Claim Missing Document
Check
Articles

Found 2 Documents
Search

Optimasi Backpropagation Menggunakan Grid Search untuk Penentuan Penerima Beasiswa Bidik Misi Berdasarkan Biodata Pendaftaran Mahasiswa Baru: Backpropagation Optimization Using Grid Search to Determine Bidik Misi Scholarship Recipients Based on New Student Registration Biodata Farida Gultom; Nova Erawati Sidabalok; Cindy Paramitha; Rinto Imanuel Gultom
Jurnal Pendidikan Sains dan Komputer Vol. 6 No. 02 (2026): Artikel Riset, Juni 2026
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/jpsk.v6i02.9083

Abstract

The Bidik Misi Scholarship Program is a form of educational assistance provided to outstanding students from economically disadvantaged families. This program aims to expand access to higher education, reduce the gap in learning opportunities, and support the improvement of human resource quality. In practice, the selection process for scholarship recipients is still often carried out manually based on assessments of various administrative, social, and economic criteria. This process has the potential to create subjectivity, requires a relatively long time, and increases the possibility of errors in decision-making. Therefore, a prediction system is needed that can assist the selection process more objectively, quickly, and accurately. This study developed a prediction model for Bidik Misi Scholarship recipients using the Backpropagation algorithm optimized through the Grid Search method to obtain the best hyperparameter combination. The data used were new student registration biodata covering various social, economic, and academic indicators. The model was built using an Artificial Neural Network by comparing the performance of the Grid Search optimization model and the standard Backpropagation model. The results showed that the optimized model using Grid Search achieved an accuracy rate of 88.46%. In comparison, the standard Backpropagation model with the Stochastic Gradient Descent (SGD) solver produced a higher accuracy of 96.15%. These findings demonstrate that selecting the right hyperparameters significantly impacts model performance and indicate that the standard Backpropagation model is more appropriate for the characteristics of the data used. The resulting system is expected to support the scholarship recipient selection process more efficiently, objectively, consistently, and transparently.
Implementasi  Naive Bayes untuk Klasifikasi Berita Hoaks pada Media Online Berbasis Web Cindy Paramitha; Iqbal Giffari Ritonga; Syaipuddin
Jurnal Nasional Komputasi dan Teknologi Informasi Vol. 9 No. 5 (2026): Oktober, 2026
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/

Abstract

Abstrak - Perkembangan teknologi informasi mempermudah penyebaran informasi, namun juga meningkatkan penyebaran berita hoaks yang dapat menyesatkan masyarakat. Penelitian ini bertujuan membangun sistem klasifikasi berita hoaks berbasis web menggunakan algoritma Multinomial Naive Bayes sebagai alat bantu identifikasi awal berita yang berpotensi hoaks. Dataset diperoleh dari Kaggle dan setelah proses pembersihan terdiri atas 23.709 berita, yang dibagi menjadi 18.967 data latih dan 4.742 data uji dengan perbandingan 80:20. Tahapan penelitian meliputi preprocessing berupa case folding, cleaning, tokenizing, stopword removal, dan stemming, kemudian pembobotan kata menggunakan Term Frequency-Inverse Document Frequency (TF-IDF). Model dilatih menggunakan data latih dan dievaluasi menggunakan data uji. Hasil pengujian menunjukkan bahwa model memperoleh akurasi sebesar 97,34%, dengan F1-score sebesar 97,49% pada kelas hoaks dan 97,18% pada kelas fakta, serta macro-F1 sebesar 97,34%. Sistem yang dikembangkan dapat menerima teks berita dan menampilkan hasil klasifikasi beserta probabilitas prediksi melalui antarmuka berbasis web. Dengan demikian, sistem ini dapat dimanfaatkan sebagai alat bantu penyaringan awal berita yang berpotensi hoaks, bukan sebagai pengganti proses verifikasi fakta. Kata Kunci : Berita Hoaks; Naive Bayes; TF-IDF; Klasifikasi; Web;   Abstract – Advances in information technology have facilitated the dissemination of information but have also increased the spread of hoaxes that may mislead the public. This study aims to develop a web-based hoax news classification system using the Multinomial Naive Bayes algorithm as an initial screening tool for news that may contain hoax information. The dataset was obtained from Kaggle and, after cleaning, consisted of 23,709 news articles, divided into 18,967 training data and 4,742 testing data using an 80:20 ratio. The research stages included preprocessing through case folding, cleaning, tokenization, stopword removal, and stemming, followed by word weighting using Term Frequency-Inverse Document Frequency (TF-IDF). The model was trained using the training data and evaluated using the testing data. The evaluation results showed an accuracy of 97.34%, with an F1-score of 97.49% for the hoax class and 97.18% for the factual class, and a macro-F1 score of 97.34%. The developed system accepts news text and displays the classification result along with the prediction probability through a web-based interface. Therefore, the system can be used as an initial screening tool for news that may contain hoax information, rather than as a substitute for fact-checking. Keywords: Hoax News; Naive Bayes; TF-IDF; Classification; Web;