Abstract

Automatic news summarizes are the activity of extracting the core from the news without compromising the significance contained in the news. In the automatic news release there are several methods that can be used, one of which is the Lexical Chain method. This method performs well in summarizes text by determining the highest chain. However, this method has the disadvantage of not being able to identify ambiguous words contained in news sentences. Therefore, to correct the shortcomings of the Lexical Chain method weaknesses, the study was equipped with Word Sense Disambiguation to identify ambiguous words. This study used 100 news about Covid-19 sourced from the most popular online news portals. Accuracy testing of automatic news releases used in this study using Recall-Oriented Understudy for Gisting Evaluation (ROUGE), while the evaluation used in this study there are three kinds of precission, recall, and f-measure. The evaluation results obtained an average precission value of 0.62, recall of 0.20, and f-measure of 0.30.