Claim Missing Document
Check
Articles

KOMPARASI ALGORITMA SUPPORT VECTOR MACHINE DAN RANDOM FOREST UNTUK ANALISIS SENTIMEN METAVERSE Sari, Putri Kumala; Suryono, Ryan Randy
Jurnal Mnemonic Vol 7 No 1 (2024): Mnemonic Vol. 7 No. 1
Publisher : Teknik Informatika, Institut Teknologi Nasional malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/mnemonic.v7i1.8977

Abstract

Fenomena metaverse menggambarkan transformasi signifikan dalam interaksi manusia dengan dunia digital. Saat ini, pemerintah dan industri berupaya memahami arah pengembangan metaverse untuk mewujudkan digitalisasi dalam berbagai sektor. Penelitian ini menggunakan data media sosial X untuk melakukan analisis sentimen publik terhadap metaverse. Metode klasifikasi teks dibangun menggunakan model algoritma Support Vector Machine dan Random Forest. Dengan melakukan komparasi kedua model tersebut dan menerapkan metode optimasi SMOTE maka eksperimen ini menghasilkan akurasi yang tinggi. Hasilnya menunjukkan bahwa kedua model menghasilkan akurasi sebesar 91% untuk model algoritma Random Forest dan 90% untuk model algoritma Support Vector Machine. Dengan demikian dapat disimpulkan bahwa model algoritma Random Forest lebih baik dari Support Vector Machine. Selain itu penerapan SMOTE terbukti meningkatkan kemampuan untuk mengenali sentimen positif pada keduanya, meskipun terjadi trade-off antara recall dan precision. Trade-off terjadi karena adanya keterbatasan dalam model klasifikasi yang membuat peningkatan dalam satu metrik akan mengakibatkan penurunan dalam metrik lainnya, karena algoritma harus mengambil keputusan yang mengoptimalkan keduanya secara bersamaan.
Analisis Sentimen Publik Terhadap Pengungsi Rohingya di Indonesia dengan Metode Support Vector Machine dan Naïve Bayes Ananda, Dhea; Suryono, Ryan Randy
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 2 (2024): April 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i2.7517

Abstract

The arrival of Rohingya refugees in Indonesia has become a highly controversial topic, eliciting various responses from the public. In this context, public sentiment analysis regarding the arrival of Rohingya refugees is crucial for understanding the dynamics of feelings, opinions, and attitudes of the Indonesian society towards this issue. In conducting public sentiment analysis, the selection of methods is crucial to ensure accurate results. The aim of this research is to conduct sentiment analysis regarding the arrival of Rohingya refugees using the Support Vector Machine (SVM) and Naive Bayes methods. The main focus is to evaluate public sentiment and compare the performance of both methods. Two common methods used in sentiment analysis are Support Vector Machine (SVM) and Naïve Bayes. This research utilized a dataset of 3350 tweets to conduct public sentiment analysis on the arrival of Rohingya refugees in Indonesia. In this study, data was divided using the 70:30 split method, where 70% of the data was used for model training and 30% for model testing. The research findings indicate that the SVM model has an accuracy of 76%, while the Naïve Bayes model has an accuracy of 70%. This suggests that the SVM model is better at predicting sentiments and has lower error rates compared to the Naïve Bayes model.
Komparasi Algoritma Naïve Bayes dan Logistic Regression Untuk Analisis Sentimen Metaverse Ramadhani, Bagus; Suryono, Ryan Randy
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 2 (2024): April 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i2.7458

Abstract

Digital transformation makes the world change rapidly, especially in the development of metaverse technology. The development of metaverse technology has received positive and negative responses from the public, so it is necessary to analyze whether public opinion accepts the development of metaverse technology or vice versa. This research aims to analyze 6728 public comment data regarding the metaverse on social media X using a text mining approach. By comparing text mining algorithm models, this experiment seeks to find the best algorithm for metaverse sentiment analysis, thereby providing insight to industry players involved in metaverse development. This research experiment uses a comparison of two algorithms, namely Naïve Bayes and Logistic Regression. The comparison results for the Naïve Bayes algorithm have an accuracy value of 90% and Logistic Regression of 91%, but the precision, recall, and F1-Score results are low. This indicates that the machine predominantly learns positive sentiment because this sentiment has a majority label, namely 5799 positive sentiment data, while negative sentiment is a minority label with 795 data. To overcome the problem of unbalanced data (Imbalance) in this research, SMOTE optimization was used. The results of SMOTE optimization have a superior value in the Logistic Regression algorithm, the accuracy value of 95% has also increased in the confusion matrix, namely the precision value of 94%, recall of 93%, and F1-Score of 95%. Meanwhile, the Naïve Bayes algorithm has a smaller value, namely 91% accuracy, and the negative sentiment confusion matrix has increased to 87% precision, 97% recall, and 92% F1-Score, so the accuracy and confusion matrix values have better performance.
Combination of Weighted Product Method and Entropy Weighting in the Best Warehouse Employee Recommendation Waqas Arshad, Muhammad; Darwis, Dedi; Sulistiani, Heni; Suryono, Ryan Randy; Rahmanto, Yuri; Megawaty, Dyah Ayu; Setiawansyah
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 5 No. 1 (2024): Agustus 2024
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v5i1.2095

Abstract

The best warehouse employees are individuals who show exceptional dedication and precision in carrying out their duties. Not only do they ensure that every process, from receipt to delivery, is carried out with high accuracy, but they are also proactive in finding ways to improve operational efficiency. The main problem lies in the proper assessment of employees' technical skills and soft skills, such as rigor, time management ability, and teamwork. Additionally, the selection process can be complicated when it comes to balancing previous work experience and adaptability to new technologies. Without effective assessment methods, the risk of selecting the wrong employee can negatively impact the overall productivity and operational efficiency of the warehouse. The purpose of the study, which combines entropy weighting method with the WP method is an approach that can increase objectivity and accuracy in multi-criteria decision-making. In this combination, the Entropy method is used first to objectively determine the weight of the criteria based on the degree of variation or information contained in the data of each criterion. The weights generated by the Entropy method reflect the importance of criteria based on how much information is provided, assuming that criteria with more variety have more information. Once the weights are determined, the Weighted Product method is used to evaluate and rank alternatives. Based on the results of the recommendation for the selection of the best warehouse employee Hadi occupies the top position in the selection of the best warehouse employee with a score of 0.07194. His position was followed by Putri who got a score of 0.07082, showing a performance that was also very good and only slightly below Hadi. Budi is ranked third with a score of 0.06621, while Deni is ranked fourth and Kiki is fifth with a score of 0.06544 and 0.06524, respectively. The score obtained by each employee shows a relatively small difference, reflecting the fierce competition and high quality of performance among the employees
Analisis Sentimen Ibu Kota Nusantara menggunakan Algoritma Support Vector Machine dan Naïve Bayes Setiawan, Andra; Suryono, Ryan Randy
Jurnal Pendidikan Informatika (EDUMATIC) Vol 8 No 1 (2024): Edumatic: Jurnal Pendidikan Informatika
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v8i1.25667

Abstract

The Government's policy of moving the Indonesian capital city (IKN) is considered controversial, sparking various responses from the public, especially on the social media platform X. This research aims to analyze tweet sentiment related to IKN and compare two algorithms. In this experiment, we collected 5,128 tweets regarding IKN from the X application. The dataset was classified into 2,598 positive sentiments and 1,659 negative sentiments. To analyze these sentiments, we used Text Mining techniques, comparing the Support Vector Machine (SVM) and Naive Bayes algorithms. To improve the performance of these algorithms in analyzing the data, SMOTE optimization was employed to address data imbalance. Our findings show that the SVM algorithm achieves an accuracy of 84%, while the Naive Bayes algorithm achieves an accuracy of 77%. Thus, it can be concluded that the SVM algorithm is superior to the Naive Bayes algorithm. Furthermore, the use of SMOTE optimization proved to enhance the ability of both algorithms to identify positive sentiment, as evidenced by the precision, recall, and F1-Score values. The SVM algorithm achieved a precision of 82%, recall of 86%, and F1-Score of 84%, while the Naive Bayes algorithm achieved a precision of 71%, recall of 92%, and F1-Score of 80%.
Decision Support System for Platform Selection in E-Commerce Using the OWH-TOPSIS Method Wang, Junhai; Isnain, Auliya Rahman; Suryono, Ryan Randy; Rahmanto, Yuri; Mesran, Mesran; Setiawansyah, Setiawansyah
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.5990

Abstract

Platforms in e-commerce are digital systems that allow online transactions to buy and sell products or services. E-commerce platforms also provide benefits for business actors because they are able to reach a wider market without geographical restrictions, while offering efficiency in business operations. The main problem in choosing a platform for e-commerce is often related to the sheer number of options available and the variety of criteria that must be considered. Criteria such as fees, platform popularity, transaction security, ease of use, features provided, as well as customer service support are important factors in determining the most suitable platform. The implementation of a decision support system to help select the optimal e-commerce platform by applying the OWH-TOPSIS method shows that this system can provide accurate and effective recommendations, so that it can be used as a reference for users in determining the e-commerce platform that suits their needs. The decision support system using the OWH-TOPSIS method provides an efficient and objective solution in the selection of e-commerce platforms. The results of the ranking of the best e-commerce platforms show that Platform D occupies the top position with the highest score value, which is 0.882. In second place is Platform E which obtained a score of 0.8599, followed by Platform A with a score of 0.8341.
Implementasi Teknologi Irigasi Tetes pada Tanaman Jagung Menggunakan Sensor Soil Moisture dan Mikrokontroler Esp 32: Technology Implementation Drip Irrigation on Plants Corn Uses Soil Moisture Sensor and Esp 32 microcontroller Saputra, Melian Jefri; Suryono, Ryan Randy
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 5 No. 1 (2025): MALCOM January 2025
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v5i1.1642

Abstract

Penelitian ini bertujuan untuk mengembangkan teknologi irigasi tetes otomatis pada tanaman jagung menggunakan sensor kelembaban tanah (Soil Moisture) dan mikrokontroler ESP32. Latar belakang penelitian ini didasarkan pada permasalahan yang dihadapi petani dalam menyirami tanaman jagung secara manual serta ketidakmampuan mereka untuk menentukan kebutuhan air yang optimal. Dengan mengintegrasikan teknologi berbasis mikrokontroler dan sensor kelembaban, sistem ini dirancang untuk mendeteksi kadar air dalam tanah secara real-time dan mengaktifkan pompa air secara otomatis saat kelembaban tanah berada di bawah ambang batas. Metode yang digunakan adalah pengembangan prototipe yang melibatkan komponen-komponen elektronik seperti ESP32, sensor kelembaban, relay, dan pompa air. Pengujian menunjukkan bahwa sistem ini mampu meningkatkan efisiensi penggunaan air serta mempertahankan kelembaban tanah secara optimal. Hasilnya, teknologi ini terbukti dapat meningkatkan produktivitas tanaman jagung dan mengurangi risiko gagal panen akibat kekurangan air selama musim kemarau.
Implementasi Sensor Gas Amonia Berbasis Internet of Things pada Peternakan Ayam Potong dengan Sistem Monitoring dan Pengendalian Kualitas Udara Otomatis: Implementation of Internet of Things-Based Ammonia Gas Sensors on Broiler Chicken Farms with an Automatic Air Quality Monitoring and Control System Budiawan, Aditia; Suryono, Ryan Randy; Darwis, Dedi
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 5 No. 1 (2025): MALCOM January 2025
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v5i1.1649

Abstract

Penelitian ini bertujuan untuk mengembangkan dan mengimplementasikan sensor gas amonia berbasis IoT pada peternakan ayam potong dengan sistem monitoring dan pengendalian kualitas udara otomatis. Sistem ini menggunakan sensor MQ137 untuk mendeteksi kadar gas amonia dan mikrokontroler ESP32 untuk mengontrol berbagai komponen seperti buzzer, RTC DS1307, dan sistem penyemprotan otomatis. Data kualitas udara dikumpulkan dan dipantau secara real-time melalui aplikasi web, memungkinkan peternak untuk mengambil tindakan cepat dalam menjaga kondisi optimal di kandang ayam. Hasil penelitian menunjukkan bahwa sistem ini efektif dalam mengendalikan kadar gas amonia, dengan penyemprotan air otomatis yang diaktifkan ketika kadar gas melebihi ambang batas 7,2 ppm, sehingga meningkatkan kesehatan dan produktivitas ayam potong
Analisis Sentimen Aplikasi BCA Mobile Menggunakan Algoritma Naive Bayes dan Suport Vector Machine Bhatara, Dimas Wahyu; Suryono, Ryan Randy
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 9, No 4 (2024)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v9i4.5536

Abstract

Kemajuan teknologi telah mengubah banyak aspek terutama dalam hal transaksi, dengan aplikasi seperti BCA Mobile menjadi salah satu pilihan utama. Aplikasi ini memungkinkan pengguna untuk melakukan berbagai aktivitas finansial secara online. Dengan popularitasnya yang terus meningkat, mencapai lebih dari 5 juta unduhan di Google Play Store, penelitian ini bertujuan untuk mengevaluasi pandangan pengguna terhadap aplikasi ini, baik positif maupun negatif. Analisis dilakukan menggunakan dua metode utama, yaitu algoritma Naïve Bayes dan Support Vector Machine (SVM), yang kemudian diperbaiki kinerjanya dengan menggunakan Synthetic Minority Over-Sampling Technique (SMOTE). Hasil penelitian menunjukkan bahwa SVM mencapai akurasi 85%, sementara Naïve Bayes 83%. Meskipun keduanya memiliki tingkat akurasi yang hampir serupa terdapat perbedaan dalam kemampuan masing-masing model dalam mengklasifikasikan sentimen positif dan negatif..Naïve Bayes memiliki recall yang sedikit lebih rendah untuk ulasan positif sebesar 81% dibandingkan dengan SVM mencapai 85%, namun memiliki presisi yang sedikit lebih tinggi..Sebaliknya, SVM memiliki recall yang lebih rendah untuk ulasan negatif, namun memiliki presisi yang lebih tinggi..Ini menunjukkan kemampuan SVM dalam menangani distribusi fitur dan kelas yang kompleks, yang tidak dapat ditangani dengan baik oleh Naïve Bayes.
ANALISIS SENTIMEN HATE SPEECH MENGENAI CALON WAKIL PRESIDEN INDONESIA MENGGUNAKAN ALGORITMA BERT Junita, Elvika Alya; Suryono, Ryan Randy
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 9, No 4 (2024)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v9i4.5625

Abstract

Indonesia sebagai negara demokratis mengalami momen penting menjelang  pemilihan  umum,  khususnya  presiden  dan  wakil  presiden.  Persaingan politik yang sengit diwarnai dengan beragam pandangan dan retorika politik. Namun, munculnya hate speech sebagai bentuk ekstrem dari ekspresi politik mengancam stabilitas sosial dan integritas demokrasi. Hate speech dapat mengganggu harmoni masyarakat, mempengaruhi proses pemilihan umum dengan menyebarkan informasi palsu, dan merusak suasana politik. Analisis sentimen sangat penting dalam mendeteksi dan menangani hate speech terkait dengan calon Wakil Presiden Indonesia. Penelitian ini menggunakan data Twitter untuk mengeksplorasi opini masyarakat terhadap calon presiden dengan kata kunci Imin, Gibran, dan Mahfud MD sebanyak 2692 data. Hasil eksperimen menunjukkan bahwa algoritma BERT memiliki tingkat akurasi yang sangat tinggi, mencapai rata-rata 100% pada dataset Gibran Rakabuming Raka dan Mahfud MD. Analisis juga menunjukkan bahwa proporsi sentimen positif terhadap calon wakil presiden menunjukkan kecenderungan bahwa Muhaimin Iskandar mencapai tingkat akurasi 98,17%.
Co-Authors ., Bagastian Achmad Nizar Hidayanto Ade Dwi Putra Aditia Yudhistira Agresia, Vania Ahmad Ari Aldino Ajie Tri Hutama Al Afif, Satria Anadas, Sylvi Ananda, Dhea AndaruJaya, Rinaldi Sukma Ansyah, Ferdi Ariany, Fenty Arshad, Muhammad Waqas Bagus Reynaldi, Dimas Bakti, Da'i Rahman Bhatara, Dimas Wahyu Budi Santosa Budi Santosa Budiawan, Aditia Budiman, Ega Christ Mario Dana Indra Sensuse Darmini Darmini DAVID KURNIAWAN Dede Krisna Friansyah Dedi Darwis Desi Fitria Dewantoro, Mahendra Dinda Septia Ningsih Dwi Nanda Agustia Dyah Ayu Megawaty Eko Putro, Dimas Eskiyaturrofikoh, Eskiyaturrofikoh Fadli, Muhammad Firdaus, Noval Dinda Firmanda, Fabian Fudholi, Muhammad Fahmi Gunawan, Rakhmat Dedi Handini, Meitry Ayu Hasiholan Simamora, Alfred Heni Sulistiani Hermana, BP Putra Ignatius Adrian Mastan Indra Budi Isnain, Auliya Rahman Iwan Purwanto Iwan Purwanto Juarsa, Doris Junita, Elvika Alya Kamrozi Karimah Sofa Kautsarina Kautsarina Kautsarina Kautsarina Kautsarina Kautsarina Kautsarina Krishna Yudhakusuma P.M. Laksono, Urip Hadi Megawaty, Dyah Ayu Meliana, Yovi Mesran, Mesran Miranda, Khyntia Muh. Alviazra Virgananda Muhamad Adhytia Wana Putra Rahmadhan Muhammad Fadli Muhammad Ridwan Mustaqim, Ilham Zharif Nababan, Cynthia Deborah Natasha Panca Hadi Putra Prasetio, Mugi Pratama, Rangga Rizky Pratiwi, Adelia Purnama, Putri Intan Purwanti, Dian Sri Putra, Djalu Bintang Rachmad Nugroho Rachmi Azanisa Putri Rahmat Dedi Gunawan Raihandika, M Rafi Ramadhani, Bagus Reifco Harry Farrizqy Rias Kumalasari Devi Riyama Ambarwati Sanjaya, Ival Sanriomi Sintaro Saputra, Melian Jefri Saputra, Rizky Herdian Sari, Cici Nurita Kumala Sari, Kevinda Sari, Putri Kumala Sarumpaet, Lisyo Hileria Setiawan, Andra Setiawansyah Setiawansyah Setiyana, Beta Agus Setyani, Tria Simarmata, Yohanes Sobirin, Muhammad Hamdan Sulistiyo, Raka Sumanto, Sumanto Surono, Muhammad Surya Indra Gunawan Tri Widodo Ulum, Faruk Wahyudi, Agung Deni Wang, Junhai Waqas Arshad, Muhammad Yeni Agus Nurhuda Yeni Agus Nurhuda Yulia Indriani Yuri Rahmanto Yuspita, Emi