cover
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
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.
Articles 1,270 Documents
A Study on the Mechanism of Virtual Anchors' Interactivity and Attractiveness Influencing Consumer Trust, Emotional Attitudes, and Purchase Intentions Li Guang Yu; Wong Chee Hoo; Wei Zhi; Christian Wiradendi Wolor; Usep Suhud
Journal of Applied Data Sciences Vol 7, No 2: May 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i2.1139

Abstract

This study presents a dual-mediation model examining how the interactivity and appeal of virtual streamers affect consumers' purchase intentions. The model is anchored in the "Stimulus-Organism-Response" (S-O-R) framework, seeking to clarify and compare the efficacy of two distinct psychological pathways: cognitive, mediated by perceived trust, and affective, mediated by emotional attitude. A survey of 515 Chinese consumers with prior exposure to virtual streamer e-commerce livestreams was conducted, with the model tested using Partial Least Squares Structural Equation Modelling (PLS-SEM). The findings demonstrate that both interactivity and appeal significantly increase perceived trust and cultivate positive emotional attitudes. Notably, the direct effect of perceived trust on purchase intention is more potent than that of emotional attitude. Intermediary analysis further confirms that both paths are important intermediaries, and the trust intermediary path consistently exerts stronger influence. These results show that in the context of AI-driven virtual anchors, the cognitive-based trust path is more influential than the emotional-based path. By comparing these two paths, this study has improved our theoretical understanding of virtual persuasion and provided a new contribution. In fact, this study puts forward a strategy of "trust first, emotional strengthening" for marketers who use virtual anchors. Future research should investigate the cross-cultural applicability of these findings and the moderating effect of product categories.
Sentiment Analysis on Slang Enriched Texts Using Machine Learning Approaches Priyo Agung Prastyo; Berlilana Berlilana; Imam Tahyudin
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.
Sentiment Unleashed: Electric Vehicle Incentives Under the Lens of Support Vector Machine and TF-IDF Analysis Johan Reimon Batmetan; Taqwa Hariguna
Journal of Applied Data Sciences Vol 5, No 1: JANUARY 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i1.162

Abstract

This research examines public sentiment regarding electric vehicle incentives through sentiment analysis of online comments. These incentives include tax deductions and other financial rewards offered to promote the adoption of electric vehicles. In this study, the researchers collected and analyzed over 1,000 comments from various online platforms to understand the public's perspective on these incentives. The study employs Support Vector Machine (SVM), a powerful machine learning algorithm, as the main method and utilizes Term Frequency-Inverse Document Frequency (TF-IDF) to analyze comment texts. The research findings depict significant variation in public sentiment regarding electric vehicle incentives. Approximately 57.3% of comments express negative sentiment towards these incentives, while 33.2% are positive, and the rest are neutral. There is strong support for these incentives, particularly from a financial standpoint. However, some dissatisfaction is expressed, especially regarding electric vehicle prices and charging infrastructure availability. External factors such as government policies and vehicle prices significantly influence public sentiment. Easy access to charging infrastructure also plays a crucial role in shaping positive sentiment. Environmental issues also contribute to a positive view of electric vehicle incentives. Policy recommendations arising from this research emphasize the need to consider these factors when designing and implementing electric vehicle incentives. Improvement efforts in pricing, infrastructure, and environmental education can help enhance electric vehicle adoption in society. This research provides valuable insights into public sentiment towards electric vehicle incentives and the factors influencing such sentiment. The results can serve as a foundation for better decision-making to support the development of sustainable and environmentally friendly electric vehicles.   
Hybrid CNN Approach for Post-Disaster Building Damage Classification Using Satellite Imagery Sahat Sonang; Y Yuhandri; Muhammad Tajuddin
Journal of Applied Data Sciences Vol 6, No 4: December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i4.931

Abstract

Accurate post-disaster building damage assessment is critical for timely response and effective reconstruction planning. This study proposes a hybrid deep learning architecture that integrates Inception-ResNet-v2 and EfficientNetV2B0, designed to enhance post-disaster damage classification from high-resolution satellite imagery. The model leverages dual-stream feature extraction, followed by concatenated fully connected layers optimized with dropout and batch normalization to improve generalization and reduce overfitting. The objective is to outperform standard Convolutional Neural Network (CNN) models in terms of classification and segmentation performance across multiple damage categories: no damage, minor damage, major damage, destroyed, and unclassified. The model was trained and validated on the publicly available xView dataset, covering over 12,000 annotated images from various natural disasters. Comparative evaluation against ResNet, GoogleNet, DenseNet, and EfficientNet demonstrates that the proposed model achieves the highest accuracy (86%), precision (85%), recall (86%), and F1-score (84%). Furthermore, it outperforms all baseline models in segmentation metrics, achieving an Intersection over Union (IoU) score of 0.7749 and a Dice Similarity Coefficient (DSC) of 0.8726. The model also significantly reduces misclassification rates in critical categories such as “major damage” and “destroyed.” A Wilcoxon signed-rank test confirmed that these improvements are statistically significant (p 0.05) across all major performance indicators. The novelty of this study lies in the fusion of two state-of-the-art CNN backbones with tailored architectural modifications, yielding a robust and generalizable model suitable for automated disaster damage assessment. This research contributes a scalable deep learning approach that can be integrated into real-time or semi-automated disaster response systems, offering improved decision-making support in emergency contexts. The results affirm the model’s potential as a reliable tool in post-disaster scenarios and set a foundation for future work in multi-modal and real-time AI-based disaster management.
Intelligent Transportation System's Machine Learning-Based Traffic Prediction S Govindaraju; M Indirani; Siti Sarah Maidin; Jingchuan Wei
Journal of Applied Data Sciences Vol 5, No 4: DECEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i4.364

Abstract

The aim of this study is to develop an accurate and timely traffic flow prediction tool that considers various factors influencing road conditions, such as road repairs, rallies, traffic signals, and other everyday events that can impact traffic movement. By providing drivers with near real-time predictive insights, they can make more informed decisions, enhancing traffic management and potentially supporting future autonomous vehicle technologies. Given the exponential growth in traffic data, this research applies big data principles to the transportation domain, where existing traffic prediction models struggle to handle real-world applications effectively. In this study, we implemented machine learning, genetic algorithms, soft computing, and deep learning techniques, achieving a traffic flow prediction accuracy of 93.5%. The results demonstrate a significant improvement in prediction accuracy compared to conventional models, which typically average around 85%. Additionally, image processing algorithms for traffic sign identification are integrated, achieving 90% accuracy in identifying key traffic signs, further aiding in the training of autonomous vehicles. The proposed approach addresses the challenges posed by large-scale transportation data, offering a solution with improved predictive accuracy and practical utility.
Institutional Readiness and Digital Service Quality as Determinants of Entrepreneur Trust in Risk Based Business Licensing Services Tunggul Sihombing; Medlin Anggreyni Hura; Asima Yanty Siahaan
Journal of Applied Data Sciences Vol 7, No 2: May 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i2.1429

Abstract

This study examines digital licensing governance in risk-based business licensing services by integrating institutional readiness, digital service quality, service dependability, procedural transparency, public trust, entrepreneur satisfaction, and compliance intention. A quantitative explanatory design was applied using 300 valid responses from entrepreneurs who had used local government licensing services and the Online Single Submission system. The respondent profile shows that 73.0% were micro and small enterprises, 60.7% operated in medium- and high-risk categories, 50.4% used assisted online services at the DPMPTSP office, and 38.3% experienced permit processing durations of more than seven days. The measurement model demonstrated strong validity and reliability, with Composite Reliability values ranging from 0.908 to 0.936 and AVE values ranging from 0.663 to 0.701. The structural model revealed that institutional readiness significantly affected digital service quality and service dependability, while digital service quality strongly influenced service dependability and procedural transparency. Procedural transparency had the strongest direct effect on public trust, with a path coefficient of 0.547, followed by entrepreneur satisfaction toward compliance intention at 0.511 and public trust toward entrepreneur satisfaction at 0.452. Mediation analysis confirmed that digital service quality contributed to satisfaction through service dependability, procedural transparency, and public trust. The findings show that digital licensing reform does not depend solely on system availability, but on the alignment of institutional capacity, digital quality, reliable service delivery, transparent procedures, and public trust. This study contributes a comprehensive governance model for explaining how digital public services strengthen satisfaction and formal compliance among entrepreneurs.
Sentiment Analysis between VADER and EDA for the US Presidential Election 2020 on Twitter Datasets Ria Devina Endsuy
Journal of Applied Data Sciences Vol 2, No 1: JANUARY 2021
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v2i1.17

Abstract

The 2020 US Election took place on November 3, 2020, the result of the election was that Joe Biden received 51.4% of the votes, Donald Trump 46.9%, and the rest were other candidates. The period before the election was a time when people conveyed who would vote and conveyed the reasons directly or through social media, especially Twitter through keywords or tags such as #JoeBiden & #DonaldTrump. In this paper, we will compare sentiment analysis and explanatory data analysis against US election data on Twitter. The overall objective of the two case studies is to evaluate the similarity between the sentiment of location-based tweets and on-ground public opinion reflected in election results. In this paper, we find that there are more "neutral" sentiments than "negative" and "positive" sentiments.
Modeling Female Contraceptive Recommendation Using Hybrid Analytical Hierarchy Process and Profile Matching Ati Zaidiah; Ria Astriratma; Ika Nurlaili Isnainiyah
Journal of Applied Data Sciences Vol 6, No 3: September 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.613

Abstract

Multi-criteria decision-making (MCDM) methodologies have been extensively employed across various domains within healthcare. They can be utilized for disease prediagnosis, aiding clinical decision-making (e.g., surgery), conducting health technology assessments, as well as establishing healthcare priorities. This research presents the outcomes of a hybrid MCDM strategy, integrating the AHP and Profile Matching to facilitate clinical recommendations related to female contraception. Many cases in Indonesia show acceptors' inappropriateness in using available contraceptives, causing side effects resulting in negative effects. The challenges in the Keluarga Berencana or Planned Parenthood program in Indonesia are increasing, based on the decline in the number of new acceptors and the high unmet needs for contraception. Failure to meet the need for contraception has the potential to increase birth rates and maternal mortality rates, which requires serious attention and the development of appropriate strategies. Based on the problem, this study aims to create a decision support model in selecting suitable contraceptives for acceptors. The criteria used in this study consisted of age, medical history, weight (BMI), breastfeeding or not, history of childbirth, period of use, and income. The seven criteria are implemented in AHP with a consistency test result value of 2.2%. Based on the target value of contraceptives obtained from the results of Profile Matching, compatibility was determined with a sample of three acceptor profiles. The results that have been achieved indicate a sample recommendation model for acceptors of IUD-type contraception that can assist midwives or medical personnel in providing recommendations for selecting appropriate contraceptive methods. Future studies can integrate the results of recommendations for health service providers (e.g., hospitals, Public Health Center or Puskesmas) in procuring contraceptives.
Cognition-Based Document Matching Within the Chatbot Modeling Framework Sunu Jatmika; Syaad Patmanthara; Aji Prasetya Wibawa; Fachrul Kurniawan
Journal of Applied Data Sciences Vol 5, No 2: MAY 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i2.209

Abstract

The aim of the study is to examine cognitive methods for document matching in a chatbot modeling framework by utilizing Euclidean Distance, Cosine Similarity, and BERT methodologies. Five primary indications are used to carry out evaluation in testing: document matching accuracy, document matching execution time, document search efficiency, consistency of document matching results, and the quality of the document representation in the matrix. Document matching accuracy is evaluated by precision; document matching execution time is measured from the beginning to the end of the document matching process; document search efficiency is measured through evaluation of execution time and matching accuracy; the consistency of document matching results is assessed by comparing method results when tested against the same or similar queries and the quality of document representation is assessed based on the method's ability to represent documents in a matrix or vector. The test findings offer a comprehensive understanding of how well the three approaches operate and exhibit their capacity to address the unique requirements of chatbot users. These results may contribute to the advancement of language technology applications, making it possible for chatbots to deliver pertinent information more rapidly and precisely. There are 1,755 labeled question samples in the dataset, which were split up into two sets: 60% for training (1,053 pieces), and 40% for testing (702 samples) to evaluate the model's performance. The test results show the accuracy of the three methods based on five measured evaluation indications, namely Euclidean Distance 0,45%, Cosine similarity 0,59%, and BERT 0,91%.  By comprehending the benefits and drawbacks of each approach, this research strengthens contributions to the growth of chatbot systems to better serve user demands and opens the door for the creation of more complex human-machine interaction solutions.
Multiclass Skin Lesion Classification Algorithm using Attention-Based Vision Transformer with Metadata Fusion Mhd. Furqan; Norliza Katuk; Dedy Hartama
Journal of Applied Data Sciences Vol 7, No 1: January 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i1.1017

Abstract

Early and accurate classification of skin lesions is essential for timely diagnosis and treatment of skin cancer. This study presents a novel multiclass classification framework that integrates dermoscopic images with clinical metadata using an attention-based Vision Transformer (ViT) architecture. The proposed model incorporates a mutual-attention fusion mechanism to jointly learn from visual and tabular inputs, augmented by a class-aware metadata encoder and imbalance-sensitive loss function. Training was conducted using the HAM10000 dataset over 30 epochs with a batch size of 32, utilizing the Adam optimizer and a learning rate of 0.0001. The model demonstrated superior performance compared to a ViT Baseline, achieving 93.4% accuracy, 92.2% F1-score, 0.95 AUC, and significant reductions in MAE and RMSE. Additionally, Grad-CAM visualizations confirmed the model’s ability to focus on diagnostically relevant regions, enhancing interpretability. These findings suggest that the integration of structured clinical information with transformer-based visual analysis can significantly improve classification robustness, particularly in underrepresented lesion types. However, the model’s current performance is evaluated only on the HAM10000 dataset, and its generalizability to other clinical or non-dermoscopic image sources remains to be validated. Future studies should therefore explore multi-institutional datasets and real-world deployment scenarios to assess robustness and scalability. The proposed framework offers a practical, interpretable solution for AI-assisted skin lesion diagnosis and demonstrates strong potential for clinical deployment.

Page 95 of 127 | Total Record : 1270