ASENTIMENT ANALYSIS OF BANK SYARIAH INDONESIA ON TWITTER SOCIAL MEDIA USING THE SUPPORT VECTOR MACHINE CLASSIFICATION METHOD

HASTU, MAHATA (2023) ASENTIMENT ANALYSIS OF BANK SYARIAH INDONESIA ON TWITTER SOCIAL MEDIA USING THE SUPPORT VECTOR MACHINE CLASSIFICATION METHOD. ["eprint_fieldopt_thesis_type_tugasakhir" not defined] thesis, University of Technology Yogyakarta.

[img] Text
5160411067_Mahata hastu_ABSTRAK.pdf
Download (16kB)

Abstract

ABSTract In 2023, 60.4% of the population in Indonesia stated that their reason for using the internet is for social media purposes. One of the social media platforms with an active user base of 556 million users is Twitter. Given the influx of information published through Twitter, it is possible that this information contains user opinions about certain objects or events. These objects can include incidents within society, such as a product or service. This has led companies to utilize Twitter as a means to disseminate information. However, at the beginning of 2023, Bank Syariah Indonesia experienced a data breach incident affecting its customers. Various comments were made regarding this incident, including on social media platform Twitter. Therefore, the author developed a sentiment analysis system to predict whether user comments on Twitter are positive or negative. The system utilizes the Support Vector Machine (SVM) algorithm for sentiment classification of user comments on Twitter. To present the system in a user-friendly manner, a web-based approach was employed. The system was designed using Node.js for data crawling, Visual Studio Code (VSC) as the source code development environment, Streamlit as the framework for creating the web interface, Python as a programming language, GitHub as the data repository, and Heroku as the hosting platform to connect the system to the internet. This system allows for the prediction of sentiment in user comments on Twitter. Keywords: Sentiment Analysis System, Support Vector Machine (SVM), Python.

Item Type: Thesis (["eprint_fieldopt_thesis_type_tugasakhir" not defined])
Subjects: T Technology > T Technology (General)
Divisions: Fakultas Sains Dan Teknologi > S1 Informatika
Depositing User: Kaprodi S1 Informatika UTY
Date Deposited: 09 Aug 2023 03:59
Last Modified: 09 Aug 2023 03:59
URI: http://eprints.uty.ac.id/id/eprint/13452

Actions (login required)

View Item View Item
UTY Open Access is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.