<![CDATA[The development of information technology has made the popularity of social media increase in recent years, one of which is Youtube. Youtube’s popularity make this platform a major source of sentiment where almost everyone tends to express their views in the form of comments. These commnent not only express people but also have more meaning about their experiences. Comments originating from social media are unstructured so that in sentiment analysis the preprocessing stage is an important task. There are many techniques used in preprocessing including stopwrod and stemming. However, several studies have shown that the use of stopword and stemming gives different result. Therefore, in this paper, the researcher further anlyzes the effect of applying stopword and stemming on Youtube video comment regarding the New Normal policy using Long Short Term-Memory. The result obtained we found that the use of stopword and stemming greatly affects the performance of the model, this is because a lot of information is lost after the stopword process and some words change meaning after stemming.]]>
Copyrights © 2022
