SISTEM IDENTIFIKASI BERITA PALSU YANG TERDAPAT DI WEB DENGAN MENGGUNAKAN METODE MACHINE LEARNING
Total View This Week0
Total View This Week0
Institusion
Universitas Sriwijaya
Author
MUHAMMAD TAMLIKHO (STUDENT ID : 09011281621031)
Reza Firsandaya Malik (LECTURER ID : 0025047609)
Firdaus Firdaus (LECTURER ID : 0221017801)
Reza Firsandaya Malik (LECTURER ID : 0025047609)
Firdaus Firdaus (LECTURER ID : 0221017801)
Subject
Q325.5 Machine learning
Datestamp
2020-07-23 07:53:09
Abstract :
With the development of the internet which continues to grow more rapidly, the internet has turned into a source of information that can be easily accessed. The development of information technology such as social media and news contained on the web helped to push the spread of fake news very easy and quick. In this study the classification was carried out using five classifiers, namely Random Forest Classifier (RFC), Support Vector Machine (SVM), Logistic Regression Classifier (LRC), Deep Neural Network (DNN) and K-Nearest Neighbor (KNN). The classification was carried out in thirty-seven experiments (models / scenarios) for two datasets. From all experiments, each classifier has the best model / scenario which is judged by the good performance value generated. Among the models / scenarios of the experiments carried out, there is each one of the best models / scenarios that produce the highest accuracy value for each dataset used. the model / scenario is also the best model / scenario for all experiments of all classifiers for each dataset used.
With the development of the internet which continues to grow more rapidly, the internet has turned into a source of information that can be easily accessed. The development of information technology such as social media and news contained on the web helped to push the spread of fake news very easy and quick. In this study the classification was carried out using five classifiers, namely Random Forest Classifier (RFC), Support Vector Machine (SVM), Logistic Regression Classifier (LRC), Deep Neural Network (DNN) and K-Nearest Neighbor (KNN). The classification was carried out in thirty-seven experiments (models / scenarios) for two datasets. From all experiments, each classifier has the best model / scenario which is judged by the good performance value generated. Among the models / scenarios of the experiments carried out, there is each one of the best models / scenarios that produce the highest accuracy value for each dataset used. the model / scenario is also the best model / scenario for all experiments of all classifiers for each dataset used.
File :
RAMA_56201_09011281621031.pdf
RAMA_56201_09011281621031_TURNITIN.pdf
RAMA_56201_09011281621031_0025047609_0221017801_01_front_ref.pdf
RAMA_56201_09011281621031_0025047609_0221017801_02.pdf
RAMA_56201_09011281621031_0025047609_0221017801_03.pdf
RAMA_56201_09011281621031_0025047609_0221017801_04.pdf
RAMA_56201_09011281621031_0025047609_0221017801_05.pdf
RAMA_56201_09011281621031_0025047609_0221017801_06_ref.pdf
RAMA_56201_09011281621031_0025047609_0221017801_07_lamp.pdf
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
