Claim Missing Document
Check
Articles

Found 32 Documents
Search

Sentiment Analysis of Public Service Using Naïve Bayes Classifier Purnama, Arga Aditia; Sipayung, Yoannes Romando
Journal of Information System and Informatics Vol 7 No 3 (2025): September
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v7i3.1207

Abstract

Public administrative service quality is a crucial factor in citizen satisfaction. This study analyzes sentiment in public service reviews using a text mining approach with the Naïve Bayes Classifier method. The dataset was collected from citizen feedback on online platforms regarding public administrative services. Preprocessing steps included tokenization, case folding, stopword removal, and stemming. The Naïve Bayes algorithm with Laplace smoothing was applied for classification, and performance was evaluated using accuracy, precision, recall, and F1-score. The experiment resulted in an accuracy of 91.2%, precision of 90.3%, recall of 89.7%, and F1-score of 90.0%. The analysis revealed that Service Speed obtained an average score of 3.21, indicating a moderate level of citizen satisfaction in that aspect. These findings suggest that while the Naïve Bayes method is effective for sentiment classification, its greatest value lies in providing actionable insights for public service improvement. Specifically, policymakers can prioritize addressing delays in service speed through simplified procedures, improved staffing, and digital innovation, while maintaining strengths such as officer politeness and effective complaint handling. By leveraging sentiment analysis, public institutions can continuously monitor citizen feedback, identify problem areas, and implement evidence-based strategies to enhance service quality and strengthen public trust.
Pemanfaatan Video Profil Sebagai Sarana Promosi Dalam Meningkatkan Eksistensi TK Islam Al Mujahidin Sipayung, Yoannes Romando; Rochmawati, Nur Intan; Romandhoni, Fajar Taufik; Lestari, Azizah Sella
Ngudi Waluyo Empowerment: Jurnal Pengabdian Kepada Masyarakat Vol. 2 No. 2 (2023): Ngudi Waluyo Empowerment: Jurnal Pengabdian Kepada Masyarakat
Publisher : Fakultas Komputer dan Pendidikan Universitas Ngudi Waluyo

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

Abstract

Dalam meningkatkan eksistensi suatu instansi ke masyarakat luas, perlu adanya suatu media yang dapat menjadi salah satu sarana promosi. Promosi yang banyak diterapkan saat ini yaitu dalam bentuk video profil. Video profil merupakan sebuah media elektronik untuk menyampaikan informasi yang efektif dalam memperkenalkan dan promosikan suatu instansi.TK Islam Al Mujahidin merupakan salah satu sekolah Taman Kanak-Kanak yang terletak di Kota Semarang yang sampai saat ini belum memiliki media promosi dalam bentuk video profil. Berdasarkan hal tersebut, maka untuk melakukan promosi, perlu dikembangkan sebuah video profil TK Islam Al Mujahidin.Dalam pembuatan video ini, digunakan peralatan pendukung, seperti kamera, lighting, aplikasi editing video, dan pendukung lainnya, sehingga akan memudahkan pembuatan video profil. Dalam pembuatan Video Profil tahapan yang akan dibuat dimulai dari tahap Pra Produksi (persiapan ide, pengerjaan video, dan dialog atau storyboard), Tahap Produksi (proses pengambilan gambar), tahap Paska Produksi (Editing Video) serta elemen-elemen yang ada setiap tahapnya. Hasilnya berupa video profil yang dapat digunakan untuk mempromosikan TK Islam Al Mujahidin.
Analisis Kepuasan Penghuni Kost Mahasiswa Di Lingkungan Universitas Ngudi Waluyo Menggunakan Algoritma C4.5 Ramadhan, Krisna Cahya; Sipayung, Yoannes Romando
Jurnal Tika Vol 8 No 2 (2023): Jurnal Teknik Informatika Aceh
Publisher : Fakultas Ilmu Komputer Universitas Almuslim Bireuen - Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51179/tika.v8i2.2081

Abstract

This study aims to measure student satisfaction with boarding houses or contracts. To achieve this goal, the authors implement the C4.5 algorithm in data analysis. Data on student satisfaction was taken through a survey covering various factors related to price, facilities, strategic layout, and the quality of the boarding house or contract. Algorithm C4.5 is used to produce a decision-making model based on criteria that are relevant to the level of student satisfaction. The results of this model provide valuable information in understanding what factors most influence student satisfaction with boarding houses or contracts. The results showed that the C4.5 algorithm was successful in building a model capable of classifying the level of student satisfaction with boarding houses or contracts with high accuracy. The results of this study are expected to help boarding or contract parties to increase student satisfaction. In addition, this research can also be a basis for further research in the field of student satisfaction and the application of the C4.5 algorithm to similar problems.
Sistem Pendukung Keputusan Evaluasi Kepuasan Reseller Di Toko Callista Bandungan Dengan Metode Simple Additive Weighting (Saw) Munawaroh, Lutfi; Sipayung, Yoannes Romando
Jurnal Tika Vol 8 No 2 (2023): Jurnal Teknik Informatika Aceh
Publisher : Fakultas Ilmu Komputer Universitas Almuslim Bireuen - Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51179/tika.v8i2.2082

Abstract

Along with the development of the times and increasingly sophisticated technology in the modern era. Callista wholesale warehouse store in the largest and most complete wholesale werehouse located on Jalan Raya Bandungan – Ambarawa, Bandungan Dostrict Semarang, Regency, Based on the problems that were in the Callista store regarding customer satisfaction, it was still used manually for reports and filling out questionnaires. With the manual method, of course, it creates a lot of difficulties for the owner in processing data and making satisfactionreports. Given these problems a sistem  will be created to help reseller get good service from Callista store, namely in the form of a satisfactionsistem  that user the web indicated for Callista stores.
Identifikasi Pola Tanda Tangan Berbasis Jaringan Syaraf Tiruan Dengan Metode Learning Vector Quantization Yoannes Romando Sipayung; Suamanda Ika Novichasari
Multimatrix Vol. 1 No. 1 (2018)
Publisher : Universitas Ngudi Waluyo

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

Abstract

Abstrak - The introduction of signature patterns is one of the fields of pattern recognition that is currently developing. Each person's signature is generally identical but not the same. LVQ is a method of artificial neural networks to conduct learning in a supervised competitive layer. There are previous studies that use this method, but in these studies do not include the processing time needed to identify signature patterns. This research will test using this method. In this study, used image data with a size of 433 x 276 pixels as many as 300 pieces from 30 people, where each person was taken 10 signatures. For training data, the data is 180 signatures, while 120 test data are used for the test data. This study uses Canny edge detection to obtain an edge in the signature image. During the training process and LVQ testing, the process was carried out 3 times. The results of the training and testing with the LVQ metodel indicate that the method can identify the signature pattern well. Keywords:  Signature Patterns, Artificial Neural Network, Learning Vector Quantization 
PSO-SVM Untuk Klasifikasi Daun Cengkeh Berdasarkan Morfologi Bentuk Ciri, Warna dan Tekstur GLCM Permukaan Daun Suamanda Ika Novichasari; Yoannes Romando Sipayung
Multimatrix Vol. 1 No. 1 (2018)
Publisher : Universitas Ngudi Waluyo

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

Abstract

Abstract— Of the two types of superior varieties cultivated cloves, clove types of zanzibar is the best kind. However, when not flowering of the three types of clove leaves indistinguishable from the image. This study uses 4 morphological features of shape, 3 color features and 10 most commonly used GLCM features and apply SVM for classification with Particle Swarm Optimization (PSO) optimization method to improve the accuracy of clove plant classification based on leaf surface image. Results of research on the top surface image classification leaf clovers, PSO-SVM method proposed is shown to have a higher accuracy compared with PSO-SVM method than previous research (Novichasari, S.I., 2015) with an accuracy of 90.5% and AUC 0.944. Keywords— Leaf image classification, cloves, shape, color, GLCM, PSO-SVM
PENGEMBANGAN SISTEM INFORMASI PENERIMAAN MAHASISWA BARU BERBASIS WEB DI UNIVERSITAS NGUDI WALUYO Sri - Mujiyono; Yoannes Romando Sipayung
Multimatrix Vol. 1 No. 2 (2019)
Publisher : Universitas Ngudi Waluyo

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

Abstract

Universitas Ngudi Waluyo saat ini telah berkembang dengan pesat hal ini dapat dilihat dari jumlah mahasiswa yang terus meningkat secara signifikan jumlah mahasiswa yang banyak, maka perlu pelayanan yang pesat pula. Pengembangan Sistem Informasi Transaksional Penerimaan Mahasiswa Baru berbasis Web adalah sebuah sistem yang dibangun untuk mempercepat dan mempermudah penerimaan mahasiswa baru. Sistem ini dibangun dengan menggunakan bahasa pemrograman PHP dan database MySQL. Dalam aplikasi ini terdapat dua user, admin dan Panitia PMBProgram aplikasi ini akan sangat membantu baik bagi pihak panitia penerimaan mahasiswa baru (PPMB) yang merupakan ajang promosi kampus ke dunia luas, juga membantu calon mahasiswa yang berasal dari luar kota ataupun luar pulau
Identifikasi Komentar Negatif Berbahasa Indonesia Pada Instagram Dengan Metode K-Means Yoannes Romando Sipayung; Reny Sulistyowati
Multimatrix Vol. 2 No. 1 (2019)
Publisher : Universitas Ngudi Waluyo

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

Abstract

Comments given by users or people on social media such as Instagram are varied, some are positive or negative. In terms of netizens, there is nothing wrong when you want to comment or pour out your heart. In Indonesia, denying netizens comments related to negativity, agreeing to agree with the law and the police. This research will help people who want to send comments that they make so as not to contain negative content so they can avoid cyber crime. The method used in supporting this research is the K-Mean method, to determine whether the comments entered are positive or negative. In this study, the data used were 40 comments that were used as research objects. Keywords:  Negative Comments, Instagram, K-Means
DEVELOPMENT OF AN EXPERT SYSTEM FOR DIAGNOSING EGGPLANT DISEASES USING THE TSUKAMOTO FUZZY LOGIC METHOD Efrizal Yudhantoro; Yoannes Romando Sipayung
Jurnal Sistem Informasi Vol. 13 No. 1 (2026)
Publisher : Universitas Serang Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30656/6ddknb34

Abstract

Eggplant diseases are a major factor contributing to decreased crop quality and yield, particularly among novice farmers with limited knowledge of early disease identification. The uncertainty of symptom manifestation and limited access to agricultural experts further increase the risk of crop failure. This study aims to develop a web-based expert system for diagnosing eggplant diseases using the Tsukamoto Fuzzy Logic method. The novelty of this research lies in the integration of weighted symptom severity, fuzzy inference rules, and confidence-level outputs into a practical decision-support system specifically designed for eggplant disease diagnosis. The research adopts the Waterfall development model, including requirements analysis, system design, implementation, and testing. The knowledge base consists of five main diseases and twenty symptoms with weighted values ranging from 0.55 to 1.00. System evaluation using Black Box Testing shows that 100% of functional features operate successfully according to system requirements. Furthermore, diagnostic results demonstrate high confidence levels, reaching up to 97% for certain disease cases, indicating reliable system performance in handling uncertainty. This study contributes to the development of intelligent agricultural decision-support systems by providing an accessible, accurate, and efficient diagnostic tool. The proposed system can assist farmers in early disease detection, reduce dependency on experts, and potentially minimize crop losses while improving eggplant productivity.   Keywords: Expert System, Eggplant Disease, Tsukamoto Fuzzy Logic, Decision Support System, Smart Agriculture
Sistem Pendukung Keputusan Menentukan Siswa Berprestasi dengan Metode SAW (Simple Addtive Weighting) Isnia Anjar Setyani; Yoannes Romando Sipayung
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 4 No. 4 (2023): Juni 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v4i4.6179

Abstract

MI Kalirejo is an Islamic Madrasah located in Kalirejo Village, East Ungaran District, Semarang Regency. Based on the number of students who have achievement in academic and non-academic fields, a process is needed to determine student achievement. Currently MI Kalirejo still uses the manual method in the assessment process and only through the results of report cards in determining outstanding students. The author is interested in building a website-based decision support system in determining outstanding students based on predetermined criteria, so that it can help make it easier for school institutions to process and determine appropriate, fast and accurate assessments there are several criteria such as the average value of report cards, attitude scores. This system designs and creates and implements a website-based decision support system using the Simple Additive Weighting method. In this study, researchers collected data throught observation and interviews. Then the researchers used the waterfall method in system development. In testing the system using a black box to obtain accuracy results. The conclusions obtained in making a decision support system in determining outstanding students using simple additive weighting based on a website are obtained alternative values from the result of calculations that have been carried out. The author shows accuracy of 100% using the sample and population of Sugiono’s theory. From the result of calculations using the SAW method, it shows that alternative A2 is obtained by a student named Faeza with a value of 1 in the first rank. Thus alternative A2 students on behalf of Faeza were chosen as the best alternative to achieve achievements as outstanding students at MI Kalirejo. Based on the trials and the resulting values have the same result so that the purpose of making this website has been achieved