Analisis Sentimen Terhadap Tweets Samsung Indonesia Menggunakan Metode Support Vector Machine

Triantoro, Aris Rendyansyah (2021) Analisis Sentimen Terhadap Tweets Samsung Indonesia Menggunakan Metode Support Vector Machine. Malaysian Journal of Computing. pp. 1-20. ISSN 2600-8238 (Unpublished)

Text Sentiment Analysis of Samsung Indonesia Tweets Using Support Vector Machine Method.pdf - Published Version Restricted to Repository staff only Download (486kB) | Request a copy

Abstract

Samsung as the world's leading smartphone company is a company that produces
various types of technological devices. Technology as the driving force of human civilization is
very important. However, in the course of time it is necessary to improve and evaluate gradually
in order to satisfy needs properly and avoid undesirable things.
Social media Twitter is an application that allows users to write about various topics
and discuss current issues. Services are available to send tweets or re-tweets messages that
have been shared. With the existence of Twitter this makes it easier for people to have an
opinion. The opinion expressed by the public is a very valuable input and can be an instrument
for evaluating. These opinions can be analyzed so that information can be obtained, but in
practice, processing a text data requires an appropriate method so that the information
generated can help many parties to support a decision or choice.
Sentiment analysis is the classification of text documents into sentiment classes, such
as positive and negative. This study aims to classify the community's tweets against the Samsung
Indonesia company on Twitter social media using the Support Vector Machine method by using
the data source from crawling tweets with samsungidas the reference keyword using the Twitter
API. This research results that the number of tweets with negative sentiment is 13.37%, positive
sentiment is 26.01%, and neutral sentiment is 60.60% tweets and the best model for classifying
tweet data with SVM is to use data sharing by sharing training data by 80% and testing data
by 20% and using value C = 1.

Item Type:	Article
Additional Information:	This open access article is distributed under a Creative Commons Attribution (CC-BY SA) 3.0 license
Uncontrolled Keywords:	classification, sentiment analysis, support vector machine.
Subjects:	T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models.
Divisions:	Faculty of Vocational > 49501-Business Statistics
Depositing User:	Aris Aris Rendyansyah
Date Deposited:	03 Sep 2021 02:15
Last Modified:	03 Sep 2021 02:15
URI:	http://repository.its.ac.id/id/eprint/90797

Actions (login required)

View Item