Claim Missing Document
Check
Articles

Found 35 Documents
Search

Implementasi Algortima Support Vector Machine Dalam Klasifikasi Komentar Pengguna Produk Skintific di E-Commerce Artika, Priti Rindi; Lubis, Aidil Halim
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol 14, No 2: Agustus 2025
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v14i2.3137

Abstract

The large number of consumer reviews of skincare products such as Skintific 5X Ceramide Barrier Repair Moisture Gel on e-commerce platforms raises the need for automated sentiment analysis. This study classifies 2,000 user comments from the Sociolla app using the Support Vector Machine (SVM) algorithm. Data were obtained through web scraping and processed through preprocessing, lexicon-based labeling, and word weighting using TF-IDF. SVM with a linear kernel was used to distinguish positive and negative comments. Performance evaluation using a confusion matrix resulted in an accuracy of 89.73%, a precision of 0.94, a recall of 0.75, and an F1-score of 0.83 for the positive class, and a precision of 0.88, a recall of 0.98, and an F1-score of 0.93 for the negative class. These results indicate that SVM is effective for sentiment classification in online beauty product reviews.Keywords: E-commerce; Support Vector Machine; Sentiment Analysis; TF-IDF; Sociolla; Skintific; Lexicon-based AbstrakBanyaknya ulasan konsumen terhadap produk perawatan kulit seperti Skintific 5X Ceramide Barrier Repair Moisture Gel di platform e-commerce menimbulkan kebutuhan akan analisis sentimen otomatis. Penelitian ini mengklasifikasikan 2000 komentar pengguna dari aplikasi Sociolla menggunakan algoritma Support Vector Machine (SVM). Data diperoleh melalui web scraping dan diproses dengan tahapan preprocessing, pelabelan berbasis lexicon, serta pembobotan kata menggunakan TF-IDF. SVM dengan linear kernel digunakan untuk membedakan komentar positif dan negatif. Evaluasi performa menggunakan confusion matrix menghasilkan akurasi sebesar 89,73%, precision 0,94, recall 0,75, dan F1-score 0,83 untuk kelas positif, serta precision 0,88, recall 0,98, dan F1-score 0,93 untuk kelas negatif. Hasil ini menunjukkan bahwa SVM efektif untuk klasifikasi sentimen pada ulasan produk kecantikan secara daring. 
Penerapan Metode Simple Additive Weighting pada Sistem Pendukung Keputusan Pemilihan Raket Bulu Tangkis Saragih, Ahmad Fadhly Sani; Muhammad Ikhsan; Lubis, Aidil Halim
Jurnal IT UHB Vol 6 No 3 (2025): Jurnal Ilmu Komputer dan Teknologi
Publisher : Universitas Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35960/ikomti.v6i3.1995

Abstract

Badminton is one of the most popular sports in Indonesia and a source of national pride due to the achievements of its athletes in international tournaments. The racket is the primary equipment used in badminton, and selecting the appropriate one is crucial for performance and comfort. However, many beginner players still find it difficult to choose a suitable racket according to the coach’s recommendation. Therefore, this study developed a Decision Support System (DSS) for badminton racket selection by applying the Simple Additive Weighting (SAW) method. Four alternatives—Yonex, Li-Ning, Flypower, and Victor—were evaluated using five criteria: price, racket weight, head type, shaft flexibility, and handle size. The integration of the SAW method into a web-based application produced ranking results for racket selection. The results showed that Li-Ning G Force Superlite 3900 achieved the highest score of 0.8845, indicating it as the most suitable racket for beginner players.
Penerapan Metode PID pada Sistem Pemberi Pakan Kucing Otomatis Berbasis IOT (Internet of Things) Fadiga, Muhammad; Kurniawan, Rakhmat; Lubis, Aidil Halim
VISA: Journal of Vision and Ideas Vol. 5 No. 1 (2025): Journal of Vision and Ideas (VISA)
Publisher : IAI Nasional Laa Roiba Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47467/visa.v5i1.5772

Abstract

An automatic feeding system that can be monitored and managed remotely is needed amidst the busy schedules of pet owners, especially for cats. As a result, an automatic cat feeder that can be operated and viewed remotely via the Internet of Things was developed in this research. By understanding the properties of loadcell sensors and servo motors, research in this case seeks to create an automatic cat feeding system that uses a PID approach to regulate food according to the cat's needs. For the convenience of remote use, the system also allows monitoring and control using the Telegram application. An ESP32 microcontroller, a servo for food release, a loadcell sensor for food weight measurement, and a camera for cat detection were all used in the development of this research system. An automatic cat feeding system that produces servo motor and load cell sensor calibration values with average error results of 1.84%, 3.86%, and accuracy of 96.14%, 98.16% was successfully developed in this research. With an error percentage of 1.67%, this research was able to produce food that matched the cat food dosage using the PID approach with trial and error tuning, especially with a cat food dosage of 60 grams. Based on the research findings, it can be said that this system works as planned and offers a practical way to feed cats food precisely and automatically.
Analisis Sentimen Masyarakat Terhadap Resesi Ekonomi Global 2023 Menggunakan Algoritma Naïve Bayes Classifier Sriani; Lubis, Aidil Halim; Harahap, Yunus Fadillah
Elkom: Jurnal Elektronika dan Komputer Vol. 16 No. 2 (2023): Desember : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v16i2.1673

Abstract

The global economic recession is a global economic downturn that affects the domestic economies of countries in the world. The stronger the economic dependence of one country on the global economy, the faster a recession will occur in that country. In 2020 the country of Indonesia and even the world are exposed to the COVID-19 virus which has an impact on the country's economic growth, even the world economy. This is the trigger for an economic recession. This has led to many different public perspectives on the occurrence of a global economic recession whose opinions or reactions are expressed on social media Youtube. The data was obtained by crawling techniques from social media Youtube with a total of 500 comments used. The data is then labeled (class) with a lexicon-based method with an Indonesian language dictionary. From the labeling results, it was obtained 185 positive labeled data (37%) and 315 negative opinions (63%). The data preprocessing stage is carried out in preparation for the data to be processed for sentiment analysis. Of the many opinions obtained, an analysis of public sentiment regarding the 2023 global economic recession will be carried out using the Naïve Bayes classification algorithm. This study also applied the TF-IDF word weighting method with the n-gram feature used, namely bigram (n=1). The system will be evaluated using a confusion matrix. The implementation results show a prediction model with a total of 500 opinion data with a comparison of training data and test data of 9:1, producing an accuracy value of 84.00%, a precision value of 75.00%, a recall of 30.00%, and an f1-score of 42.86%. The performance of the system model built in this study can be said to be good.
RANCANG BANGUN SISTEM KONTROL SUHU, KELEMBABAN DAN CAHAYA PADA RUMAH WALET MENGGUNAKAN FUZZY BERBASIS MIKROKONTROLER Sihombing, Rizki Andika; Kurniawan, Rakhmat; Lubis, Aidil Halim
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol 8, No 4 (2025): November 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i4.4684

Abstract

Abstract: Swiftlet nests have a high market value because the saliva used to make them has many benefits, including treating illnesses. They can also promote a healthy reproductive system and strengthen the lungs. Therefore, a system is needed to simplify swiftlet farming. This involves designing a microcontroller-based fuzzy control system for temperature, humidity, and light in swiftlet houses as a solution for swiftlet breeders. The device will utilize two sensors: a DHT11 sensor and an LDR sensor. The DHT11 sensor maintains the stability of the room's temperature and humidity, while the LDR sensor maintains the light intensity of the swiftlet house. The conditions that have been determined based on 12 fuzzy logic rules, from the DHT11 sensor conditions, namely cold temperatures with a range of 0 - 15, moderate temperatures with a range of 15-30, and hot temperatures with a range of 30 - 45, in humidity conditions with a dry range of 0-50 and humid 0 - 95 while in the LDR sensor conditions, namely bright with an ADC value range on the LDR of 0 - 500 and dark conditions in the range of 500 - 1024. The defuzzification output value obtained is [0 10] where 0 is OFF and 10 is on for 10 minutes. Keyword: Swiftlet, Fuzzy Logic, DHT11, LDR Abstrak: Sarang burung walet mempunyai nilai jual yang tinggi karena air liur yang digunakan untuk membuat sarang memiliki banyak manfaat salah satunya adalah mengobati penyakit. Selain itu bisa juga untuk menyehatkan sistem reproduksi dan memperkuat paru-paru. Sehingga di butuhkan suatu sistem agar peternakan burung walet semakin lebih mudah dengan membuat perancangan suatu sistem kontrol suhu kelembaban dan cahaya pada rumah walet menggunakan fuzzy berbasis mikrokontroler sebagai solusi bagi para peternak burung walet. Dimana alat yang akan dibuat menggunakan dua sensor yaitu sensor DHT11 dan sensor LDR. Sensor DHT11 berfungsi untuk menjaga kestabilan suhu dan kelembaban ruangan sedangkan sensor LDR berfungsi unutuk menjaga intensitas cahaya dari rumah walet tersebut. Kondisi yang telah di tentukan berdasarkan 12 rule logika fuzzy, dari kondisi sensor DHT11 yaitu suhu dingin dengan range 0 – 15, suhu sedang dengan range 15-30, dan suhu panas dengan range 30 – 45, pada kondisi kelembaban dengan range kering 0 50 dan lembab 0 - 95 sedangkan pada kondisi Sensor LDR yaitu terang dengan range nilai ADC pada LDR sebesar 0 - 500 dan kondisi gelap pada range 500 – 1024. Nilai ouput defuzzifikasi yang didapat adalah [0 10] dimana 0 dengan kondisi OFF dan 10 dengan kondisi output hitup selama 10 menit. Kata kunci: Burung Walet, Fuzzy , DHT 11, LDR