Claim Missing Document
Check
Articles

Found 2 Documents
Search

Klasifikasi Berita detik.com Terkait Teknologi Informasi Menggunakan TF-IDF dan Naive Bayes Nur Bainatun Nisa; Rivaldi Prima Nanda; Zahra Humaira Kudadiri; Bagus Ageng Alfahri; Mhd Furqan
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 8, No 3 (2025): Juni 2025
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v8i3.9171

Abstract

Abstrak – Penelitian ini membahas tentang klasifikasi berita Detik.com terkait teknologi informasi dengan menerapkan metode Term Frequency-Inverse Document Frequency (TF-IDF) sebagai ekstraksi fitur dan algoritma Naive Bayes sebagai model klasifikasi. Tujuan dari penelitian ini adalah untuk mengelompokkan berita-berita yang dimuat pada situs Detik.com ke dalam beberapa kategori utama di bidang teknologi informasi, seperti kecerdasan buatan, keamanan siber, gadget, dan aplikasi. Proses penelitian diawali dengan pengumpulan 1.050 data berita dari Detik.com menggunakan search query ‘teknologi informasi’ pada rentang Maret hingga April 2025. Data kemudian diproses melalui tahapan text preprocessing, meliputi case folding, tokenizing, stopword removal, dan stemming. Selanjutnya, fitur teks diubah menjadi representasi numerik menggunakan TF-IDF, lalu dilakukan pelatihan model klasifikasi dengan algoritma Naive Bayes. Evaluasi kinerja model dilakukan menggunakan metrik akurasi, precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa kombinasi TF-IDF dan Naive Bayes efektif dalam mengklasifikasikan berita teknologi informasi, dengan akurasi model mencapai 85%. Temuan ini menunjukkan bahwa pendekatan klasifikasi berbasis machine learning dapat membantu pengelompokan dan identifikasi topik utama secara otomatis dalam berita teknologi informasi di Detik.com.Kata Kunci: TF-IDF; Naive Bayes; Klasifikasi; Detik.com; Teknologi Informasi.Abstract – This study discusses the classification of Detik.com news related to information technology by applying the Term Frequency-Inverse Document Frequency (TF-IDF) method as a feature extraction and the Naive Bayes algorithm as a classification model. The purpose of this study is to group news published on the Detik.com site into several main categories in the field of information technology, such as artificial intelligence, cybersecurity, gadgets, and applications. The research process began with the collection of 1,050 news data from Detik.com using the search query 'information technology' in the range of March to April 2025. The data was then processed through the text preprocessing stage, including case folding, tokenizing, stopword removal, and stemming. Furthermore, text features were converted into numeric representations using TF-IDF, then training a classification model with the Naive Bayes algorithm. Model performance evaluation was carried out using accuracy, precision, recall, and F1-score metrics. The results showed that the combination of TF-IDF and Naive Bayes was effective in classifying information technology news, with a model accuracy reaching 85%. This finding suggests that a machine learning-based classification approach can help automatically cluster and identify key topics in information technology news on Detik.com.Keywords: TF-IDF; Naive Bayes; Classification; Detik.com; Information Technology.
Ekstraksi Fitur Citra Grayscale dengan Convolutional Neural Networks Diah Putri Kartikasari; Fiqri Dian Priyatna Sinaga; Tiara Ayu Triarta Tambak; Zahra Humaira Kudadiri; M. Khalil Gibran
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 5 No. 1 (2025): April: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v5i1.5175

Abstract

This study aims to explore the use of Convolutional Neural Networks (CNN) in feature extraction from grayscale images for avocado object identification. The process begins with taking a grayscale image of the avocado object to be recognized. Convolution is applied using a 3x3 horizontal Sobel kernel filter with a stride of 1 to the right, and a ReLU (Rectified Linear Unit) activation function to improve the network's ability to extract relevant features. After the convolution stage, pooling is carried out using the max pooling method to reduce the image dimension while retaining important information, thereby speeding up the training process and reducing the risk of overfitting. The processed image is then flattened to produce a feature vector that is ready to be used in classification. The results of the study indicate that the CNN approach can be used as an effective method for feature extraction and edge detection on avocado objects from grayscale images.