Article Per Year (5 Year)
p-Index From 2021 - 2026
3.535
P-Index
This Author published in this journals
All Journal JURNAL SISTEM INFORMASI BISNIS MATICS : Jurnal Ilmu Komputer dan Teknologi Informasi (Journal of Computer Science and Information Technology) JIKO (Jurnal Informatika dan Komputer) METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Compiler TELEKONTRAN: Jurnal Ilmiah Telekomunikasi, Kendali dan Elektronika Terapan Jurnal Abdimas PHB : Jurnal Pengabdian Masyarakat Progresif Humanis Brainstorming Bakti Cendana: Jurnal Pengabdian Masyarakat Mitra Mahajana: Jurnal Pengabdian Masyarakat Jurnal Dialektika Informatika (Detika) HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi Journal of Informatics Management and Information Technology Jurnal Saintekom : Sains, Teknologi, Komputer dan Manajemen Jurnal Sisfotek Global J-Icon : Jurnal Komputer dan Informatika Jurnal Inovatif Wira Wacana
Sebastianus Adi Santoso Mola
Universitas Nusa Cendana
Agriculture, Biological Sciences & Forestry Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemistry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Mechanical Engineering Nursing Public Health Social Sciences

Published : 30 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 30 Documents
Search

 1   2   3 
Analisis Sentimen Sunscreen Azarine dengan Naïve Bayes di Toko Aneka Kosmetik Kupang pada Marketplace Shopee Sain, Adriana Yohana; Mola, Sebastianus Adi Santoso; Huan, Arni Yusfin; Nomleni, Inggi Rosina
Jurnal Saintekom : Sains, Teknologi, Komputer dan Manajemen Vol 15 No 1 (2025): Maret 2025
Publisher : STMIK Palangkaraya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33020/saintekom.v15i1.783

Abstract

Advancements in information and communication technology have changed the way customers shop and share experiences through reviews. Marketplaces like Shopee allow customers to rate products through reviews, making sentiment analysis crucial for understanding consumer perceptions. The Naïve Bayes algorithm is used in this study to analyze 3,504 reviews of the Azarine sunscreen product from Aneka Kosmetik Kupang on Shopee, followed by a text preprocessing process. The dataset is then split into 80% for training and 20% for testing, with reviews categorized into three sentiment classes: positive, negative, and neutral. Evaluation with a Confusion Matrix resulted in an accuracy of 84%, demonstrating the reliability of this algorithm in analyzing customer reviews. The findings of this study offer fresh perspectives for brand owners and potential buyers regarding public perception of the Azarine sunscreen product at Aneka Kosmetik Kupang.
Sentiment Analysis on User Reviews of the Edlink Application Using the Random Forest Classifier Method Mola, Sebastianus Adi Santoso; Polly, Dian Putri Novita; Rumlaklak, Nelcy D.
JURNAL SISFOTEK GLOBAL Vol 15, No 1 (2025): JURNAL SISFOTEK GLOBAL
Publisher : Institut Teknologi dan Bisnis Bina Sarana Global

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38101/sisfotek.v15i1.15788

Abstract

Edlink is a learning platform developed by PT. Sentra Vidya Utama (SEVIMA), established in 2004. Although it offers useful features, some aspects need improvement based on user reviews on Google Play Store. This study aims to accurately classify user sentiment to identify areas that need enhancement. The main challenges include language diversity, sentiment class imbalance, and the need for a reliable classification method. The random forest classifier method was chosen for its ability to handle overfitting and optimize performance. The dataset consists of 1,117 reviews divided into three classes: 385 negative, 118 neutral, and 614 positive. Data was collected through web scraping and processed using cleaning, normalization, tokenizing, stemming, negation conversion, and stopword removal, then weighted using TF-IDF. Testing results showed an accuracy of 86% using 5-Fold cross-validation and SMOTE. The 10-Fold cross-validation test demonstrated that this method outperforms other classification methods with 90% accuracy.
Rancang Bangun Sistem Informasi Akademik Berbasis Website untuk Meningkatkan Infrastruktur dan Kualitas Kinerja Tenaga Kependidikan Taman Kanak-kanak (TK) Kristen Gereja Masehi Injili di Timor (GMIT) Silo Kota Kupang Gloria, Ayuntha; Mola, Sebastianus Adi Santoso; Polly, Dian Putri Novita; Leobisa, Elisabeth Ester Eunike
Bakti Cendana Vol 6 No 2 (2023): Bakti Cendana: Jurnal Pengabdian Masyarakat
Publisher : LPPM Universitas Timor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32938/bc.6.2.2023.119-128

Abstract

Sistem informasi telah diterapkan dalam segala bidang kehidupan termasuk dalam bidang Pendidikan. Salah satu contoh penerapan sistem informasi yaitu pembuatan sistem informasi akademik bagi institusi pendidikan. Taman kanak-kanak (TK) Kristen Gereja Masehi Injili di Timor (GMIT) Silo belum memiliki sistem informasi akademik. Hal ini menyebabkan proses pengelolaan data masih di tulis pada sebuah buku induk anak didik. Selain itu, TK Kristen GMIT Silo juga mengalami kesulitan dalam proses penerimaan siswa baru. TK Kristen GMIT Silo masih memberikan informasi mengenai penerimaan peserta didik baru melalui gereja sebagai sarana promosi. Tujuan dari kegiatan pengabdian ini untuk membangun sebuah sistem informasi akademik bagi TK Kristen GMIT Silo berbasis website, meningkatkan kulitas kinerja dari para guru dan membangun infrastruktur. Kegiatan pengabdian ini dimulai dari analisis kebutuhan, pembangunan sistem dan implementasi serta pelatihan bagi pihak sekolah .Hasil dari kegiatan pengabdian ini berupa sebuah sistem informasi akademik berbasis website yang mampu mengelola data anak didik, data penilaian hasil belajar anak didik dan mengelola penerimaan calon peserta didik secara online serta memberikan pelatihan bagi pihak TK Kristen GMIT Silo agar dapat mengoperasikan sistem informasi akademik tersebut secara mandiri.
Implementation of the Psychological Scale Depression Anxiety Stress Scale 21 (Dass-21) in the Expert System for Diagnosing Mental Health Disorder Mola, Sebastianus Adi Santoso; Melly, Margaretha Delima; Yublina Pandie, Emerensye Sofia
Compiler Vol 13, No 1 (2024): May
Publisher : Institut Teknologi Dirgantara Adisutjipto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28989/compiler.v13i1.1938

Abstract

Mental health is something that needs to be considered properly because if the mental is disturbed then the body also feels the impact. Mental health disorders including depression, stress, and anxiety can affect anyone, especially students. Due to the lack of awareness of mental health in students and the minimal number of clinical psychologists in Indonesia, students are reluctant to see a psychologist. The existence of an expert system for early detection of mental health disorders using the Depression Anxiety Stress Scale (DASS-21) with 21 symptoms can help students analyse the level of mental health disorders which are divided into depression, stress, and anxiety. The results of the study based on 100 student data of Nusa Cendana University obtained the system can diagnose mental health disorders including depression, stress, and anxiety with an accuracy rate of expert and system results of 100% which shows that the implementation of the DASS-21 instrument into the system is correct. Findings from the diagnosis results show that most students (70%) suffer from anxiety in the moderate to severe category. However, special attention needs to be paid to students who suffer from moderate to severe depression (37%) and severe to moderate stress (36%).
Analisis Sentimen Masyarakat Terhadap Pelayanan Jasa Ekspedisi JNE dan J&T Express Menggunakan Metode Lexicon-Based Mola, Sebastianus Adi Santoso; Mbatu, Dinda Permata; Sihotang, Dony Martinus
METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 9 No. 1 (2025): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/jmika.Vol9No1.pp56-65

Abstract

JNE and J&T Express are two of the largest and most popular courier companies in Indonesia, leading to various public opinions regarding the quality of their services. This research employs a lexicon-based method using the InSet dictionary, a simple scientific approach where the system calculates the weight of words and classifies them as positive, negative, or neutral sentiments. The analysis process begins with data collection of reviews using scraping techniques, followed by text processing including cleaning, case folding, normalization, tokenization, stemming, and stopword removal. Out of 3,565 reviews for JNE and 3,967 reviews for J&T, the sentiment analysis indicates that the majority of the public holds negative opinions towards the services of both courier companies. The analysis accuracy reaches 82% for JNE data, with a precision value of 95% for negative sentiment, 54% for positive sentiment, and 7% for neutral sentiment. The sensitivity values are 83% for negative sentiment, 82% for positive sentiment, and 15% for neutral sentiment. Data for J&T shows an accuracy of 78%, with a precision value of 97% for negative sentiment, 28% for positive sentiment, and 4% for neutral sentiment. Sensitivity values are 80% for negative sentiment, 82% for positive sentiment, and 4% for neutral sentiment.
Perbandingan Arsitektur ResNet50V2, InceptionV3, dan DenseNet121 dalam Klasifikasi Pengenalan Ekspresi Wajah Mola, Sebastianus Adi Santoso; Wadu, Benyamin Orison Darling Kana; Kenlopo, Asnat Nofri; Tungga, Varra Chandrika Kumara
JURNAL INFORMATIKA DAN KOMPUTER Vol 9, No 2 (2025): Juni 2025
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat - Universitas Teknologi Digital Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26798/jiko.v9i2.1584

Abstract

Ekspresi wajah mampu menyampaikan perasaan seseorang, seperti kebahagiaan, kesedihan, atau kemarahan. Meski manusia secara alami mampu mengenali ekspresi wajah, pengklasifikasian ekspresi sering kali menjadi tantangan. Dengan kemajuan teknologi, analisis dan klasifikasi ekspresi wajah kini dapat dilakukan secara otomatis menggunakan pembelajaran mesin, terutama pada metode Convolutional Neural Network (CNN) seperti ResNet50V2, InceptionV3, dan DenseNet121. Penelitian ini bertujuan untuk membandingkan kemampuan dan efisisensi dari tiga model arsitektur CNN yaitu ResNetV50, InceptionV3, dan DenseNet121 dalam klasifikasi pengenalan ekspresi wajah. Penelitian ini menggunakan dataset ekspresi wajah berjumlah 14.248 gambar yang terbagi menjadi lima kelas: bahagia, marah, netral, sedih, dan terkejut. Data dibagi menjadi 80% untuk pelatihan dan 20% untuk validasi. Hasil evaluasi menunjukkan bahwa ResNet50V2 memberikan performa terbaik dengan akurasi 79%, macro average F1-score 0,76, dan weighted average F1-score 0,75. Model ini unggul dalam menangani distribusi data tidak merata, terutama pada kelas dominan seperti Happy dan Neutral. DenseNet121 menempati posisi kedua dengan akurasi 75%, diikuti oleh InceptionV3 dengan akurasi terendah 65%. ResNet50V2 terbukti sebagai model yang paling efektif untuk klasifikasi ekspresi wajah
Comparison of Linear Regression, Decision Tree Regression, and Random Forest Regression Algorithms in Predicting Baldness Risk Mola, Sebastianus Adi Santoso; Goru, Alfonsus Maria De Liguori; Lamapaha, Christian Jaquelino; Bekayo, Yoseph Kurubingan
MATICS: Jurnal Ilmu Komputer dan Teknologi Informasi (Journal of Computer Science and Information Technology) Vol 17, No 2 (2025): MATICS
Publisher : Department of Informatics Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/mat.v17i2.30256

Abstract

Abstract—Baldness is a common condition affecting both men and women, primarily caused by age, hormones, and genetics. Predicting the risk of baldness is crucial for early diagnosis and prevention of further hair loss. This study aims to compare the performance of Linear Regression (LR), Decision Tree Regression (DTR), and Random Forest Regression (RFR) in predicting baldness risk using data with variables such as age, gender, occupation, stress levels, and other lifestyle factors. A dataset of 5925 samples was processed through a series of steps, including normalization, parameter tuning, cross-validation, and residual analysis. The results show that Random Forest Regression outperformed other models with the lowest MSE (0.0979) and the highest R² (0.9056) on both training and testing data, followed by Decision Tree Regression and Linear Regression. Hyperparameter optimization using Grid Search significantly enhanced model performance. In conclusion, Random Forest Regression is the most suitable model for predicting baldness risk with complex datasets, while Linear Regression remains a viable alternative for simpler datasets.
Analisis Sentimen Masyarakat Terhadap Pelayanan Jasa Ekspedisi JNE dan J&T Express Menggunakan Metode Lexicon-Based Mola, Sebastianus Adi Santoso; Mbatu, Dinda Permata; Sihotang, Dony Martinus
METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 9 No. 1 (2025): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/jmika.Vol9No1.pp56-65

Abstract

JNE and J&T Express are two of the largest and most popular courier companies in Indonesia, leading to various public opinions regarding the quality of their services. This research employs a lexicon-based method using the InSet dictionary, a simple scientific approach where the system calculates the weight of words and classifies them as positive, negative, or neutral sentiments. The analysis process begins with data collection of reviews using scraping techniques, followed by text processing including cleaning, case folding, normalization, tokenization, stemming, and stopword removal. Out of 3,565 reviews for JNE and 3,967 reviews for J&T, the sentiment analysis indicates that the majority of the public holds negative opinions towards the services of both courier companies. The analysis accuracy reaches 82% for JNE data, with a precision value of 95% for negative sentiment, 54% for positive sentiment, and 7% for neutral sentiment. The sensitivity values are 83% for negative sentiment, 82% for positive sentiment, and 15% for neutral sentiment. Data for J&T shows an accuracy of 78%, with a precision value of 97% for negative sentiment, 28% for positive sentiment, and 4% for neutral sentiment. Sensitivity values are 80% for negative sentiment, 82% for positive sentiment, and 4% for neutral sentiment.
Perbandingan Metode Machine Learning dalam Analisis Sentimen Komentar Pengguna Aplikasi InDriver pada Dataset Tidak Seimbang Mola, Sebastianus Adi Santoso; Luttu, Yufridon Charisma; Rumlaklak, Dessy Nelci
Jurnal Sistem Informasi Bisnis Vol 14, No 3 (2024): Volume 14 Nomor 3 Tahun 2024
Publisher : Diponegoro University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21456/vol14iss3pp247-255

Abstract

The InDriver service is an online transportation service that has more flexibility in price and driver choice by consumers. Various comments from InDriver service users can affect people's views, so it is necessary to carry out a sentiment analysis of these comments. The purpose of this study was to identify positive, negative and neutral sentiments in user comments and to compare the performance of classification methods. The results of analysis with unbalanced datasets show that the Support Vector Machine (SVM) and Logistic Regression methods have the highest accuracy, reaching 89%. However, quality assessment is not only based on accuracy alone. In terms of the balance between precision and recall in the minority (neutral) class, the Random Forest method shows a more balanced performance with an F1-score of 55%. After balancing the dataset with the SMOTE method, performance increases significantly for the Naïve Bayes Classifier method, especially in the neutral class for recall and F1-score metrics of 57% and 52%. In conclusion, SVM and Logistic Regression have high accuracy, but to consider the balance of precision and recall in the minority class, the Random Forest method is recommended.
Analisis Sentimen Terhadap Data Komentar Publik Mengenai Isu UU Pilkada 2024 Menggunakan Metode Naïve Bayes dan K-Nearest Neighbor Sebastianus Adi Santoso Mola; Yulianto Triwahyuadi Polly; Atok, Yosefa Carela
Journal of Informatics Management and Information Technology Vol. 5 No. 3 (2025): July 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jimat.v5i3.514

Abstract

The 2024 Regional Head Election Law (UU Pilkada) has become an important issue widely discussed in Indonesia, especially on the social media platform X. Various public comments related to this issue contain positive, negative, and neutral sentiments, reflecting public perceptions. This study aims to analyze the sentiment of public comments on the 2024 UU Pilkada using two machine learning methods: Naïve Bayes and K-Nearest Neighbor (K-NN). The dataset consists of 3864 comments divided into three sentiment classes: 1477 negative comments, 1385 neutral comments, and 1002 positive comments, all of which have undergone text preprocessing. Evaluation was conducted using k-fold cross-validation (k=10). The test results show that the Naïve Bayes method achieves the highest accuracy of 63.47%, while K-NN reaches 56.73%. The precision for negative sentiment is 56.84%, meaning that about 43% of the comments predicted as negative by the model are actually not negative. The recall for negative sentiment is 45.45%, indicating that the model only captures less than half of the actual negative comments. For neutral sentiment, the precision of 60.71% and recall of 66.23% suggest that the model performs fairly well in recognizing neutral comments, although there is still a 39.29% error. For positive sentiment, the precision of 55.55% and recall of 57.63% indicate errors in classifying positive comments. Overall, while the model can correctly classify a portion of the data, there is potential to improve accuracy for both the negative and positive classes.
Co-Authors Abdul G Farid Adelysa P Gitaswara Adriana Fanggidae Adriana Fanggidae Arfan Y Mauko Atok, Yosefa Carela Baun, Diandra Lyan Bethseba Bekayo, Yoseph Kurubingan Boru, Meiton Clarissa Elfira Amos Pah Dwi Prasetyo Elfrida Veranda Beka Dede Emerensiana S.Y Pandie Emerensye S. Y. Pandie Emerensye Sofia Yublina Pandie Febryan Cornelis Lomi Finit, Awi Susanto Giri, Imanuel Raja Gloria, Ayuntha Goru, Alfonsus Maria De Liguori Huan, Arni Yusfin Jakha Rama Phosa Juan Rizky Mannuel Ledoh Juliet Reinita Angelia Lao Kase, Bernardino Antonius Kenlopo, Asnat Nofri Kornelis Letelay Lamapaha, Christian Jaquelino Leobisa, Elisabeth Ester Eunike Luttu, Yufridon Charisma Mbatu, Dinda Permata Meiton Boru Melly, Margaretha Delima N.A.Manbait, Yoseph D’Timor Nelci D Rumlaklak Nomleni, Inggi Rosina Novi Penna Nunes, Ingratcia Oktaviana Polly, Dian Putri Novita Prityaningsih, Ni Putu Dana Rassa, Delfiana M Romy O. D. Djami Roswita R Ligoresi Rumlaklak, Dessy Nelci Rumlaklak, Nelci D. Rumlaklak, Nelcy D. Sain, Adriana Yohana Sani, Michelle Maria Angely Rani Saragih, Alexandro Eurico Yosafat Sihotang, Dony Martinus Sitepu, Rasional Sonlay, Febronia B Ssainah P Faransyah Sultani, Akhzan Akbar Tiwuk Widiastuti Tokan, Diana Inda Carmilla Tungga, Varra Chandrika Kumara Viani Anika Afeanpah Wadu, Benyamin Orison Darling Kana Yelly Y Nabuasa Yelly Yosiana Nabuasa Yelly Yosiana Nabuasa Yublina Pandie, Emerensye Sofia Yulianto Triwahyuadi Polly Yulianto Triwahyuadi Polly