Article Per Year (5 Year)
p-Index From 2021 - 2026
4.14
P-Index
This Author published in this journals
All Journal IKRA-ITH Informatika : Jurnal Komputer dan Informatika Jurnal Review Pendidikan dan Pengajaran (JRPP) REMIK : Riset dan E-Jurnal Manajemen Informatika Komputer Frontiers JOINTER : Journal of Informatics Engineering Journal La Multiapp Indonesian Journal of Innovation Studies Jurnal Minfo Polgan (JMP) International Journal of Information Techonology and Education (IJITE) Journal of Artificial Intelligence and Digital Business The Indonesian Journal of Computer Science semanTIK Edutik : Jurnal Pendidikan Teknologi Informasi dan Komunikasi Journal of Vocational, Informatics and Computer Education Academia Open
Efraim R. S. Moningkey
Universitas Negeri Manado
Aerospace Engineering Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Public Health Social Sciences Other

Published : 33 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 33 Documents
Search

 1   2   3   4 
Deteksi Ujaran Kebencian Pada Media Sosial Terkait Pemilu 2024 Menggunakan Algoritma Naive Bayes Adesyan Lahinda; Irene R.H.T. Tangkawarow; Efraim R.S. Moningkey
Jurnal Minfo Polgan Vol. 14 No. 2 (2025): Artikel Penelitian
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/jmp.v14i2.15665

Abstract

Pemilu 2024 memiliki peranan yang sangat krusial dalam sistem demokrasi Indonesia, terutama karena didominasi oleh pemilih muda yang aktif menggunakan media sosial sebagai alat komunikasi politik. Namun, kondisi ini juga menghadirkan tantangan besar, terutama dengan meningkatnya penyebaran ujaran kebencian yang dapat dianggap sebagai pelanggaran Pemilu. Konten semacam ini terus meningkat, berpotensi merusak citra dan kualitas Pemilu serta mengganggu proses demokrasi. Meskipun ujaran kebencian telah diatur dalam Undang-Undang Pemilu dan Undang-Undang Informasi dan Transaksi Elektronik (ITE), pengawasan secara manual masih sulit dilakukan karena banyaknya konten yang beredar di media sosial. Penelitian ini bertujuan untuk mendeteksi ujaran kebencian sebagai pelanggaran Pemilu 2024 di media sosial dengan menggunakan metode Naïve Bayes. Dataset yang digunakan terdiri dari 408 komentar dari Twitter dan 445 komentar dari YouTube. Data tersebut dikategorikan ke dalam dua kelompok, yaitu ujaran kebencian dan non-ujaran kebencian, kemudian diuji secara otomatis dan manual. Hasil penelitian menunjukkan bahwa model mencapai akurasi 100% untuk data Twitter dan YouTube pada pengujian otomatis, sedangkan pengujian manual memperoleh akurasi 95,00% untuk Twitter dan 92,59% untuk YouTube.
Website Klasifikasi Kepuasan Pengguna Layanan Teknik Informatika Menggunakan K-Means Clustering Dea Karlina Pali; Audy Aldrin Kenap; Efraim Ronald S. Moningkey
Jurnal Minfo Polgan Vol. 15 No. 1 (2026): Artikel Penelitian
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/jmp.v15i1.16163

Abstract

Evaluasi tingkat kepuasan pengguna terhadap layanan akademik berbasis web menjadi salah satu faktor penting dalam upaya peningkatan kualitas pelayanan di Jurusan Teknik Informatika Universitas Negeri Manado (UNIMA). Permasalahan yang dihadapi adalah proses evaluasi layanan yang masih dilakukan secara manual sehingga hasil penilaian belum mampu memberikan informasi yang terstruktur dan akurat sebagai dasar pengambilan keputusan. Penelitian ini bertujuan untuk merancang dan membangun website klasifikasi tingkat kepuasan pengguna layanan dengan menerapkan algoritma K-Means Clustering sebagai metode analisis data. Metode pengembangan sistem yang digunakan adalah Rapid Application Development (RAD), sedangkan penentuan jumlah cluster optimal dilakukan menggunakan metode Elbow dan validasi hasil cluster menggunakan Silhouette Coefficient. Data penelitian diperoleh melalui kuesioner berbasis web dengan skala Likert 1–3 yang melibatkan 48 responden, 15 layanan, dan 10 indikator penilaian. Hasil penelitian menunjukkan bahwa sistem berhasil mengelompokkan tingkat kepuasan pengguna ke dalam tiga kategori, yaitu puas, cukup puas, dan kurang puas. Website yang dibangun mampu mengintegrasikan proses pengumpulan data, analisis clustering, dan penyajian hasil klasifikasi secara otomatis sehingga dapat membantu pihak jurusan dalam melakukan evaluasi layanan secara lebih objektif, efektif, dan berbasis data.
Implementation K-Means Algorithm in Promotional Media Destination Tour Minahasa Web Based Efraim Moningkey; Vivi Peggie Rantung; Peliks Andreas Surbakti
Journal La Multiapp Vol. 7 No. 1 (2026): Journal La Multiapp
Publisher : Newinera Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37899/journallamultiapp.v7i1.2659

Abstract

Minahasa Regency has great tourism potential with a variety of destinations including cultural, natural, and man-made tourism. However, tourism promotion efforts still face obstacles due to the lack of integrated media capable of grouping destination information based on tourist interests and preferences. This study aims to apply the K-Means clustering algorithm in web-based promotional media to group Minahasa tourist destinations based on the level of user interaction, which is represented by the number of likes and comments on promotional content for each destination. The research method is carried out through several stages, namely collecting tourist destination data, pre-processing interaction data, implementing the K-Means algorithm with a specified number of clusters of three according to the main categories of tourismcultural, natural, and man-made), and implementing the clustering results into a web-based evaluation system that uses the Silhouette Coefficient to evaluate the quality of cluster formation. The results show that the K-Means algorithm is able to effectively group tourist destinations into three clusters that reflect the level of popularity, making it easier for users to find destination recommendations according to their interests. Implementation in a web-based system also provides an interactive display in the form of a list of destinations per cluster and recommendations for popular destinations. Thus, this study proves that the application of K-Means can increase the effectiveness of Minahasa tourism promotion, and in the future it can be developed with the integration of real-time data from social media and comparison with other clustering algorithms.
Sentiment Analysis of the Song Lost - Bring Me the Horizon Based on Reviews on YouTube Using the SVM Algorithm Efraim Moningkey; Wanki Dwi Warsun Sombo
Journal La Multiapp Vol. 7 No. 2 (2026): Journal La Multiapp
Publisher : Newinera Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37899/journallamultiapp.v7i2.2685

Abstract

Bring Me The Horizon's song "Lost" received a wide response on YouTube, evident in the thousands of comments containing a variety of responses ranging from support and criticism to neutral opinions. The rapid development of social media has made it easier for people to freely share their views and experiences on musical works without being bound by space and time. YouTube, as one of the largest video-sharing platforms, plays a crucial role in documenting public perception of the song. This study was conducted to analyze listener sentiment towards the song "Lost" based on YouTube comments using the Support Vector Machine (SVM) algorithm and the Term Frequency–Inverse Document Frequency (TF-IDF) feature extraction technique. Comments were collected through web scraping from the song's official video, then processed through case folding, punctuation removal, tokenizing, stopword removal, and stemming to produce clean and uniform data. Term weights were calculated using TF-IDF and then used to label positive, negative, and neutral sentiments. The SVM model was built from training data and tested with test data to evaluate its performance using accuracy, precision, recall, and f1-score metrics so that classification quality could be assessed comprehensively. Based on the test results, the SVM algorithm was able to classify listener comments with 94% accuracy, with a distribution of negative sentiment of 207 comments, neutral comments of 1,280, and positive comments of 732. These findings demonstrate the effectiveness of SVM in analyzing the sentiment of song comments on social media and provide a more comprehensive picture of the public's view of Bring Me the Horizon's song "Lost.".
The Best Web-Based Employee Assessment Application Using the SAW Method Chelsea Aprilia Tendean; Kristofel Santa; Efraim Ronald Stefanus Moningkey
Journal La Multiapp Vol. 7 No. 1 (2026): Journal La Multiapp
Publisher : Newinera Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37899/journallamultiapp.v7i1.2862

Abstract

This study aims to develop a web-based system to evaluate the performance of top employees at the Secretariat of the Minahasa Regency Regional People's Representative Council. Previously, the performance evaluation process was conducted manually, resulting in inefficiency in data management, low transparency, and subjectivity in decision-making. To address these issues, a decision support system was designed and implemented using the Simple Additive Weighting (SAW) method to calculate the final score for each employee based on predetermined performance criteria. This study employed a structured system development approach, which included the stages of needs analysis, system design, implementation, testing, and maintenance. The system was developed using a web-based programming environment supported by a relational database to manage employee data, assessment criteria, and evaluation results. Employee performance assessments were conducted based on several criteria, including discipline, attendance, responsibility, and productivity, each of which was weighted according to its level of importance. The system performed data normalization, weighting, and ranking to objectively determine the best-performing employees. Functional testing using the black box method showed that all system features, including user authentication, data processing, performance evaluation, and report generation, functioned as expected. The results of the study show that the developed system is able to increase efficiency, accuracy, and transparency in the employee performance assessment process, and can be used as a reliable decision-making tool for management in selecting high-performing employees and improving overall organizational performance.
Sistem Klasifikasi Tingkat Kematangan Cabai Rawit Menggunakan Algoritma K-Nearest Neighbor (KNN) Asti Ananta; Sondy C. Kumajas; Efraim Moningkey
IKRA-ITH Informatika : Jurnal Komputer dan Informatika Vol. 9 No. 3 (2025): IKRAITH-INFORMATIKA Vol 9 No 3 November 2025
Publisher : Fakultas Teknik Universitas Persada Indonesia YAI

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

Abstract

Cabai rawit melrulpakan salah satul komoditas pelrtanian belrnilai elkonomi tinggi di Indonelsia, namuln pelnelntulan tingkat kelmatangannya masih dilakulkan selcara manulal olelh peltani selhingga selring melnyelbabkan keltidakkonsistelnan dalam prosels paneln. Pelnellitian ini melngelmbangkan sistelm klasifikasi tingkat kelmatangan cabai rawit melnggulnakan algoritma K-Nelarelst Nelighbor (KNN) belrbasis fitulr warna HSV (Hulel, Satulration, Valulel). Data citra cabai dipelrolelh langsulng dari pelrkelbulnan dan diprosels mellaluli tahap prelprocelssing, elkstraksi fitulr HSV, pellatihan modell, hingga implelmelntasi dalam aplikasi belrbasis welb melnggulnakan Flask. Sistelm mampul melngklasifikasikan cabai kel dalam tiga katelgori, yaitul melntah, seltelngah matang, dan matang. Modell KNN delngan nilai k=3 melnghasilkan akulrasi selbelsar 86% belrdasarkan pelnguljian melnggulnakan data ulji. Hasil pelnellitian melnulnjulkkan bahwa algoritma KNN dapat digulnakan selcara elfelktif dalam klasifikasi tingkat kelmatangan cabai rawit selrta dapat melndulkulng prosels paneln dan distribulsi selcara lelbih objelktif dan konsisteln.
Sistem Suhu dan Kelembapan Tanah Pada Tanaman Cabai Rawit Di Greenhouse Berbasis Internet OF Things (IOT) Jessa V Komaling; Kristofel Santa; Efraim R. S. Moningkey
IKRA-ITH Informatika : Jurnal Komputer dan Informatika Vol. 10 No. 1 (2026): IKRAITH-INFORMATIKA Vol 10 No 1 Maret 2026
Publisher : Fakultas Teknik Universitas Persada Indonesia YAI

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

Abstract

The soil moisture monitoring system for cayenne pepper plants is an important part in ensuring optimal plant growth. The limited land that is often found makes the use of greenhouses one solution to deal with this problem. In this research, the system uses a soil moisture sensor which can measure soil moisture and a DHT11 sensor as an air temperature measurement with IoT-based monitoring. The integration of the NodeMCU ESP8266 with the Telegram platform is going well, marked by the success of the system in sending test result notifications automatically every time there is a change in soil moisture status and also local display via the 16×2 LCD making it easier for users if they want to check directly in the field. The test results show that the monitoring system built has met the basic needs for monitoring soil moisture in cayenne pepper plants in a small-scale greenhouse and can be an effective solution in supporting IoT-based agricultural activities. Keywords (Agriculture, Cayenne Pepper Plants, Greenhouse, Internet of Things, Soil Moisture)
Aplikasi Augmented Reality Pengenalan Bahasa Toulour Menggunakan Metode Multimedia Development Life Cycle Gabrielle Richard Suwuh; Efraim R. S. Moningkey; Glenn D. P. Maramis
IKRA-ITH Informatika : Jurnal Komputer dan Informatika Vol. 10 No. 2 (2026): IKRAITH-INFORMATIKA Vol 10 No 2 Juli 2026
Publisher : Fakultas Teknik Universitas Persada Indonesia YAI

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

Abstract

Bahasa Toulour merupakan salah satu bahasa daerah di Sulawesi Utara yang berstatus terancam punah akibat dominasi penggunaan bahasa Melayu Manado di kalangan generasi muda. Fase usia dini (golden age) merupakan periode krusial dalam penyerapan kosakata, namun media pembelajaran konvensional dua dimensi (2D) saat ini dinilai kurang interaktif dan gagal mempertahankan fokus anak. Penelitian ini bertujuan untuk merancang dan membangun aplikasi edukasi Augmented Reality (AR) berbasis Android sebagai media pengenalan kosakata dasar bahasa Toulour yang interaktif. Metode pengembangan sistem menggunakan Multimedia Development Life Cycle (MDLC) versi Luther-Sutopo yang mencakup enam tahapan: Concept, Design, Material Collecting, Assembly, Testing, dan Distribution. Aplikasi ini mengintegrasikan enjin Unity 3D dengan Vuforia SDK untuk memproyeksikan visualisasi model tiga dimensi (3D) beserta audio pelafalan asli dari 25 objek fundamental tepat di atas kartu penanda (flashcard/marker) secara real-time. Pengujian fungsionalitas dilakukan melalui metode Black-Box Testing, sedangkan uji kompatibilitas dieksekusi pada lintas gawai Android. Hasil pengujian menunjukkan bahwa seluruh fitur tombol navigasi, kestabilan pelacakan marker oleh kamera, dan keselarasan output audio berjalan dengan sukses 100%, sehingga layak digunakan sebagai media ajar inovatif untuk mendukung pelestarian kebudayaan Minahasa.
Rancang Bangun Sistem Pendaftaran Online Siswa Baru Dengan Algoritma SAW untuk Mendukung Keputusan Penerimaan diSMA Katolik Santo Fransiskus Xaverius Kema Kasumi Cecilia Nelwan; Parabelem Rompas; Efraim Moningkey
IKRA-ITH Informatika : Jurnal Komputer dan Informatika Vol. 10 No. 2 (2026): IKRAITH-INFORMATIKA Vol 10 No 2 Juli 2026
Publisher : Fakultas Teknik Universitas Persada Indonesia YAI

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

Abstract

Proses penerimaan siswa baru yang masih dilakukan secara manual di SMA Katolik Santo Fransiskus Xaverius Kema menimbulkan berbagai kendala, mulai dari inefisiensi waktu dan potensi kesalahan input data hingga kurangnya transparansi dalam proses seleksi. Studi ini bertujuan untuk merancang dan membangun sistem pendaftaran siswa baru online yang mengintegrasikan algoritma Simple Additive Weighting (SAW) sebagai metode pendukung keputusan. Sistem ini dikembangkan menggunakan pendekatan Riset dan Pengembangan (R&D) berbasis web. Tiga kriteria penilaian diterapkan: Nilai Laporan Nilai (bobot 45%), Nilai Tes Kompetensi Akademik (TKA) (bobot 30%), dan Nilai Prestasi (bobot 25%). Sistem ini telah terbukti meningkatkan objektivitas, transparansi, dan efisiensi proses penerimaan siswa baru.
Analisis Sentimen Pelanggaran Politik Uang pada Pilkada Menggunakan Integrasi SMOTE dan Long Short-Term Memory (LSTM) Keiza Sasako; Irene Realyta Haldy Trosi Tangkawarow; Efraim Ronald S Moningkey
Edutik : Jurnal Pendidikan Teknologi Informasi dan Komunikasi Vol. 6 No. 4 (2026): EduTIK : Agustus 2026
Publisher : Jurusan PTIK Universitas Negeri Manado

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67142/edutik.v6i4.524

Abstract

ABSTRAK               Praktik politik uang merupakan ancaman serius terhadap integritas Pemilihan Kepala Daerah (Pilkada) di Indonesia, di mana opini dan keluhan publik banyak disuarakan melalui media sosial X. Namun, analisis sentimen otomatis terhadap isu ini sering terkendala oleh ketimpangan kelas data yang parah antara dokumen teks positif dan negatif. Penelitian ini bertujuan untuk mengimplementasikan alur kerja baru yang mengintegrasikan teknik penyeimbangan data berbasis Synthetic Minority Over-sampling Technique (SMOTE) dan arsitektur sekuensial Long Short-Term Memory (LSTM) untuk mengklasifikasikan sentimen terkait pelanggaran pemilu. Dataset yang digunakan terdiri dari 1.013 unggahan bahasa Indonesia dari platform X yang diekstraksi dari Oktober hingga November 2024. Metode penelitian meliputi prapemrosesan teks (cleaning, case folding, normalisasi, stopword removal, dan tokenisasi), ekstraksi fitur Embedding, aplikasi SMOTE pada ruang vektor, dan klasifikasi menggunakan LSTM 128 memori tersembunyi. Hasil penelitian menunjukkan bahwa penambahan SMOTE berhasil mengatasi masalah bias kelas mayoritas pada model LSTM standar. Model usulan SMOTE-LSTM ini mampu mendongkrak performa deteksi kelas minoritas secara signifikan, menghasilkan nilai presisi sebesar 0,84, recall sebesar 0,83, dan F1-score sebesar 0,83 pada kelas negatif (laporan kecurangan). Kesimpulan dari penelitian ini menunjukkan bahwa integrasi SMOTE dan LSTM memberikan sensitivitas yang kokoh dalam mengenali opini kecurangan pemilu, sehingga sangat layak dipertimbangkan sebagai modul awal sistem pemantauan digital otomatis bagi Badan Pengawas Pemilihan Umum (Bawaslu).  ABSTRACT               The practice of money politics poses a serious threat to the integrity of regional elections (Pilkada) in Indonesia, where public opinions and complaints are widely voiced through the social media platform X. However, automated sentiment analysis on this issue is frequently hindered by a severe data class imbalance between positive and negative text documents. This study aims to implement a new workflow integrating the data balancing technique based on Synthetic Minority Over-sampling Technique (SMOTE) and the sequential architecture of Long Short-Term Memory (LSTM) to classify sentiments regarding election violations. The dataset consists of 1,013 Indonesian posts from platform X, extracted from October to November 2024. The methodology includes text preprocessing (cleaning, case folding, normalization, stopword removal, and tokenization), Embedding feature extraction, the application of SMOTE in the vector space, and classification using an LSTM with 128 hidden memory units. The results indicate that the incorporation of SMOTE successfully resolved the majority class bias inherent in the standard LSTM model. The proposed SMOTE-LSTM model significantly boosted the detection performance of the minority class, yielding a precision of 0.84, a recall of 0.83, and an F1-score of 0.83 for the negative class (fraud reports). The conclusion of this study demonstrates that the integration of SMOTE and LSTM provides robust sensitivity in recognizing election fraud opinions, making it highly viable as an initial automated digital monitoring module for the Elections Supervisory Agency (Bawaslu).
Co-Authors Adesyan Lahinda Andry Wilson Siahaan Asti Ananta Atuna, Annisa Salsabilah Audy Aldrin Kenap Chelsea Aprilia Tendean Dea Karlina Pali Della Deviani Harisondak Detuage, Rivni Dinda Asfiani Modeong Frendy Rikal Gerung Friska Regina Maralantang Gabrielle Richard Suwuh Gladly Caren Rorimpandey Glenn D. P. Maramis Grace Junita Wuysang Gupuh, Andi Irene Realyta Halldy Trosi Tangkawarow Jessa V Komaling Kasumi Cecilia Nelwan Keiza Sasako Kristofel Santa Kumajas, Sondy Campvid Lordy Frangky Karel Meisela Renata Ondang Mochamad Bruri Triyono Nathania Piri Nelsi Timang Onibala, Angely Wulandari Onibala, Rahellea Joiby Parabelem Rompas parabelem tinno dolf rompas Peliks Andreas Surbakti Priyanto Quido Conferti Kainde Ratu, Regina Gloria Ropa, Sifra Rudy Harijadi Wibowo Pardanus Sandra Keren Lumanauw Sanusi, Rahmat Hidayat Sondakh, Inggried Rillya Sondy C. Kumajas Tular, Feonri Vivi Peggie Rantung Wanki Dwi Warsun Sombo