Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal Zero : Jurnal Sains, Matematika, dan Terapan Progresif: Jurnal Ilmiah Komputer
Ikhsan, Muhammad
Universitas Islam Negeri Sumatera Utara
Agriculture, Biological Sciences & Forestry Chemistry Computer Science & IT Control & Systems Engineering Mathematics Physics

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Analisis Sentimen Pada Aplikasi Tokopedia Menggunakan Metode Support Vector Machine Fadila, Daffa; Ikhsan, Muhammad
Progresif: Jurnal Ilmiah Komputer Vol 21, No 1: Februari 2025
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v21i1.2593

Abstract

Tokopedia application attracts buyers with various opinions that reflect public sentiment. This study applies machine learning and text mining techniques to analyze sentiment based on the collected dataset comments. The process begins with data preprocessing, including tokenizing, stopword removal, and TF-IDF weighting. The Support Vector Machine (SVM) model is used to classify sentiment into positive and negative. The data is divided into 80% training data and 20% test data. The experimental results show that the model achieves an accuracy of 81.25%, indicating a fairly good performance in recognizing public opinion patterns. This analysis provides insight into aspects that are appreciated and criticized by the public regarding the Tokopedia application. These findings can be utilized by policies to design strategies that are more responsive to the needs and expectations of the public using the marketplace.Keyword: Machine Learning; Text Mining; Tokopedia; SVM AbstrakAplikasi Tokopedia menarik perhatian pembeli dengan berbagai opini yang mencerminkan sentimen masyarakat. Penelitian ini menerapkan machine learning dan teknik text mining untuk menganalisis sentimen berdasarkan komentar dataset yang telah dikumpulkan. Proses dimulai dengan preprocessing data, termasuk tokenizing, penghapusan stopword, serta pembobotan TF-IDF. Model Support Vector Machine (SVM) digunakan untuk mengklasifikasikan sentimen menjadi positif dan negatif. Data dibagi menjadi 80% data training dan data uji 20%. Hasil eksperimen menunjukkan bahwa model mencapai akurasi 81,25%, menandakan kinerja yang cukup baik dalam mengenali pola opini masyarakat. Analisis ini memberikan wawasan mengenai aspek yang diapresiasi maupun dikritik oleh masyarakat terkait Aplikasi Tokopedia. Temuan ini dapat dimanfaatkan oleh kebijakan untuk merancang strategi yang lebih responsif terhadap kebutuhan dan harapan masyarakat menggunakan marketplace.Kata kunci: Machine Learning; Text Mining; Tokopedia; SVM
IMPLEMENTATION OF SUGENO FUZZY LOGIC ON A RICE-EATING BIRD REPELLENT IN RICE FIELDS TO HELP FARMERS BASED ON MICROCONTROLLERS Ikhsan, Muhammad; Hasugian, Abdul Halim; Gunawan, Gunawan
ZERO: Jurnal Sains, Matematika dan Terapan Vol 6, No 2 (2022): Zero: Jurnal Sains Matematika dan Terapan
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/zero.v6i2.15031

Abstract

The rapid development of technology in the current era, especially in the field of sensors, has made many technologies that use sensors appear. In the agricultural sector itself, the use of sensor technology is not spared. In the agricultural sector, rice fields also require a tool that can detect pests which are usually done by the manual method. The purpose of this research is to help farmers repel bird pests with automation tools to make it easier to monitor the fields from pests. This study conducted experiments carried out by manipulating the research object. The tools used are Arduino Uno microcontrollers as tool controllers, PIR sensors as detection sensors and servo motors as tool drivers. When a pest is detected by the sensor it is then sent to the device controller in the form of Arduino after which the servo motor moves. From the results of testing all the components of the tool, it can be concluded that the results of the entire system work and function in accordance with the system design, the results of the PIR sensor test can detect objects that pass through the sensor with an average of 120 cm
Co-Authors Abdul Halim Hasugian Fadila, Daffa Gunawan, Gunawan