<![CDATA[Keyword Extraction is the process of identifying and extracting key words or important phrases from a text or document, aiming to quickly identify keyword information from a large amount of data. This research investigates three online news sites in Indonesia, namely Kompas.com, Detik.com, and Tempo.co. The keyword extraction process is strengthened by the TF-IDF (Term Frequency - Inverse Document Frequency) method, assigning a high weight to words that frequently appear in one document but rarely in others. The TF-IDF calculation results in different weights for each word. Many words were successfully extracted from the three sites, displaying 30 keywords from the dataset. The accuracy of the weight calculation was then tested using F1-Score, resulting in an F1-Score of 99.67%, with an accuracy rate of 99.76%.]]>
Copyrights © 2024
