data-driven insights, the SILCARE system contributes to digital transformation in MSME logistics, improving operational efficiency and user satisfaction The paper explores the development process of the system, starting from the requirements gathering phase, where user needs were identified through extensive surveys and interviews with stakeholders. The iterative prototyping method allowed for the creation of an initial version of the system that was refined based on user feedback, ensuring that the final product met both functional and usability standards. The SILCARE system holds substantial promise for MSMEs, offering a digital solution for streamlining logistics and shipping processes and contributing to the overall success of small businesses.
Improved Deep Learning Model for Prediction of Dermatitis in Infants Setiawan, Debi; Noratama Putri, Ramalia; Fitri, Imelda; Nizar Hidayanto, Achmad; Irawan, Yuda; Hohashi, Naohiro
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.542

Abstract

Indonesia's equatorial climate, characterized by summer and rainy seasons, presents environmental conditions that contribute to a high incidence of dermatitis in infants. Dermatitis, an inflammatory skin condition, can lead to significant discomfort in infants, affecting their sleep, growth, and development. Early diagnosis is crucial for effective treatment; however, conventional diagnostic methods in clinics and hospitals—such as physical observation and parental interviews—are often time-consuming, subjective, and may lack precision, creating a need for more efficient diagnostic tools. This study explores the application of deep learning models to enhance the accuracy and speed of dermatitis diagnosis in infants. Four convolutional neural network (CNN) models were evaluated: MobileNet, VGG16, ResNet, and a Custom CNN model specifically designed for this study. Using a dataset of 1,088 skin images collected from three regions in Riau Province, Indonesia, we conducted training and testing to assess each model’s performance in distinguishing between dermatitis-affected and healthy skin. Results show that MobileNet and the Custom CNN outperformed other models, achieving accuracy rates of 97% and 85%, respectively. MobileNet’s high accuracy and efficiency make it a viable option for mobile applications, enabling rapid, on-site diagnosis in resource-limited settings. The Custom CNN model, tailored to the unique features of infant skin, also showed promising results. These findings demonstrate the potential of automated, image-based diagnostic tools for assisting medical professionals in early dermatitis detection, improving patient outcomes. This study contributes a valuable diagnostic solution that leverages deep learning to support healthcare providers, particularly in areas with limited access to specialized medical resources.
Sentiment Analysis on Slang Enriched Texts Using Machine Learning Approaches Prastyo, Priyo Agung; Berlilana, Berlilana; Tahyudin, Imam
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.626

Abstract

This study explores sentiment analysis of slang-enriched user reviews using machine learning techniques, specifically Naive Bayes, Support Vector Machine (SVM), and Random Forest, to classify user sentiment into Positive, Negative, and Neutral categories while addressing challenges posed by informal and conversational language through slang normalization. A lexicon-based scoring method was employed to standardize slang terms such as “gak,” “aja,” and “banget,” ensuring consistency in sentiment analysis. The results indicate that Neutral sentiment dominates the dataset (51%), followed by Negative (28%) and Positive (21%), with lexicon-based scores confirming this distribution. Negative sentiment exhibits a broader intensity range, reflecting user dissatisfaction primarily related to network quality, service reliability, and pricing, as evident from recurring terms like “sinyal” (signal), “jaringan” (network), and “mahal” (expensive). Word cloud visualizations reinforce these findings, highlighting the prevalence of these concerns in user feedback. Performance evaluation of the machine learning models reveals that SVM and Random Forest achieved the highest accuracy (96%), significantly outperforming Naive Bayes (73%), demonstrating their effectiveness in handling high-dimensional text data and accurately classifying slang-rich content. These findings underscore the importance of slang normalization in preprocessing, as it significantly enhances sentiment classification accuracy. This study provides actionable insights for service providers, helping them identify and address key sources of user dissatisfaction. Future research can explore deep learning models such as BERT and LSTM to further enhance sentiment analysis by capturing contextual relationships within text data, while topic modeling techniques could uncover deeper thematic patterns in user feedback, enabling data-driven strategies to improve customer satisfaction.
Optimizing Sentiment Analysis on Imbalanced Hotel Review Data Using SMOTE and Ensemble Machine Learning Techniques Putra, Pandu Pratama; Anam, M. Khairul; Chan, Andi Supriadi; Hadi, Abrar; Hendri, Nofri; Masnur, Alkadri
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.618

Abstract

This research addresses the challenge of imbalanced sentiment classes in hotel review datasets obtained from Traveloka by integrating SMOTE (Synthetic Minority Oversampling Technique) with ensemble machine learning methods. The study aimed to enhance the classification of Positive, Negative, and Neutral sentiments in customer reviews. Data preprocessing techniques, including tokenization, stemming, and stopword removal, prepared the textual data for analysis. Various machine learning models—CART, KNN, Naive Bayes, and Random Forest—were evaluated individually and in ensemble configurations such as Bagging, Stacking, Soft Voting, and Hard Voting. The Stacking ensemble approach, utilizing Logistic Regression as a meta-classifier, demonstrated superior performance with an accuracy, precision, recall, and F1-score of 88%, outperforming Bagging (86%), Hard Voting (84%), and Soft Voting (81%). The findings highlight the effectiveness of SMOTE in balancing sentiment classes, particularly improving the classification of underrepresented Neutral and Negative categories. The novelty of this study lies in the comprehensive use of ensemble techniques combined with SMOTE, which significantly enhanced prediction stability and accuracy compared to previous approaches. These results provide valuable insights into leveraging advanced machine learning techniques for sentiment analysis, offering practical implications for improving customer experience and service quality in the hospitality industry.
Enhancing Digital Marketing Strategies with Machine Learning for Analyzing Key Drivers of Online Advertising Performance Berlilana, Berlilana; Hariguna, Taqwa; El Emary, Ibrahiem M. M.
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.658

Abstract

The rapid growth of digital advertising has underscored the need for data-driven strategies to optimize campaign performance. This study applies machine learning techniques to analyze online advertising data, aiming to identify key performance drivers and provide actionable insights for optimizing marketing strategies. The dataset includes metrics such as clicks, displays, costs, and revenue, which were preprocessed, analyzed, and modeled using ensemble methods, including Random Forest and Gradient Boosting. These ensemble methods were chosen for their ability to handle high-dimensional data, mitigate overfitting, and capture complex, nonlinear relationships between variables. Random Forest, with its bagging approach, enhances generalization by reducing variance, while Gradient Boosting incrementally corrects errors by focusing on hard-to-predict instances, improving overall predictive performance. Descriptive analysis revealed significant variability in campaign outcomes, with cost and user engagement emerging as primary predictors of revenue. Machine learning models demonstrated strong predictive accuracy, with Random Forest achieving 92% accuracy and an F1-score of 89%. Visualizations such as feature importance charts, correlation heatmaps, and learning curves validated the robustness of the models and highlighted key insights, including inefficiencies in cost allocation and the limited impact of certain categorical features like placement. The study emphasizes the potential of machine learning to optimize digital marketing strategies by identifying critical factors that influence campaign success. The findings provide a scalable framework for resource allocation, audience targeting, and strategic decision-making in online advertising. Future research could further enhance predictions by incorporating additional features, such as audience demographics and temporal trends, to provide deeper insights into campaign dynamics.
Development of Skyline Query Algorithm for Individual Preference Recommendation in Streaming Data Amin, Ruhul; Djatna, Taufik; Annisa, Annisa; Sitanggang, Sukaesih
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.599

Abstract

The ability of a recommendation system to deliver relevant outcomes is significantly influenced by its adaptability to the dynamic nature of individual user preferences. Data-streaming-based recommendation systems face substantial challenges in aligning recommendations with rapid shifts in user preferences. Previous research on the development of skyline query algorithms has predominantly focused on processing efficiency and parallel performance optimization yet has not addressed the dynamic nature of individual user preferences—an essential factor for generating relevant and responsive recommendations in streaming data environments. This study aims to develop a skyline query algorithm called Distributed Data Skyline (DDSky) to provide recommendations based on dynamic individual user preferences within data-streaming contexts. DDSky leverages the Recency, Frequency, Monetary, and Rating (RFMRT) model to capture real-time changes in user preferences. This model is integrated with parallel skyline computation and structured to enhance the data processing efficiency on a large scale. The parallel processing approach divides tasks into smaller subtasks executed simultaneously across multiple threads. This strategy enables the simultaneous processing of attributes such as price, distance, and individual user preferences, thereby delivering relevant and responsive recommendations to real-time changes in user preferences. The DDSky algorithm was evaluated using a local dataset from the JALITA application and compared with the Eager algorithm. The results demonstrated that DDSky outperformed Eager, achieving an average recall value of 0.45 and an F1-measure of 0.55, compared to Eager's recall value of 0.33 and F1-measure of 0.47. Furthermore, DDSky achieved an average precision of 0.73, which closely approached Eager's precision of 0.82. Additionally, DDSky exhibited optimal throughput performance for datasets containing up to 10,000 items with high flexibility across various data types. With its unique technical approach, DDSky delivers more responsive and relevant recommendations to dynamic user preferences, establishing its superiority in data-streaming-based recommendation systems.
Improving Evaluation Metrics for Text Summarization: A Comparative Study and Proposal of a Novel Metric Junadhi, Junadhi; Agustin, Agustin; Efrizoni, Lusiana; Okmayura, Finanta; Habibie, Dedi Rahman; Muslim, Muslim
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.547

Abstract

This research evaluates and compares the effectiveness of various evaluation metrics in text summarization, focusing on the development of a new metric that holistically measures summary quality. Commonly used metrics, including ROUGE, BLEU, METEOR, and BERTScore, were tested on three datasets: CNN/DailyMail, XSum, and PubMed. The analysis revealed that while ROUGE achieved an average score of 0.65, it struggled to capture semantic nuances, particularly for abstractive summarization models. In contrast, BERTScore, which incorporates semantic representation, performed better with an average score of 0.75. To address these limitations, we developed the Proposed Metric, which combines semantic similarity, n-gram overlap, and sentence fluency. The Proposed Metric achieved an average score of 0.78 across datasets, surpassing conventional metrics by providing more accurate assessments of summary quality. This research contributes a novel approach to text summarization evaluation by integrating semantic and structural aspects into a single metric. The findings highlight the Proposed Metric's ability to capture contextual coherence and semantic alignment, making it suitable for real-world applications such as news summarization and medical research. These results emphasize the importance of developing holistic metrics for better evaluation of text summarization models.
HU Variance Moment Optimizes Keyframe Selection Based on Deep Learning for Violence Detection Putri, Sukmawati Anggraeni; Andono, Pulung Nurtantio; Purwanto, Purwanto; Soeleman, Moch Arief
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.648

Abstract

Violence in public spaces poses a serious threat to individuals and society. Manual monitoring and violence detection require much time and human resources, ultimately hindering detection accuracy and speed. Therefore, an automated method is needed to detect violence to ensure fast and efficient action. Along with technological advances, violence detection research has adopted various methods and models, including deep learning, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs). In this study, the classification process for detecting violence and non-violence uses the VGG19 model, one of the CNN models that has good performance with limited computing. In addition, the Long Short-Term Memory (LSTM) model is the best RNN model for processing temporal data in videos. However, this performance will decrease with noise and irrelevant data in the classification process. Therefore, to optimize deep learning performance, this study in the pre-processing phase selects keyframes in frame extraction using the Hu Variance Moment Technique. This method calculates each frame’s Hu and Variance Moment values and selects keyframes based on high Hu values. Next, we use Adaptive Moment Estimation (Adam) to optimize the gradient of the selected keyframes. This study produces a Hu19LSTM model tested on three datasets: hockey fight, crowd, and AIRTLab. The proposed Hu19LSTM model produces an accuracy of 97% on the Hockey Fight dataset, 97% on the Crowd dataset, and 95% on the AIRTLab dataset. These results indicate that the Hu19LSTM model can increase its accuracy on the hockey fight and Crowd dataset by 97%.

Page 33 of 52 | Total Record : 518

 31   32   33   34   35 

Filter by Year

2020 2026


Reset
Filter By Issues
All Issue Vol 7, No 1: January 2026 Vol 6, No 4: December 2025 Vol 6, No 3: September 2025 Vol 6, No 2: MAY 2025 Vol 6, No 1: JANUARY 2025 Vol 5, No 4: DECEMBER 2024 Vol 5, No 3: SEPTEMBER 2024 Vol 5, No 2: MAY 2024 Vol 5, No 1: JANUARY 2024 Vol 4, No 4: DECEMBER 2023 Vol 4, No 3: SEPTEMBER 2023 Vol 4, No 2: MAY 2023 Vol 4, No 1: JANUARY 2023 Vol 3, No 4: DECEMBER 2022 Vol 3, No 3: SEPTEMBER 2022 Vol 3, No 2: MAY 2022 Vol 3, No 1: JANUARY 2022 Vol 2, No 4: DECEMBER 2021 Vol 2, No 3: SEPTEMBER 2021 Vol 2, No 2: MAY 2021 Vol 2, No 1: JANUARY 2021 Vol 1, No 2: DECEMBER 2020 Vol 1, No 1: SEPTEMBER 2020 More Issue