<![CDATA[At this time the use of the internet is growing rapidly and the internet plays an important role in various aspects of human life. With the increasing number of Internet users like that, many internet service providers are competing to use their services. In addition, the internet can also be used to search for information through social media, one of which is social media Twitter. Twitter is often used to express emotions about something good or bad. Tweets published by users via Twitter contain an opinion about an object, the object can be of various kinds, such as one of them is about a product or service. One of the internet services that is familiar to various groups of people is First Media, which is often given feedback by its users on the quality of the internet service provider. These responses are often given through various kinds of social media, one of which is Twitter and from these responses a method, namely sentiment analysis, will be carried out. This study discusses reviews in the form of tweets related to first media with the K-Nearest Neighbor algorithm using Rapid Miner tools. Data taken as many as 500 tweets related to the first media. Then do the deletion of ambiguous data so that it only produces 300 tweets. The methodology used is Knowledge Discovery in Databases, namely Data Selection, Data Pre-processing, Transformation, Data Mining, Evaluation. Data labeling is carried out by experts who are divided into positive and negative sentiments. The results of the modeling using K-Fold Cross Validation, and testing the value of k variations with odd numbers ranging from 3 to 25 to get the best accuracy. The highest accuracy was obtained with an accuracy of 84% with a value of k=3. Good classification results can be seen by how much accuracy is obtained.]]>
Copyrights © 2022
