Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal SAINTIKOM (Jurnal Sains Manajemen Informatika dan Komputer)
Priskilla Parimanen
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Pemodelan Deteksi Black Campaign Sumber Media Berita Online Menggunakan Long Short Term Memory Anita Sindar Sinaga; Priskilla Parimanen
Jurnal SAINTIKOM (Jurnal Sains Manajemen Informatika dan Komputer) Vol 22, No 1 (2023): Februari 2023
Publisher : PRPM STMIK TRIGUNA DHARMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53513/jis.v22i1.7554

Abstract

Developed a black campaign detection model to obtain an accuracy level of classifying online news using the LSTM (Long Short Term Memory) algorithm.Aggregation of neural networks in sheet layers to iteratively learn from the data collected by emulating the workings of the like human brain does the job so computers can be trained in abstraction with the problem is not well defined. The LSTM (Long Short Term Memory) text-processing learning method is used for text classification through the stages of data collection, data preprocessing, word representation, classification, and evaluation. LSTM adds capability and erases information from the cell state. Gates consist of a sigmoid part of layers and multiplication operation. Hyperparameter value is determined from Vocab_size, Embedding_dim Activation Function, Number of epoc, and Learning rate. Evaluation of the showing of the data training performance on data testing shows that the value of LSTM is in identifying online news MAPE 8%. The RMSE evaluation shows that the parameter Number of epochs has a high value of 0.053728. 
Co-Authors Sinaga, Anita Sindar R M