Claim Missing Document
Check
Articles

Found 22 Documents
Search

ANALISA SENTIMEN KOMENTAR VIDEO YOUTUBE DI CHANNEL TVONENEWS TENTANG CALON PRESIDEN PRABOWO SUBIANTO MENGGUNAKAN SUPPORT VECTOR MACHINE Tohidi, Edi; Perdana Herdiansyah, Reza; Wahyudin, Edi; Kaslani, Kaslani
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 8 No. 1 (2024): JATI Vol. 8 No. 1
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v8i1.8560

Abstract

Indonesia merupakan negara demokrasi di mana rakyat memilih presiden melalui Pemilihan Umum Presiden (Pilpres) yang dilakukan 5 tahun sekali. Pada Pilpres 2024, ada 3 kandidat capres yaitu Anies Baswedan, Prabowo Subianto, dan Ganjar Pranowo. Youtube menjadi platform utama masyarakat menyampaikan opini politik. Penelitian ini menganalisis sentimen komentar video Youtube TVOneNews tentang calon presiden Prabowo sebagai capres 2024 dengan SVM. Tujuan penelitian ini adalah mengukur akurasi SVM dalam mengklasifikasi sentimen komentar video Youtube TVOneNews berjudul "Relawan dari Berbagai Daerah Deklarasikan Prabowo sebagai Capres 2024" serta melihat sentimen masyarakat terhadap calon presiden prabowo subianto. Metode penelitian ini menggunakan Knowledge Discovery in Database (KDD) yang terdiri dari lima tahapan yaitu Selection, Preprocessing, Transformation, Data Mining dan Interpretation. Datadalam penelitian ini berjumlah 927 komentar yang didapatkan melalui crawling setelah preprocessing tersisa 877 data dengan label positif 530 dan label negatif 346. Hasil penelitian menunjukkan terdapat sebuah perbedaan jumlah label sentimen awal dengan hasil SVM, dimana sentimen positif bertambah dari 530 menjadi 542 dan sentimen negatif berkurang dari 346 menjadi 334. Dan hasil klasifikasi SVM mendapatkan nilai akurasi 85%, presisi 87% dan recall 89%.
MARKET BASKET ANALYSIS PADA DATA PENJUALAN UMKM MENGGUNAKAN ALGORITMA FP-GROWTH Pratama, Denni; Kaslani, Kaslani; Tohidi, Edi
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 8 No. 4 (2024): JATI Vol. 8 No. 4
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v8i4.10939

Abstract

UMKM di Indonesia menghadapi tingkat kegagalan yang tinggi, mencapai 78-80%, yang disebabkan oleh berbagai faktor termasuk pengelolaan inventori yang buruk, persaingan usaha, dan rendahnya penjualan. Pandemi COVID-19 juga memberikan dampak signifikan, terutama pada usaha sektor makanan dan minuman. Toko Rafa Cake, UMKM di Kota Cirebon yang memproduksi dan menjual makanan, mengalami dampak pandemi pada penjualannya. Pasca pandemi, Toko Rafa Cake, berusaha memperbaiki pengelolaan dan berinovasi dengan menghadirkan 155 varian produk, namun mengalami kesulitan dalam mengelola inventori dan menentukan strategi penjualan yang tepat. Penelitian ini menggunakan Market Basket Analysis dengan algoritma FP-Growth dan empat matriks evaluasi aturan asosiasi untuk menganalisis data transaksi penjualan. Kerangka penelitian menggunakan CRISP-DM. Dari 10.987 data transaksi, dihasilkan 6 aturan asosiasi umum dengan hasil yang bervariasi setiap bulannya. Produk Roti Regular All Varian memiliki support tertinggi sebesar 32,10%. Analisis menunjukkan bahwa pelanggan yang membeli Donat Ring Regular dan Glass Cake cenderung membeli Roti Regular All Varian dengan support 5,50%, confidence 98,80%, lift 3.075, dan conviction 55.436. Rekomendasi yang dihasilkan meliputi pengaturan tata letak produk yang sering dibeli bersamaan dan penerapan strategi bundling Roti Regular All Varian dengan produk lainnya. Hasil penelitian ini dapat membantu Toko Rafa Cake dalam menentukan strategi penjualan dan mengelola inventori dengan lebih efektif.
K-Means Algorithm to Improve Leaf Image Clustering Model for Rice Disease Early Detection Gina Regiana; Irma Purnamasari, Ade; Bahtiar, Agus; Tohidi, Edi
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.840

Abstract

This research aims to improve the accuracy of rice leaf image clustering in early disease detection using the K-Means algorithm. The approach used involves the Knowledge Discovery in Databases (KDD) method, which includes data selection, pre-processing, data transformation, data mining, evaluation, and presentation of results. The dataset used consists of images of healthy leaves and leaves infected with diseases such as Bacterial Leaf Blight, Brown Spot, and Leaf Smut. The images are processed through grayscale conversion, noise removal, size adjustment, and data augmentation. The K-Means algorithm is applied to cluster image features based on visual similarity. Evaluation results using Silhouette Score showed that the best clustering was obtained at K=2 with a score of 0.8340, resulting in two main clusters separating healthy and infected images. This study concludes that the K-Means algorithm is able to improve the efficiency and accuracy of rice disease detection, so that it can assist farmers in taking early preventive measures and increase agricultural productivity. This implementation shows significant potential in the development of smart agriculture technology.
Analisis Prediksi Tingkat Penjualan Brownies Tape Menggunakan Algoritma Naïve Bayes Tohidi, Edi; Danar Dana, Raditya; Mukhlashin, Khairul
BULLET : Jurnal Multidisiplin Ilmu Vol. 3 No. 1 (2024): BULLET : Jurnal Multidisiplin Ilmu
Publisher : CV. Multi Kreasi Media

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

Abstract

The problem of this covid pandemic has hit all parties, sales in this pandemic era must be observant of changes, entrepreneurs are obliged to manage finances properly so as not to experience colaps or bankruptcy. solutions made by entrepreneurs ranging from reducing the amount of production, reducing employees and or promoting massively. The criteria for this study were obtained from the journals used, namely the criteria, namely date, month, year, code, product name, price and quantity. Then this study uses primary data, which means that the data is used with brownie purchase data from tape products with sales records from 2021 in September. The method used is the naïve bayes algorithm with retrive operators, cross validation, naïve bayes, apply model and performance. The accuracy result in this study is 83.24% Prediction of Less Selling with true Less Selling as much as 2004 data. Prediction of Less Selling with true Selling as much as 350 data. In-demand predictions with less in-demand as much as 202 data. Laris prediction with true Laris as much as 737 data.
Pengembangan Model Prediksi Keberhasilan Mahasiswa Menggunakan Algoritma Machine Learning Dalam Learning Management System Tohidi, Edi; Ali, Irfan
BULLET : Jurnal Multidisiplin Ilmu Vol. 2 No. 1 (2023): BULLET : Jurnal Multidisiplin Ilmu
Publisher : CV. Multi Kreasi Media

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

Abstract

The advancement of digital technology in education has driven the widespread adoption of Learning Management Systems (LMS) as effective platforms for online learning. This study aims to develop a predictive model for student success in LMS environments using machine learning algorithms. Student success is classified based on parameters such as participation levels, access frequency, assessment results, and punctuality in assignment submissions. Several machine learning algorithms, including Decision Tree, Random Forest, Support Vector Machine, and K-Nearest Neighbors, are employed to build the prediction model. The performance of each model is evaluated using metrics such as accuracy, precision, recall, and F1-score. The results show that the Random Forest algorithm achieved the best performance with an accuracy of 89%, followed by Support Vector Machine and Decision Tree. The developed model is expected to assist educators and academic institutions in identifying students who may face learning difficulties at an early stage, allowing for timely and targeted interventions. This research contributes to the application of machine learning in supporting adaptive learning processes and enhancing data-driven educational quality.
Improving the Education Development Contribution Payment Model at SMK Istiqomah Maruyung Using the C4.5 Algorithm Noviyanti; Purnamasari, Ade Irma; Bahtiar, Agus; Tohidi, Edi
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 3 (2025): June 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i3.729

Abstract

  Payment of tuition fees is one of the important aspects of school financial management. At SMK Istiqomah Maruyung, the management of SPP payments is still done manually, which causes student non-compliance in paying on time. The purpose of the research is to improve the SPP payment model by using the C4.5 algorithm to classify the level of student compliance and identify the main factors that influence late payments. The method used is the Knowledge Discovery in Databases (KDD) approach which includes the stages of data selection, preprocessing, transformation, data mining, and result evaluation. The research data was taken from 206 students in the 2023/2024 academic year with attributes such as parental income, number of siblings, scholarship status, and academic grade point average. The C4.5 algorithm was applied to build a decision tree model, with evaluation using five-fold cross validation. The result of this study is that the C4.5 algorithm is able to classify student compliance levels with an average accuracy of 93.55%. The main factors that influence late payment are academic grade point average, class, and parental income. Although the model is very good at predicting compliant students (precision 95%, recall 98%), it shows weakness in predicting lateness (precision 67%, recall 40%). It is concluded that the C4.5 algorithm can improve the efficiency of managing tuition payments and provide data-driven insights for policy making. With further implementation, this algorithm is expected to be adopted by other educational institutions to address similar challenges in financial management.
Pemesanan Paket Wedding Organizer pada Cahaya Bridal Decoration Berbasis Web Sukabumi Faturachman, Rifcki Aziz; Rahaningsih, Nining; Basysyar, Fadil M; Kaslani; Tohidi, Edi
MEANS (Media Informasi Analisa dan Sistem) Volume 7 Nomor 1
Publisher : LPPM UNIKA Santo Thomas Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (709.422 KB) | DOI: 10.54367/means.v7i1.1842

Abstract

The Wedding Organizer package ordering information system is made by utilizing web-lined information technology, with the aim of expanding the area of promotion and sales of wedding packages and simplifying the ordering process. so the author tries to make a Final Project on the Website-Based Website-Based Information System for ordering wedding organizer packages. In the process of collecting data with the aim of solving problems, the authors use data sources (Observation and Interview). The authors Wedding Organizer package ordering information system uses the PHP and MySQL programming languages. For system design, the author uses the Prototype method. The final result obtained in this study is a website-based Information System, which can provide information about several wedding organizer packages, wedding organizer package prices and the contents of wedding organizer packages available at Cahaya Bridal Decoration. With several advantages of website technology as an information medium, the Website-Based Information System for ordering wedding organizer packages is expected to expand the reach of information dissemination to all aspects
RANCANG BANGUN SISTEM INFORMASI PORTAL BERITA BERBASIS WEB PADA DINAS PEMUDA DAN OLAHRAGA KABUPATEN CIREBON Pratama, Hilda Fidyah Hadi; Hamonangan, Ryan; Herdiana, Ruli; Tohidi, Edi; Hayati, Umi
MEANS (Media Informasi Analisa dan Sistem) Volume 7 Nomor 1
Publisher : LPPM UNIKA Santo Thomas Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (646.917 KB) | DOI: 10.54367/means.v7i1.1856

Abstract

The Cirebon Regency Youth and Sports Office (Dispora Cirebon) is a regional work unit that is given the mandate and duties and responsibilities in handling development in the Youth and Sports Sector in the Cirebon Regency environment. In this day and age, a touch of Information System technology such as a website must have become a necessity for government agencies, as a support for more centralized, accurate, and fast information. However, there was no website-based information system at the Cirebon Dispora as a medium for disseminating information at that time. The writer uses primary data sources (Observation and Interview) and secondary data sources (Documentation Study). For system design, the author uses the SDLC (System Development Life Cycle) method. The final result obtained is a website-based Information System, which can provide information about profiles, activities or articles about Dispora Cirebon to the wider community. With several advantages of website technology, the Website-Based News Portal Information System is expected to expand the reach of information dissemination to all aspects of society.
PENERAPAN ALGORITMA FP GROWTH PADA PENJUALAN PRODUK DISTRO RADEN MADURA Putra, Arya Kamandanu; Hamonangan, Ryan; Herdiana, Ruli; Tohidi, Edi; Hayati, Umi
MEANS (Media Informasi Analisa dan Sistem) Volume 7 Nomor 1
Publisher : LPPM UNIKA Santo Thomas Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (661.226 KB) | DOI: 10.54367/means.v7i1.1858

Abstract

The transaction data for the purchase of the distro's cost of selling is quite stable but its sales are less than the sales target, so it is necessary to manage sales data. The focus of this research is focused on the management of purchase transaction data that will be used as a dataset. The management uses the FP-Growth algorithm which takes from the item set, from the algorithm it gets a buying pattern that will become information for making a decision. Based on the results of the study, the authors conclude that the pattern of purchases by consumers gets a pattern of sales, namely, consumers by buying 1 item of T-shirts from distributions will buy back one item of T-shirts from 26 different distributions. consumers by buying 2 items of t-shirts distributions will buy back 1 item of t-shirts from different distributions as many as 72 patterns, and consumers by buying 3 items of t-shirts distributions will buy back 1 item of t-shirts with different distributions of 25 patterns.
RANCANG BANGUN E-COMMERCE BERBASIS WEB UNTUK UMKM BATIK Nugraha, Syahrul; Hamonangan, Ryan; Dana, Raditya Danar; Tohidi, Edi; Hayati, Umi
MEANS (Media Informasi Analisa dan Sistem) Volume 7 Nomor 1
Publisher : LPPM UNIKA Santo Thomas Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (754.963 KB) | DOI: 10.54367/means.v7i1.1859

Abstract

In the sales process carried out by batik craftsmen who are in Trusmi village, namely still selling their batik cloth to the sorum of batik sellers, so that the craftsmen take profits from selling their batik cloth only slightly, because the batik cloth will be resold by the sorum of batik sellers. In terms of application development, the author uses the Software Development Life Cycle (SLDC) model with an approach using the waterfall method, while the stages use the waterfall method, namely communication, planning, modeling, construction, and deployment. Therefore, the author makes an application for selling batik cloth that aims to break the chain of batik cloth sales, so that craftsmen can get greater profits because they directly sell their products to consumers without going through a batik seller sorum. The final result obtained in this study is an application for selling batik cloth which is expected to help batik craftsmen in Trusmi village in selling their batik cloth directly to consumers without having to go through the center of batik sellers. In the sales process carried out by batik craftsmen who are in Trusmi village, namely still selling their batik cloth to the sorum of batik sellers, so that the craftsmen take profits from selling their batik cloth only slightly, because the batik cloth will be resold by the sorum of batik sellers. In terms of application development, the author uses the Software Development Life Cycle (SLDC) model with an approach using the waterfall method, while the stages use the waterfall method, namely communication, planning, modeling, construction, and deployment. Therefore, the author makes an application for selling batik cloth that aims to break the chain of batik cloth sales, so that craftsmen can get greater profits because they directly sell their products to consumers without going through a batik seller sorum. The final result obtained in this study is an application for selling batik cloth which is expected to help batik craftsmen in Trusmi village in selling their batik cloth directly to consumers without having to go through the center of batik sellers.