Article Per Year (5 Year)
p-Index From 2021 - 2026
0.961
P-Index
This Author published in this journals
All Journal Sinkron : Jurnal dan Penelitian Teknik Informatika Indonesian Journal of Artificial Intelligence and Data Mining JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika)
Andreas Leonardo Sumendap
Universitas Papua
Computer Science & IT Education

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
Comparative Study of Machine Learning Methods for Sentiment Analysis of TikTok Comments Related to Cyberbullying Celestina Florecita Mariwy; Lorna Yertas Baisa; Andreas Leonardo Sumendap
Indonesian Journal of Artificial Intelligence and Data Mining Vol. 9 No. 1 (2026): March 2026
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The rapid growth of internet use in Indonesia has contributed to the rise of cyberbullying on TikTok, increasing the importance of automated sentiment analysis for digital safety. This study compares the performance of Support Vector Machine, K-Nearest Neighbors, and Naive Bayes in classifying sentiments in TikTok comments related to cyberbullying. The dataset was collected via web scraping and processed through several preprocessing stages, yielding 7,900 unique comments. Sentiment labeling used a lexicon-based approach, and the data were split into training and testing sets with an 80:20 ratio. Results show that 34.18% of comments were negative, indicating a notable level of harmful content. Among the three models, Support Vector Machine performed best with an accuracy of 91.5%, followed by Naive Bayes at 82.8% and K-Nearest Neighbors at 80.8%. These findings suggest Support Vector Machine is the most effective method for sentiment classification in this context and offer a useful reference for developing more accurate content moderation systems on social media.
Analysis of Students’ Perceptions of the Free Nutritious Food Program (MBG) Based on K-Means Clustering Nur Rahmi; Lorna Yertas Baisa; Andreas Leonardo Sumendap
Indonesian Journal of Artificial Intelligence and Data Mining Vol. 9 No. 1 (2026): March 2026
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The Free Nutritious Food Program is a strategic policy to support students’ nutritional resilience and readiness to learn. This study examined students’ perceptions of the program and identified respondent profiles using the K-Means clustering algorithm. Data from 501 students were collected through a Likert-scale questionnaire and analyzed to determine distinct perception patterns. The results revealed five clusters with strong validity, indicated by a silhouette value of 0.917. Overall, 74.6% of respondents expressed positive perceptions, suggesting that the program has been well received and supports school nutrition. However, some groups reported concerns regarding menu variety and cleanliness at distribution points. These findings underscore the need for routine quality monitoring, standardized implementation procedures, and greater attention to service consistency. Future studies should also include objective indicators such as body mass index and school attendance to provide a more comprehensive evaluation of program impact
Public Sentiment Analysis of the Affan Kurniawan Social Issue: A Comparison of Naïve Bayes and SVM Algorithms Marsella Iriana Mamusung; Lorna Yertas Baisa; Andreas Leonardo Sumendap
Indonesian Journal of Artificial Intelligence and Data Mining Vol. 9 No. 1 (2026): March 2026
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Social media X is a dynamic public space where opinions on social issues, including the Affan Kurniawan case, spread rapidly. This study aims to analyze sentiment distribution, compare the performance of Multinomial Naïve Bayes and Linear Support Vector Machine (LinearSVC), and evaluate classification consistency under a unified evaluation framework. Indonesian-language posts were collected using keyword-based crawling and cleaned from 10,624 to 7,431 valid records (28 August–2 September 2025). The data were preprocessed through normalization, tokenization, stopword removal, and stemming, and labeled into negative, neutral, and positive sentiments using a lexicon-based approach. The results show a dominance of negative sentiment (50.26%), followed by neutral (30.96%) and positive (18.77%). Using Bag-of-Words features and an 80:20 train–test split, LinearSVC outperformed Naïve Bayes with higher accuracy (0.826 vs 0.745) and macro F1-score (0.759 vs 0.579). This study highlights the effectiveness of SVM as a stronger baseline model for Indonesian sentiment classification on social media data.
Comparative Sentiment Analysis of GrabFood Reviews Using BiLSTM and BiGRU Jakasurya Siswoyo; Andreas Leonardo Sumendap; Lorna Yertas Baisa
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 3 (2026): Article Research July 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i3.16165

Abstract

The exponential growth of user-generated reviews on digital platforms has made manual sentiment interpretation of Online Food Delivery (OFD) services increasingly impractical. GrabFood, operating within the Grab ecosystem, has accumulated over 16.1 million reviews on the Google Play Store, necessitating an automated and scalable approach to sentiment monitoring. Conventional labeling approaches, including star-rating proxies and lexicon-based annotation, are inadequate for capturing contextual nuance, negation, and informal linguistic patterns prevalent in Indonesian-language OFD reviews. Furthermore, limited research has systematically compared BiLSTM and BiGRU architectures within a transformer-assisted labeling framework for Indonesian OFD sentiment analysis. This study aims to implement RoBERTa-based automatic sentiment labeling and to comparatively evaluate BiLSTM and BiGRU models for three-class sentiment classification of GrabFood reviews. A corpus of 265,500 raw reviews was collected via web scraping, filtered to 17,709 reviews through rigorous preprocessing, and annotated using the w11wo/indonesian-roberta-base-sentiment-classifier. Random Oversampling was applied to address class imbalance. BiLSTM and BiGRU models were trained and benchmarked against Support Vector Machine (SVM) and Naïve Bayes baselines. BiLSTM achieved 86% accuracy while BiGRU attained 85%, both substantially outperforming SVM (82%) and Naïve Bayes (77%). However, BiGRU demonstrated superior convergence speed and more stable per-class performance, particularly on the neutral category (F1: 51% vs. 50%). Transformer-assisted automatic labeling combined with bidirectional recurrent architectures constitutes an effective and scalable pipeline for Indonesian OFD sentiment classification, with neutral sentiment remaining the primary classification challenge.
Design of a Parking Area Detection System Based on ESP32-CAM and YOLOv8 Natalya Sibarani; Andreas Leonardo Sumendap; Abdul Zaid Patiran
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 3 (2026): Article Research July 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i3.16282

Abstract

Conventional car parking management systems still face challenges such as manual vehicle monitoring, limited real-time monitoring, and non-automatic parking access control. This study aims to develop an Internet of Things (IoT)-based smart parking system using ESP32-CAM and the YOLOv8n method to detect four-wheeled vehicles in real time. The developed system consists of ESP32CAM as an image acquisition device, a Python program as a processing center, YOLOv8n as an object detection model, EasyOCR for reading license plates, and MySQL as a storage medium for detection results. This system is also equipped with vehicle distance estimation features, LED flash control, and automatic gate control. Based on testing on 20 four-wheeled vehicle samples in a limited test environment, the system successfully detected all tested vehicles and no vehicle detection errors were found. The system was able to read vehicle license plates using EasyOCR and control automatic gates based on the detection results. However, the accuracy of driver detection and OCR decreased in night conditions, to 40% and 60%, respectively. In addition, the FPS dropped from 18 FPS in the morning to 11 FPS at night. These results indicate that the system is capable of supporting real-time vehicle monitoring and parking access control, although its performance is still affected by lighting conditions, image quality, and the limitations of the ESP32CAM camera.
ANALISIS FAKTOR YANG MEMPENGARUHI PEMANFAATAN QRIS SEBAGAI ALAT PEMBAYARAN PADA UMKM: STUDI KASUS AREA WOSI MANOKWARI Stefan Johan Arnold Tirajoh; Andreas Leonardo Sumendap; Marlinda Sanglise
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 11, No 2 (2026)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v11i2.7815

Abstract

Tujuan dari studi ini adalah untuk menganalisis faktor-faktor yang memengaruhi pemanfaatan QRIS di kalangan UMKM di wilayah Wosi, Manokwari, melalui pendekatan TAM. Partial Least Squares Structural Equation Modeling (PLS-SEM) adalah metode yang digunakan dalam penelitian ini untuk menganalisis data yang dik-umpulkan dari 81 responden pelaku UMKM. Menurut temuan studi, Persepsi Kemudahan Penggunaan (PEOU) memiliki dampak yang signifikan terhadap Penggunaan Aktual QRIS (AU), Sikap terhadap Penggunaan (ATU), dan Persepsi Kegunaan (PU). Namun, PU hanya berpengaruh terhadap ATU tanpa memberikan dampak langsung pada AU. Hasil analisis nilai R-square menunjukkan kekuatan prediksi sedang untuk ATU (51,1%), AU (57,2%), dan PU (46,0%). Uji validitas diskriminan (HTMT < 0,90) dan reliabilitas (CR > 0,70; AVE > 0,50) memastikan bahwa model penelitian menunjukkan akurasi yang baik. Studi ini menekankan betapa pentingnya kemudahan penggunaan (ease of use) dalam pemanfaatan QRIS sebagai faktor utama. Berdasarkan temuan ini, rekomendasi praktis mencakup penyederhanaan antarmuka QRIS, pelatihan berbasis pengalaman langsung, dan pendampingan teknis berkelanjutan bagi UMKM. Penelitian ini memberikan kontribusi pada literatur adopsi teknologi digital dalam konteks regional dengan karakteristik yang unik serta memberikan arahan strategis bagi pemangku kebijakan untuk memperluas penerapan QRIS.
Co-Authors Abdul Zaid Patiran Celestina Florecita Mariwy Jakasurya Siswoyo Lorna Yertas Baisa Marlinda Sanglise Marsella Iriana Mamusung Natalya Sibarani Nur Rahmi Stefan Johan Arnold Tirajoh