Article Per Year (5 Year)
p-Index From 2021 - 2026
3.321
P-Index
This Author published in this journals
All Journal Voteteknika (Vocational Teknik Elektronika dan Informatika) Jurnal Edukasi dan Penelitian Informatika (JEPIN) JOIV : International Journal on Informatics Visualization JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Building of Informatics, Technology and Science Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Progresif: Jurnal Ilmiah Komputer Infotekmesin JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Jurnal Sistem Komputer dan Informatika (JSON) Jurnal Teknik Informatika (JUTIF) Jurnal Abdimas Bina Bangsa Jurnal INFOTEL Infact: Jurnal Sains dan Komputer
Sunneng Sandino Berutu
Universitas Kristen Immanuel
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Languange, Linguistic, Communication & Media Mathematics Mechanical Engineering Social Sciences Other

Published : 23 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 23 Documents
Search

 1   2   3 
Implementasi Fuzzy-VADER pada Analisis Sentimen Pengguna Terhadap Aplikasi Pinjaman Online Berutu, Sunneng Sandino
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol 10, No 3 (2024): Volume 10 No 3
Publisher : Program Studi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jp.v10i3.79741

Abstract

 Analisis sentimen merupakan sebuah pendekatan penting untuk memahami opini masyarakat dari data teks yang besar dan tidak terstruktur. Penelitian ini mengusulkan mtode inovatif dalam bidang analisis sentimen berbasis metode VADER dan fuzzy logic. Metode ini diimplementasikan pada pengukuran sentimen pengguna terhadap aplikasi pinjaman online (pinjol). Tahapan penelitian yang dilakukan, yaitu pertama, crawling data ulasan dari 6 (enam) aplikasi pinjol di play store. Kemudian, dilakukan data preprocessing. Selanjutnya, klasifikasi data ulasan menjadi tiga kategori sentimen seperti positif, negatif dan netral dengan metode VADER. Terakhir, implementasi metode fuzzy untuk memperoleh likert scale 5 (lima) kategori sentimen dengan nilai compound VADER. Hasil eksperimen dengan metode VADER, semua aplikasi pinjol memperoleh sentimen tertinggi pada kategori positif dengan persentase rata-rata sebesar 54,8%, disusul kategori negatif sebesar 27,7% dan netral sebesar 17,5%.  Sementara itu, implementasi dengan metode fuzzy, semua aplikasi pinjol memperoleh sentimen tertinggi pada kategori netral dengan persentase rata-rata sebesar 43%, disusul kategori positif sebesar 22,6%, kategori sangat positif sebesar 21%, kategori negatif sebesar 11,3% dan kategori sangat negatif sebesar 5%.  
KLASIFIKASI KALIMAT PERUNDUNGAN PADA TWITTER MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE Nauli, Sumitta; Berutu, Sunneng Sandino; Budiati, Haeni; Maedjaja, Febe
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 1 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i1.5749

Abstract

Cyberbullying menjadi masalah yang semakin serius, terutama dengan meningkatnya media sosial dan teknologi. Twitter adalah sebagai salah satu media digital yang kerap dijadikan ajang untuk memunculkan tekanan dari sesama pengguna. Dalam riset yang dilakukan, teknik Support Vector Machine (SVM) akan diterapkan untuk membuat klasifikasi terhadap tweet sebagai tujuannya. Crawling data digunakan untuk mengumpulkan data pelatihan, yang kemudian diproses dengan melakukan tokenisasi, pembersihan data, dan TF-IDF untuk pembobotan kata. Kata-kata yang membentuk sebuah frasa memiliki fungsi sebagai fitur. Untuk menentukan model klasifikasi yang ideal, teknik SVM dikembangkan dengan memanfaatkan beberapa jenis kernel dan parameter yang berbeda. Klasifikasi tweet dilakukan berdasarkan aspek fisik dan non-fisik. Dataset yang digunakan terdiri dari 2752 data, dengan 568 kategori bullying, 2183 kategori non bullying, dan 428 untuk aspek fisik, 132 untuk aspek non-fisik. Klasifikasi terbaik ditunjukkan melalui kernel Linear yang memiliki perbandingan 90:10, menghasilkan 89,47% akurasi, 57,14% recall, 100% presisi, serta 72,72% f1-score. Perolehan riset membuktikan yaitu nilai parameter tertentu dan model teknik SVM oleh esensi linear mahir mengklasifikasikan kalimat perundungan pada Twitter dengan akurasi yang tinggi. Penelitian ini memberikan kontribusi dalam upaya mendeteksi dan menangani perundungan siber pada platform media sosial.
RANCANG BANGUN SISTEM INFORMASI PEMAKAMAN DAN KREMASI DI TPU MADUREJO PRAMBANAN Budiati, Haeni; Sumihar, Yo’el Pieter; Berutu, Sunneng Sandino
Jurnal Abdimas Bina Bangsa Vol. 6 No. 1 (2025): Jurnal Abdimas Bina Bangsa
Publisher : LPPM Universitas Bina Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46306/jabb.v6i1.1595

Abstract

In the context of expanding housing developments, the issue of burial places has emerged as a contentious subject, giving rise to conflicts with local residents.On average, 70-80% of cemetery land has been occupied, a situation that has given rise to concerns among residents.In an effort to address this issue, the Sleman Regency Government has constructed the Public Cemetery, a facility that boasts an organised and planned architectural design, a dynamic layout, and a natural atmosphere characterised by beautiful hills. Presently, registration services, grave plot booking, cremation, and data collection of corpses are still conducted manually, a practice that is set to be streamlined by the implementation of a public cemetery information system. This web-based system, once implemented, is poised to bring about significant improvements in terms of efficiency, transparency, and accessibility in the management of funeral facilities.
Implementasi Text Mining Pada Pengukuran Sentimen Opini Masyarakat Terhadap Universitas Kristen Immanuel Indriyani Hulu; Haeni Budiati; Sunneng Sandino Berutu
Infact: International Journal of Computers Vol. 7 No. 02 (2023): Jurnal Sains dan Komputer
Publisher : Universitas Kristen Immanuel

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61179/jurnalinfact.v7i02.445

Abstract

Analisis sentimen merupakan suatu metode analisis yang bertujuan untuk mengidentifikasi emosi yang terkandung dalam teks, baik itu emosi positif, negatif, atau netral. Analisis sentimen, juga dikenal sebagai opinion mining, digunakan untuk mengekstrak emosi yang terdapat dalam tulisan orang-orang di berbagai platform media sosial. Data yang digunakan berasal dari twitter dimana twitter merupakan salah satu jejaring sosial yang interaktif dan banyak digunakan untuk dapat berbagi opini dan pendapat mengenai banyak hal. Penelitian dilakukan dengan menggunakan text mining dengan proses seperti crawling data, data cleaning, filtering, translating dan data splitting. Hasil analisis yang yang didapatkan dengan persentase sentimen positif 41.4%, persentase sentimen netral 45.5% dan persentase sentimen negatif 12.9%.
Implementasi Data Mining Untuk Menganalisis Pola Peminjaman Buku Perpustakaan Dengan Menggunakan Metode Apriori: Implementasi Data Mining Febe Maedjaja; Tri Yuli Yanto; Sunneng Sandino Berutu
Infact: International Journal of Computers Vol. 7 No. 02 (2023): Jurnal Sains dan Komputer
Publisher : Universitas Kristen Immanuel

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61179/jurnalinfact.v7i02.446

Abstract

The library is a place where you can find the information andknowledge you need. Library space is a very important means oforganizing book loans because it not only creates space and thenfills it with collections, but also pays attention to how the layout ofthe books is arranged. Therefore, the data is analyzed in order tohelp recommend the layout of books and borrowers can find theappropriate books. To determine the suggestion of borrowedbooks, with the existence of play data can use the a priorialgorithm, a kind of association rule. The market basket analysismethod used by the a priori algorithm to establish associationsbetween various variables allows the system to further analyze andidentify trends related to borrowed books. Based on the results ofthe analysis that has been carried out, it is stated that this a priorialgorithm can be used to display recommendations betweenborrowed books. The support value can show the classification ofbooks borrowed simultaneously while the confidence value canfind out the recommendations for books borrowed.
Aspect-Based Sentiment Analysis Using Latent Dirichlet Allocation (LDA) and DistilBERT on Threads App Reviews Kambayo, Andreas Noprianto Kambayo; Berutu, Sunneng Sandino; Jatmika, Jatmika; Nshimiyimana, Aristophane
Infact: International Journal of Computers Vol. 9 No. 01 (2025): International Journal of Computers
Publisher : Universitas Kristen Immanuel

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61179/infact.v9i01.707

Abstract

Threads is a social media application that offers news services and user interaction, integrated with Instagram. Unlike other platforms, Threads does not have features like direct messaging (DM), trending topics, or advertisements. To understand users' opinions about this app, a sentiment analysis based on aspects was conducted on Threads reviews. The steps involved include applying web scraping techniques to collect reviews data from the Play Store. Aspect categories were identified using the Latent Dirichlet Allocation (LDA) algorithm. Sentiment labeling was then performed for positive and negative categories using the DistilBERT method. The results show that the LDA algorithm identified three aspects: Usage and Integration (with 3.147 positive and 8.173 negative reviews), Features and Comparisons (with 1.108 positive and 1.709 negative reviews), and User Experience and Satisfaction (with 3.529 positive and 2.208 negative reviews). The sentiment analysis results indicated 7,784 positive reviews and 12,090 negative reviews. Model performance evaluation using the Confusion Matrix showed an accuracy of 96.71%, precision of 97.24%, recall of 94.48%, and F1-score of 95.84%. Evaluation was also conducted for each aspect, with an accuracy of 96.99%, precision of 96.60%, recall of 92.85%, and F1-score of 94.69% for the Usage and Integration aspect; accuracy of 95.74%, precision of 94.11%, recall of 95.23%, and F1-score of 94.67% for the Features and Comparisons aspect; and accuracy of 96.74%, precision of 95.83%, recall of 99.06%, and F1-score of 97.42% for the User Experience and Satisfaction aspect.
Pemodelan Topik pada Ulasan Google Maps Candi Borobudur Menggunakan Latent Dirchlet Allocation Reonardh Sibarani; Sunneng Sandino Berutu; Kristian Juri Damai Lase; Jatmika Jatmika
Voteteknika (Vocational Teknik Elektronika dan Informatika) Vol 12, No 3 (2024): Vol. 12, No 3, September 2024
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/voteteknika.v12i3.129028

Abstract

Penelitian ini bertujuan untuk menggali wawasan yang mendalam dari ulasan Google Maps wisatawan tentang Candi Borobudur menggunakan metode Pemodelan Topik Latent Dirichlet Allocation(LDA). Candi Borobudur, salah satu situs warisan dunia yang terkenal di Indonesia, menerima banyak ulasan dari wisatawan yang berbeda-beda. Namun, untuk mengidenfikasi tren, preferensi, dan aspek yang paling penting bagi pengunjung, diperlukan analisis yang lebih dalam. Dengan menggunakan pendekatan LDA, mengelompokkan ulasan-ulasan ini kedalam topik-topik latensial yang memungkinkan untuk mengeksplorasi pola-pola umum dan perbedaan-perbedaan dalam persepsi dan pengalaman pengunjung terhadap Candi borobudur. Proses pemodelan topik ini mencakup beberapa langkah, dimulai dari persiapan data, pra-pemrosesan data, wordcloud, topic coherence serta pemodelan topik. Adapun nilai koherensi paling baik diperoleh dalam model Latent dirichlet allocation (LDA) adalah topik terbaik dengan jumlah 4 topik. Sedangkan dari hasil analisis pemodelan topik pada metode Latent dirichlet allocation (LDA) pada Kata "candi" (0.050883695), "borobudur" (0.02406518), "tiket" (0.018967053), dan "masuk" (0.018507887), menyoroti fokus pada aspek kuil, aksesibilitas, dan biaya masuk. Kata "jalan" (0.012353696) dan "parkir" (0.011362941) menunjukkan perhatian terhadap infrastruktur, sementara "area" (0.01039175) mengacu pada lingkungan sekitar candi. Istilah "rb" (0.009597249) dan "harga" (0.0092093265) merujuk pada biaya dalam rupiah, dan "beli" (0.008586656) terkait dengan pembelian tiket. Hasil ini memberikan wawasan tentang fokus utama dalam pembahasan Borobudur, mencakup kuil, aksesibilitas, infrastruktur, dan biaya.Kata kunci: Google Maps, Pemodelan Topik, Latent Dirichlet Alloation(LDA), Nilai Koherensi This research aims to extract deep insights from tourists' Google Maps reviews of Borobudur Temple using the Latent Dirichlet Allocation (LDA) Topic Modeling method. Borobudur Temple, one of the famous world heritage sites in Indonesia, receives many reviews from different tourists. However, to identify trends, preferences, and aspects that are most important to visitors, a deeper analysis is required. Using the LDA approach, categorizing these reviews into latent topics makes it possible to explore common patterns and differences in visitors' perceptions and experiences of Borobudur Temple. This topic modeling process includes several steps, starting from data preparation, data pre-processing, wordcloud, topic coherence and topic modeling. The best coherence value obtained in the Latent dirichlet allocation (LDA) model is the best topic with a total of 4 topics.. While based on the results of the analysis of topic modeling with the Latent dirichlet allocation (LDA) method on Borobudur reviews get 4 topic models The best coherence value obtained in the Latent dirichlet allocation (LDA) model is the best topic with a total of 4 topics. While from the results of the topic modeling analysis on the Latent dirichlet allocation (LDA) method on the words “temple” (0.050883695), “borobudur” (0.02406518), “ticket” (0.018967053), and “entrance” (0.018507887), highlighting the focus on aspects of the temple, accessibility, and entrance fees. The words “road” (0.012353696) and “parking” (0.011362941) indicate attention to infrastructure, while “area” (0.01039175) refers to the temple's surroundings. The terms “rb” (0.009597249) and “harga” (0.0092093265) refer to costs in rupiah, and “beli” (0.008586656) is related to ticket purchases. These results provide insight into the main focus of the Borobudur discussion, covering temples, accessibility, infrastructure, and costs.Keywords: Google maps, topic modelling, Latent Dirichlet Alloation(LDA), Coherence Score
Analisis Sentimen Aplikasi Lion Parcel Menggunakan Lexicon Based dan Support Vector Machine Bobby Girsang; Sunneng Sandino Berutu; Haeni Budiati; Febe Maedjaja
Voteteknika (Vocational Teknik Elektronika dan Informatika) Vol 12, No 3 (2024): Vol. 12, No 3, September 2024
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/voteteknika.v12i3.129033

Abstract

Dengan adanya perkembangan teknologi digital pada masa kini, masyarakat dapat melakukan pengiriman barang jarak jauh dengan lebih mudah dan efisien. Lion parcel merupakan salah satu aplikasi ekpedisi populer yang melayani pengiriman barang. Penelitian ini dilakukan untuk mengukur sentimen yang diberikan oleh para pengguna aplikasi terhadap jasa ekspedisi dari Lion Parcel. Proses analisis sentimen ini dilakukan melalui tahapan pengumpulan data, preprocessing data, labelling data menggunakan pendekatan berbasis lexicon, dan membangun model klasifikasi berbasis algoritma Support Vector Machine (SVM) melalui tahap pelatihan dan pengujian data, dan evaluasi model dengan confusion matrix. Data yang berhasil dikumpulkan melalui scrapping data dari ulasan aplikasi Lion Parcel pada google play store mencapai 1194 ulasan. Hasil yang didapatkan setelah memproses data yang diambil yaitu sentimen positif mencapai 55.51 % dengan jumlah 630 data. Sentimen netral mencapai 24.76% dengan jumlah 281 data. Sentimen negatif mencapai 19.74% dengan jumlah 224 data. Hasil pengujian SVM juga menghasilkan nilai akurasi, presisi, recall dan f1-score tertinggi berturut turut sebesar 77.78%, 85%, 94% dan 89%.Kata kunci : Lion Parcel, SVM, sentimen, Lexicon Based. With the advancement of digital technology today, people can deliver long-distance goods more easily and efficiently. Lion parcel is one of the popular expedition applications that serves the delivery of goods. The research was conducted to measure the sentiment given by the users of the application to the Lion Parcel's expedition services. This sentiment analysis process is carried out through stages of data collection, data preprocessing, data labelling using lexicon-based approaches, and building an algorithm-based classification model based on the Support Vector Machine (SVM) through training and data testing stages, and model evaluation with a confusion matrix. The data collected successfully through scrapping data from the review of the Lion Parcel app on the google play store reached 1194 reviews. The results obtained after processing the data taken are positive sentiment reached 55.51% with a total of 630 data. Neutral feeling reached 24.76% with the total of 281 data. Negative feelings reached 19.74% with 224 data. SVM test results also yielded the highest accuracy, precision, recall and f1 scores in a row of 77.78%, 85%, 94% and 89%.Keywords: Lion Parcel, SVM, Sentiment, Lexicon Based.
Hybrid Time-Series Approaches for PV Power Prediction: Evaluating SARIMAX and Generative Model Berutu, Sunneng Sandino; Zakaria, Immanuel Richie De Harjo; Yuan, Anita; Rahman, Mosiur
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 4 (2025): JUTIF Volume 6, Number 4, Agustus 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.4.4955

Abstract

Forecasting the output power of photovoltaic (PV) systems is crucial in managing renewable energy efficiently and sustainably. The availability of historical data and environmental variables, such as temperature and humidity, greatly influences prediction accuracy. However, in practice, historical data is often incomplete due to technical constraints or limited monitoring infrastructure, which results in decreased prediction quality and system efficiency. To overcome these challenges, this study proposed a comparative approach between two predictive models, namely SARIMAX (Seasonal AutoRegressive Integrated Moving Average with eXogenous variables) as a classical statistical model, and WGAN-GP (Wasserstein Generative Adversarial Network with Gradient Penalty) as a generative deep learning model designed to handle incomplete data and capture nonlinear relationships. The datasets included PV power output from the monitoring system at Universitas Kristen Immanuel (UKRIM) Yogyakarta, along with temperature and humidity data from the Kalitirto weather station in Sleman, Yogyakarta. The research was conducted through several stages, namely: data collection, pre-processing, model training, and evaluation using MAE, MSE, RMSE, and MAPE metrics. The results show that the SARIMAX model using the Time-Series Cross-Validation (TSCV) achieves the best numerical performance (MAE = 0.085; RMSE = 0.145). However, this model fails to represent daily patterns realistically. In contrast, both the standard SARIMAX and WGAN-GP models are more consistent in representing seasonal patterns and daily fluctuations, even though their prediction errors were slightly higher in terms of numerical metrics. The findings advance scientific understanding of hybrid forecasting models and offer practical implications for improving energy reliability and decision-making in data-constrained environments.
Analisis Sentimen Opini Masyarakat Terhadap Presiden Jokowi Sebelum Dan Sesudah Pilpres 2024 Menggunakan Metode Naive Bayes Classification Nehe, Pius Hermanto; Berutu, Sunneng Sandino; Budiati, Haeni
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol 13, No 1: April 2024
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v13i1.1841

Abstract

The 2024 presidential election in Indonesia is an important moment in political dynamics. This research analyzes changes in public sentiment towards President Jokowi before and after the 2024 Presidential Election using the naive bayes classification method. Datasets consist of 10,014 tweets that have gone through the process of crawling, preprocessing, translating, labeling, classification, and model evaluation. The analysis results show that before the 2024 presidential election, positive sentiment reached 41.17%, neutral sentiment 34.30%, and negative sentiment 24.53%. After the 2024 presidential election, positive sentiment decreased to 39.08%, neutral sentiment increased to 37.59%, and negative sentiment decreased to 23.33%. Prediction accuracy increased to 64 and neutral sentiment had a precision of 88, with a dataset focusing on President Jokowi after the 2024 Presidential Election, while recall for positive sentiment was 87, and f1-score for neutral sentiment was 69, with a dataset of President Jokowi before the 2024 Presidential Election. Keywords: Presiden Jokowi; Public opinion dynamics; Naive Bayes Classification; Presidential Election 2024; Sentiment AbstrakPemilihan Presiden 2024 di Indonesia merupakan momen penting dalam dinamika politik. Penelitian ini menganalisis perubahan sentimen publik terhadap Presiden Jokowi sebelum dan sesudah Pilpres 2024 dengan menggunakan metode klasifikasi naive bayes. Datasets terdiri dari 10.014 tweets yang telah melalui proses crawling, preprocessing, translating, labeling, classification, dan evaluation model. Hasil analisis menunjukkan bahwa sebelum Pilpres 2024, sentimen positif mencapai 41,17%, sentimen netral 34,30%, dan sentimen negatif 24,53%. Setelah Pilpres 2024, sentimen positif menurun menjadi 39,08%, sentimen netral meningkat menjadi 37,59%, dan sentimen negatif menurun menjadi 23,33%. Akurasi prediksi meningkat menjadi 64 dan Sentimen netral memiliki precision 88, dengan dataset yang berfokus pada Presiden Jokowi setelah pelaksanaan Pilpres 2024, sementara recall untuk sentimen positif adalah 87, dan f1-score untuk sentimen netral adalah 69, dengan dataset Presiden Jokowi sebelum Pilpres 2024.
Co-Authors Bobby Girsang Chen, Yeong-Chin Dachi, Christian Moris Febe Maedjaja Febe Maedjaja Fornieli Gulo Haeni Budiati Heri Wijayanto Indriyani Hulu Jatmika Jatmika Jatmika Jatmika Jatmika Jatmika, Jatmika Jatmitka, Jatmitka Juli Supriyanto Gea Kambayo, Andreas Noprianto Kambayo Kristian Juri Damai Lase Laia, Yardiana Lase, Anan Sosmita Nauli, Sumitta Nehe, Pius Hermanto Nshimiyimana, Aristophane Rahman, Mosiur Reonardh Sibarani Sispianygala, Aprilia Sumihar, Yo’el Pieter Tri Elsa, Maria Tri Yuli Yanto Veren, Yolanda Yuan, Anita Zakaria, Immanuel Richie De Harjo Zendrato, Agus Dirgahayu