Article Per Year (5 Year)
p-Index From 2021 - 2026
1.642
P-Index
This Author published in this journals
All Journal Jurnal Pustakawan Indonesia Jurnal INSYPRO (Information System and Processing) JURNAL INSTEK (Informatika Sains dan Teknologi) Journal Software, Hardware and Information Technology Jurnal Pustakawan Indonesia Journal of Health and Nutrition Research Innovative: Journal Of Social Science Research Journal of Embedded Systems, Security and Intelligent Systems System Information and Computer Technology (SYNCTECH)
Ibrahim, Firmansyah
Unknown Affiliation
Humanities Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Law, Crime, Criminology & Criminal Justice Library & Information Science Medicine & Pharmacology Nursing Public Health Social Sciences Other

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
Extracting Value from Minority Voices: Epistemic Validation of Naive Bayes and SMOTE Models for E-Commerce Review Sentiment Analysis Ibrahim, Firmansyah; Prasetya, Didik Dwi; Patmanthara, Syaad
Journal of Embedded Systems, Security and Intelligent Systems Vol 6, No 4 (2025): Desember 2025
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v6i4.10275

Abstract

In the e-commerce ecosystem, negative customer reviews, despite often being a numerical minority, represent the most valuable (axiological) business asset for service improvement. However, this value is frequently obscured by the high volume of positive reviews, creating a significant imbalance in the data. This study aims to design and validate a text mining model that is axiologically focused on extracting critical insights from this "minority voice." We applied the Naive Bayes Classifier (NBC) algorithm, augmented with TF-IDF feature weighting, on a dataset of 6,000 reviews from the 'Famous Florist' store. The epistemic challenge of severe data imbalance (5,432 positive vs. 97 negative) was addressed through the methodological intervention of the Synthetic Minority Over-sampling Technique (SMOTE). The model's validity was assessed using 10-Fold Cross-Validation. The epistemic validation results demonstrated the model's validity, achieving an average accuracy of 90%. Crucially, the model achieved a 99% rate for the negative class. This affirms the model's axiological validity: its ability to reliably identify customer complaints (e.g., 'damaged,' 'packaging') and transform raw data into actionable recommendations for improvement.
Public Sentiment on Indonesia’s Free Nutritious Meal Program: A Mixed-Methods NLP Evaluation Ibrahim, Firmansyah; Prasetya, Didik Dwi; Kaswar, Andi Baso; Pratiwi, Hardyanti
Journal of Health and Nutrition Research Vol. 5 No. 1 (2026)
Publisher : Media Publikasi Cendekia Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56303/jhnresearch.v5i1.1053

Abstract

Large-scale nutrition intervention programs such as the Free Nutritious Meal Program (MBG) are likely to attract considerable attention on social media. While conventional evaluation techniques are often too slow to capture rapidly shifting sentiment, this study seeks to determine how sentiment can be evaluated. More specifically, we aimed to identify the key emerging issues. Methodology: In this study, one approach to examining emerging issues is to use a two-stage workflow in Natural Language Processing (NLP). The first step in sentiment analysis is using a transformer model (Indo-RoBERTa) to assign 'Positive', 'Negative', or 'Neutral' to 3,459 public texts from X (Twitter) social media. Secondly, we focused on 1,130 'Negative' texts. We used topic modeling (BERTopic) on this and identified the most critical clusters of issues to map and their relative importance. Results & Conclusions: Negative sentiment involves multiple factors, to which our model successfully highlighted four of the most impactful areas: (1) Financial concerns and budgetary priorities; (2) Responses to particular media coverage (e.g., Kompas); (3) Political general discourse; and (4) Expectations of particular local issues (education issues in Papua). Conclusion: Compared with the gaps in the program's nutrition components, the economic consequences, budget gaps, inequities, and regional policy deficiencies drew more public interest. Implications: The findings point to a clear need for a differentiated and open approach to communicating public policy. This approach should communicate the nutritional value and the need to align messaging with the public for the geographic and budgetary realities.
Co-Authors Agus Buono Akib, Faisal Andi Baso Kaswar Andi Baso Kaswar ANTAMIL, ANTAMIL Asminarni, Asminarni Asrul Azhari Muin, Asrul Azhari Didik Dwi Prasetya Dillah, Nur Fadilah Rahmat Erfina Irman Hermadi Ismi, Nur Katili, Andi Yusuf Nahrun Hartono, Nahrun Nur Inayah Prabujaya, Ilham Pratiwi, Hardyanti Rachman, Ellys Rahman Rahman Rahman Reza Maulana Rizaldy, Adhy Sri Wahyuni Syaad Patmanthara Syah, Herwan