Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 3 No 1 (2019): Januari 2019

Klasifikasi Film Berdasarkan Sinopsis dengan Menggunakan Improved K-Nearest Neighbor (K-NN)

Nurul Muslimah (Fakultas Ilmu Komputer, Universitas Brawijaya)
Indriati Indriati (Fakultas Ilmu Komputer, Universitas Brawijaya)
Randy Cahya Wihandika (Fakultas Ilmu Komputer, Universitas Brawijaya)



Article Info

Publish Date
24 Aug 2018

Abstract

Movie is audio visual communication media, which imply the message the movie creator wants to convey. Movie has several genres namely romantic, horror, thriller, comedy, fantasy and so on. Not a few movie connoisseurs are still confused about the differences in these genres. This resulted in many movie lovers who were difficult to distinguish the genre of movie so that the message in the movie could not be fully conveyed to the audience of the movie. Therefore, the classification of movies based on the synopsis of the movie can be one of the solutions to the problem. Classification in the movie synopsis will help in grouping movies with the appropriate genre. The genre genre classification process based on the synopsis begins with preprocessing, then weighting the term to classification with the Improved K-NN method. Based on the implementation and testing conducted in the movie classification research based on the synopsis using Improved K-NN which uses 250 documents as training data and 50 documents as the test data the best results are precision = 1, recall = 0.88, f-measure = 0.936170213, and an accuracy rate of 88%. As well as comparison with K-NN, it was proven that classification using the Improved K-NN method was better than the K-NN method.

Copyrights © 2019






Journal Info

Abbrev

j-ptiik

Publisher

Subject

Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Description

Jurnal Pengembangan Teknlogi Informasi dan Ilmu Komputer (J-PTIIK) Universitas Brawijaya merupakan jurnal keilmuan dibidang komputer yang memuat tulisan ilmiah hasil dari penelitian mahasiswa-mahasiswa Fakultas Ilmu Komputer Universitas Brawijaya. Jurnal ini diharapkan dapat mengembangkan penelitian ...