Comparison of Support Vector Machines and K-Nearest Neighbor Algorithm Analysis  of Spam Comments on Youtube Covid Omicron

Sudianto Sudianto; Juan Arton Arton Masheli; Nursatio Nugroho; Rafi Wika Ananda Rumpoko; Zarkasih Akhmad

doi:10.15408/jti.v15i2.24996

Authors

Sudianto Sudianto Informatics Engineering, Telkom Institute of Technology Purwokerto https://orcid.org/0000-0001-8610-0587
Juan Arton Arton Masheli Informatics Engineering, Telkom Institute of Technology Purwokerto
Nursatio Nugroho Informatics Engineering, Telkom Institute of Technology Purwokerto
Rafi Wika Ananda Rumpoko Informatics Engineering, Telkom Institute of Technology Purwokerto
Zarkasih Akhmad Informatics Engineering, Telkom Institute of Technology Purwokerto

DOI:

https://doi.org/10.15408/jti.v15i2.24996

Keywords:

Comment, Covid-19, KNN, spam, SVM, YouTube

Abstract

Every time a new variant of Coronavirus (Covid-19) appears, the
media or news platforms review it to find out whether the new variant
is more dangerous or contagious than before. One of the media or
platforms that is fast in presenting news in videos is YouTube.
YouTube is a social media that can upload videos, watch videos, and
comment on the video. The comment field on YouTube videos cannot
be separated from spam comments that annoy other users who want to
follow or participate in the comment column. Indication of spam
comments is still done by observing one by one; this is very inefficient
and time-consuming. This study aims to create a model that can
classify spam on YouTube comments. The classification method uses the SVM (Support Vector Machines) algorithm and the KNN (K-Nearest Neighbor) algorithm to identify spam comments or not with comment data taken from Omicron's Covid-19 news video on national news channels. The classification results show that the SVM method is superior inaccuracy with the Linear SVC algorithm of 75.12%, SVC of 76.11%, and Nu-SVC of 77.11%. While the KNN algorithm with k=2 is 65.67%, k=4 is 64.51%, k=6 is 62.35%.