APLIKASI FILTERING BERITA HOAX BERBASIS WEB DENGAN MENGGUNAKAN METODE COSINE SIMILARITY
Total View This Week0
Total View This Week0
Institusion
Institut Teknologi Perusahaan Listrik Negara
Author
Manik, Ivana Hotma Duma
Jatnika, Hendra
Abdurrasyid, Abdurrasyid
Jatnika, Hendra
Abdurrasyid, Abdurrasyid
Subject
Teknik Informatika
Datestamp
2022-09-20 03:49:06
Abstract :
Google appears in new media and always gets a warm welcome from internet users. Google, we can exchange information with everyone who is a fellow user of the media. The behavior of using social media in Indonesian society, which tends to be consumptive, makes true and false information mixed up. The Cosine Similarity method is a method used to calculate the similarity between two objects expressed in two vectors using keywords from a document as a measure. Data processing starts from text preprocessing, and then topic modeling is done using Cosine Similarity. Meanwhile, the implementation of Precision and Recall is also carried out by preprocessing the text, so that the term is obtained which is then obtained which is then calculated by the TF IDF. Then it is calculated using the Cosine Similarity formula so that the degree value of the training data explanation of the news is obtained with the data collection of news titles. The final result of the Precision and Recall calculation is the magnitude of the degree between the topics from the training data and the title data of a news story so that it is classified from the news title as a hoax or not a hoax. obtained in this study amounted to 77.2%
Google appears in new media and always gets a warm welcome from internet users. Google, we can exchange information with everyone who is a fellow user of the media. The behavior of using social media in Indonesian society, which tends to be consumptive, makes true and false information mixed up. The Cosine Similarity method is a method used to calculate the similarity between two objects expressed in two vectors using keywords from a document as a measure. Data processing starts from text preprocessing, and then topic modeling is done using Cosine Similarity. Meanwhile, the implementation of Precision and Recall is also carried out by preprocessing the text, so that the term is obtained which is then obtained which is then calculated by the TF IDF. Then it is calculated using the Cosine Similarity formula so that the degree value of the training data explanation of the news is obtained with the data collection of news titles. The final result of the Precision and Recall calculation is the magnitude of the degree between the topics from the training data and the title data of a news story so that it is classified from the news title as a hoax or not a hoax. obtained in this study amounted to 77.2%
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
