<![CDATA[Comics are literary works whose story descriptions are displayed in the form of pictures and in the story there is one character who is favored. The division of comics into genres is less effective, because the words represent inappropriate genres. Therefore we need a system that can determine the genre of a comic automatically due to the many genres of the comic. This study uses text mining and TF-IDF for the process of determining the comic genre. Text mining can be defined as the discovery of new information that was previously unknown to computers by extracting automatic information from different sources. Meanwhile, resource data is used as a reference in determining the comic genre. In this study, comics were divided into 4 categories: horror, inspirational, mystery and romantic. The text entered is in the form of title, author, and synopsis. This synopsis will be processed to produce a comic genre. The first process is the process of document preparation and document selection. Then proceed with the word weighting process using TF-IDF, then determining the genre of comics is done by comparing the similarity value between the text and a node in the resource data. The text obtained will be classified in an existing genre or node, if it has the highest similarity value in one of the nodes in the data resource. It is hoped that the system to be built is in accordance with the expectations of researchers, so that the system to be built can determine the genre of a comic.Keywords: Classification, Comic, Text Mining, Resource Data, TFIDF]]>
Copyrights © 2020
