<> "The repository administrator has not yet configured an RDF license."^^ . <> . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS"^^ . "The COVID-19 pandemic has highlighted the importance of leveraging online data\r\nas a tool for predicting future infectious disease trends. This study aims to compare\r\nthe performance of two deep learning methods, namely Convolutional Neural\r\nNetwork (CNN) and Recurrent Neural Network (RNN), in predicting the daily frequency\r\nof online news publications based on three sentiment classes: negative, neutral,\r\nand positive. The results show that CNN delivers the best performance, with\r\nan RMSE of 0.14 and MAPE of 27%, demonstrating its superiority in recognizing\r\ncomplex patterns in large datasets, especially for negative and neutral sentiment\r\ndata. Meanwhile, RNN also yields reasonably good results, particularly for smaller\r\ndatasets such as those with positive sentiment, although with slightly lower accuracy\r\n(RMSE of 0.17 and MAPE of 35%). These findings suggest that CNN is\r\nhighly recommended for predictions on large-scale datasets, while RNN serves as\r\na relevant alternative when data availability is limited, albeit with a slightly lower\r\naccuracy rate. Overall, deep learning models have proven effective in predicting\r\nthe frequency of online news publications based on sentiment, supporting the use\r\nof online news as an alternative data source for monitoring public health issues.\r\nKeywords: COVID-19, infectious diseases, online news, sentiment.\r\n\r\nPandemi COVID-19 telah menyoroti pentingnya pemanfaatan data online sebagai\r\nalat untuk memprediksi tren penyakit menular di masa depan. Studi ini bertujuan\r\nuntuk membandingkan kinerja dua metode deep learning, yaitu Convolutional Neural\r\nNetwork (CNN) dan Recurrent Neural Network (RNN), dalam memprediksi\r\nfrekuensi harian publikasi berita online berdasarkan tiga kelas sentimen: negatif,\r\nnetral, dan positif. Hasil penelitian menunjukkan bahwa CNN memberikan kinerja\r\nterbaik, dengan nilai RMSE sebesar 0,14 dan MAPE sebesar 27%, menunjukkan\r\nkeunggulannya dalam mengenali pola kompleks pada dataset besar, terutama untuk\r\ndata sentimen negatif dan netral. Sementara itu, RNN juga menghasilkan performa\r\nyang cukup baik, khususnya untuk dataset yang lebih kecil seperti data dengan sentimen\r\npositif, meskipun dengan tingkat akurasi yang sedikit lebih rendah (RMSE\r\nsebesar 0,17 dan MAPE sebesar 35%). Temuan ini menunjukkan bahwa CNN sangat\r\ndirekomendasikan untuk prediksi pada dataset berskala besar, sementara RNN\r\nmerupakan alternatif yang relevan ketika ketersediaan data terbatas, meskipun dengan\r\ntingkat akurasi yang sedikit lebih rendah. Secara keseluruhan, model deep\r\nlearning terbukti efektif dalam memprediksi frekuensi publikasi berita online berdasarkan\r\nsentimen, sehingga mendukung penggunaan berita online sebagai sumber\r\ndata alternatif untuk pemantauan isu kesehatan masyarakat.\r\nKata kunci: COVID-19, penyakit menular, berita online, sentimen."^^ . "2025-05-20" . . . . . "FAKULTAS MATEMATIKA DAN ILMU PENGETAHUAN ALAM"^^ . . . . . . . "CLARISA "^^ . "SEPTIA DAMAYANTI"^^ . "CLARISA SEPTIA DAMAYANTI"^^ . . . . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (File PDF)"^^ . . . "ABSTRAK.pdf"^^ . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (File PDF)"^^ . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (File PDF)"^^ . . . "SKRIPSI FULL TANPA BAB PEMBAHASAN.pdf"^^ . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (Other)"^^ . . . . . . "indexcodes.txt"^^ . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (Other)"^^ . . . . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (Other)"^^ . . . . . . "indexcodes.txt"^^ . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (Other)"^^ . . . . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (Other)"^^ . . . . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (Other)"^^ . . . . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (Other)"^^ . . . . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (Other)"^^ . . . . . . "lightbox.jpg"^^ . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (Other)"^^ . . . . . . "preview.jpg"^^ . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (Other)"^^ . . . . . . "medium.jpg"^^ . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (Other)"^^ . . . . . . "small.jpg"^^ . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (Other)"^^ . . . . . . "lightbox.jpg"^^ . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (Other)"^^ . . . . . . "preview.jpg"^^ . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (Other)"^^ . . . . . . "medium.jpg"^^ . . . "TIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL\r\nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN)\r\nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE\r\nEPIDEMIC NEWS (Other)"^^ . . . . . . "small.jpg"^^ . . "HTML Summary of #88535 \n\nTIME SERIES ANALYSIS USING CONVOLUTIONAL NEURAL \nNETWORKS (CNN) AND RECURRENT NEURAL NETWORKS (RNN) \nFOR MODELING THE FREQUENCY OF INFECTIOUS DISEASE \nEPIDEMIC NEWS\n\n" . "text/html" . . . "500 ilmu pengetahuan alam dan matematika" . . . "505 Terbitan berseri di bidang ilmu pengetahuan alam" . . . "510 Matematika" . .