Article Per Year (5 Year)
p-Index From 2021 - 2026
0.983
P-Index
This Author published in this journals
All Journal Journal of Intelligent Decision Support System (IDSS) Jurnal Mandiri IT
Heikhmakhtiar, Aulia Khamas
Unknown Affiliation
Computer Science & IT Library & Information Science Mathematics

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Journal of Intelligent Decision Support System (IDSS)

 1 
Comparison of Naïve Bayes Classifier and Support Vector Machine for sentiment analysis on civil military relations conflict among Rohingya refugees as recommendation for defense policy making Putri, Nanda Selviana; Saragih, Hondor; Heikhmakhtiar, Aulia Khamas
Journal of Intelligent Decision Support System (IDSS) Vol 7 No 3 (2024): Intelligent Decision Support System (IDSS)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/idss.v7i3.255

Abstract

This research focuses on the evaluating the performance of various sentiment analysis techniques using the Naive Bayes Classifier and Support Vector Machine in identifying civil-military conflicts among Rohingya refugees. The goal is to assist leaders in formulating defense policies. This research uses text data from news sources on Twitter, with a total of 5018 data that have been processed to become clean data, then divided into 1004 test data and 4018 training data to be classified using the Support Vector Machine and Naive Bayes methods. This research analyzes the sentiment and polarity of public opinion related to the issues that occur in this situation. The results of the sentiment analysis from the two methods are then classified using the Support Vector Machine and Naive Bayes methods, and then compared to determine which method is more effective in capturing the complex dynamics of sentiment. The findings of this research indicate that the Support Vector Machine method has a higher accuracy in identifying sentiments related to the civil-military conflict among Rohingya refugees, with an accuracy of 87.95%, compared to the Naive Bayes Classifier with an accuracy of 85.16%. The analysis results in the form of frequently occurring words in the true positive word cloud, namely apology, human, angry, and solidarity, are handed over to experts to be formulated into recommendation sentences and can be used to assist in the formulation of policies for defense decision-makers in more effectively addressing the Rohingya refugee issue.
Strategy for preventing human trafficking through verification of online job vacancies in Indonesia: English Passu Beta, Arga Husein; Rimbawa, H.A. Danang; Heikhmakhtiar, Aulia Khamas
Journal of Intelligent Decision Support System (IDSS) Vol 8 No 4 (2025): December: Intelligent Decision Support System (IDSS)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/idss.v8i4.324

Abstract

This study addresses the rise of online job ads used to recruit victims of human trafficking (TPPO). We propose a practical screening approach that combines automated checks with human moderation. The goal is not to prove crimes, but to prioritize high-risk ads for fast review and referral. Using a public dataset of 500 job postings (fake_job_postings_500), we clean the text and basic metadata, extract simple text features (TF–IDF), and add light verification signals (e.g., contact and firm consistency). We then train two models in a leakage-safe pipeline: calibrated Logistic Regression (LR-cal) and Random Forest (RF). Performance is evaluated with standard accuracy measures ROC-AUC, PR-AUC, F1 plus calibration (how well risk scores match reality) and triage metrics that reflect real operations: precision for the highest-risk group, recall for all medium-and-above risk, and the share of ads moderators must review. Results show LR-cal is accurate and well-calibrated (5-fold means: ROC-AUC 0.993, PR-AUC 0.986, F1 0.934). In triage with thresholds T_high = 0.80 and T_med = 0.50, LR-cal yields Precision@High = 1.00 and Recall@≥Med=0.925 with ~34% of ads needing review. RF reaches near-ceiling accuracy (1.00/1.00 at ~35.3% workload) but requires careful calibration and leakage auditing. Practical contribution: AI-assisted, risk-based gatekeeping can reduce exposure to Human Trafficking or TPPO at the source. We recommend: (1) adopting calibrated models with adjustable thresholds; (2) standard operating procedures (SOPs) for cross-platform verification, including Know Your Customer (KYC) and Open-Source Intelligence (OSINT) checks; and (3) direct integration with official reporting channels to escalate flagged ads swiftly.
Co-Authors Aulia, Regifia Ningrum Nur Azahra, Manda Fatimah Bimorogo, Sembada Denrineksa Fikri, Muhammad Naufal Arits Hondor Saragih Lediwara, Nadiza Mayuni, Angga Ferdian Passu Beta, Arga Husein Prabukusumo, M Azhar Priyani, Kadek Jana Putri, Nanda Selviana Rimbawa, H.A. Danang Sarwoko, Nisrina Labiba Sunami, Yoga Zhafirah, Findi