ANALYSIS OF SENTIMENT ON TEACHER MARKETPLACE ISSUES USING THE LEXICON AND K-NEAREST NEIGHBOR ALGORITHMS

Abstract

The advancement of social media makes it easier for users to express opinions. 
Twitter has become one of the media that is loved by internet users, users can freely 
express their thoughts or opinions, apart from that they can also express everything that is 
being experienced. The busy issue of the Teacher Marketplace initiated by the Minister of 
Education, Nadiem Makarim, has invited many comments from internet users. Twitter 
users' tendencies in posting content can be determined by analyzing sentiment. In this 
research, the Lexicon and K-Nearest Neighbor (KNN) methods are proposed to analyze 
sentiment towards the education minister's discourse on Twitter social media on the topic 
of Teacher Marketplace Issue Sentiment by classifying it into positive, neutral and 
negative. The results of this research show that the accuracy value obtained was 91.70%, 
precision 90.51%, recall 71.95%. By carrying out this sentiment analysis, it is hoped that 
the problems contained in the Marketplace Guru topic controversy can be identified, used 
as input and consideration for further research.