Claim Missing Document
Check
Articles

Found 4 Documents
Search

A Review of Data Mining Techniques in the Development of Decision Support Systems Silvi Munawaroh
International Journal of Research and Applied Technology Vol. 3 No. 2 (2023): International Journal of Research and Applied Technology (INJURATECH)
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v3i2.15943

Abstract

This study aims to examine the role and effectiveness of various data mining techniques in improving the performance of Decision Support Systems (DSS). Using a systematic literature review method, relevant academic papers and recent studies from the last decade were analyzed to identify common approaches, applications, and challenges. The findings show that classification, clustering, association rule mining, and anomaly detection are the most widely adopted data mining techniques in DSS development. Machine learning methods such as decision trees, neural networks, and support vector machines further contribute in improving prediction accuracy and decision quality. This discussion highlights that although data mining significantly strengthens the analytical capabilities of DSS, challenges such as data quality, model interpretability, and computational complexity remain important issues. Overall, this review underscores the importance of integrating advanced data mining approaches into DSS frameworks to support smarter, scalable and adaptable decision-making processes
Explainable AI (XAI) for Fake News Detection: A Review of Interpretability in Deep Learning Models for Misinformation Classification Silvi Munawaroh
International Journal of Research and Applied Technology Vol. 4 No. 2 (2024): Vol 4 No 2 (2024)
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v4i2.19642

Abstract

This study provides a comprehensive review of Explainable AI (XAI) applications in fake news detection, addressing the critical "black-box" nature of deep learning models used for misinformation classification. We systematically analyze various interpretability techniques, categorized into ante-hoc and post-hoc methods, applied to neural architectures such as CNNs, RNNs, and Transformers. The study evaluates how these techniques extract linguistic, social context, and visual features to justify classification outcomes. The findings reveal that while attention mechanisms and gradient-based explanations improve transparency, there remains a significant trade-off between model complexity and explanatory clarity. The discussion highlights the challenges of "explanation consistency" and the susceptibility of interpretability tools to adversarial attacks. We conclude that integrating XAI is essential for fostering user trust and regulatory compliance. Future research should prioritize human-centric evaluations to ensure that AI-generated explanations are cognitively accessible to non-expert end-users.
Evaluating the Usability and Accessibility of Cloud-Based AI Translation Interfaces: A Systematic Review of Freelancer User Experience (UX) Silvi Munawaroh
International Journal of Research and Applied Technology Vol. 4 No. 2 (2024): Vol 4 No 2 (2024)
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v4i2.19684

Abstract

This study evaluates the usability and accessibility of cloud-based AI translation interfaces for freelance translators. Using a systematic literature review (SLR) approach, this research synthesizes academic publications and industry reports from the last decade to identify global UX trends in cloud-native CAT tools. Findings reveal that while cloud infrastructure democratizes access to high-level Neural Machine Translation (NMT), significant barriers remain, including high-latency issues in remote regions, steep learning curves for complex AI dashboards, and economic constraints of subscription models. The analysis suggests that current AI infrastructures often prioritize technical scalability over the ergonomic and cognitive needs of non-technical linguists, exacerbating the digital divide. The study concludes that a "Translator-Centered Design" framework is essential to ensure that AI-driven cloud architectures are inclusive and accessible, recommending that developers optimize low-bandwidth performance to support the global freelance community effectively
Cross-Domain Sentiment Analysis using Transfer Learning: A Literature Review on Natural Language Model Adaptation from Social-Media to Macroeconomic Indicator Prediction Silvi Munawaroh
International Journal of Research and Applied Technology Vol. 5 No. 2 (2025): December 2025
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v5i2.19657

Abstract

This study reviews the efficacy of transfer learning in adapting sentiment analysis from social media domains to macroeconomic indicator prediction. Specifically, it evaluates existing literature on natural language processing architectures, predominantly Transformer-based models, performing domain adaptation from informal social media discourse to formal economic contexts. Findings indicate that pre-trained models significantly enhance predictive accuracy for data-scarce economic indicators by capturing real-time public perception. Although effective in mitigating labeled data sparsity, primary challenges persist, notably linguistic noise and inherent demographic biases within social media datasets. Ultimately, transfer learning serves as a critical bridge for transforming public sentiment into actionable predictive economic signals. This cross-domain methodology provides a dynamic, supplementary instrument for policymakers seeking to monitor macroeconomic fluctuations through digital behavioral patterns.