ANALISIS DAN IMPLEMENTASI SISTEM SENTIMEN TERHADAP ELEKTABILITAS CALON PRESIDEN INDONESIA 2024 MENGGUNAKAN METODE SUPPORT VECTOR MACHINE

Harahap, Jasmine Avrile Kaniasari (2024) ANALISIS DAN IMPLEMENTASI SISTEM SENTIMEN TERHADAP ELEKTABILITAS CALON PRESIDEN INDONESIA 2024 MENGGUNAKAN METODE SUPPORT VECTOR MACHINE. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (COVER) 20083010012_COVER.pdf Download (666kB)
	Text (BAB 1) 20083010012_BAB 1.pdf Download (111kB)
	Text (BAB 2) 20083010012_BAB 2.pdf Restricted to Repository staff only until 24 July 2026. Download (387kB)
	Text (BAB 3) 20083010012_BAB 3.pdf Restricted to Repository staff only until 24 July 2026. Download (303kB)
	Text (BAB 4) 20083010012_BAB 4.pdf Restricted to Repository staff only until 24 July 2026. Download (1MB)
	Text (BAB 5) 20083010012_BAB 5.pdf Download (59kB)
	Text (DAFTAR PUSTAKA) 20083010012_DAFTAR PUSTAKA.pdf Download (163kB)
	Text (LAMPIRAN) 20083010012_LAMPIRAN.pdf Restricted to Repository staff only Download (238kB)

Abstract

Indonesia is a country that implements democracy in choosing presidential candidates through the election process. In responding to presidential candidates, people have their own views about the presidential candidates they support. In this digital era, social media has become a place for people to express their opinions. These opinions can be in the form of positive or negative opinions, public opinion, and hate speech and various other comments that can cause hostility, humiliation, debate and dispute. It is important to consider public opinion, as it can influence people's choices and determine the final results of the 2024 elections. In response to these issues, it is necessary to identify the extent to which public opinion on Indonesian presidential candidates is positive or negative. A system was thus devised to classify sentiments expressed by the public in their opinions, with the objective of categorising public comments on Twitter related to the 2024 election into positive and negative sentiments and implementing them into a web-based system. In this study, the efficacy of data modelling using the Support Vector Machine (SVM) method will be evaluated using a confusion matrix, with the objective of achieving the optimal average accuracy value of 93.78%, precision value of 93.67%, and recall value of 93.78%. The results yielded a precision value of 93.67%, recall value of 93.78%, and an f1-score value of 93.72% with an rbf kernel and a cost parameter value (C) of 10 and a gamma parameter (γ) of 1, with a proportion of 70% for the training data and 30% for the test data.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Saputra, Wahyu Syaifullah Jauharis	NIDN6686111	wahyu.s.j.saputra.if@upnjatim.ac.id
Thesis advisor	Idhom, Mohammad	NIDN6139745	idhom@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Data Science

Depositing User:

Jasmine Avrile Kaniasari Harahap

Date Deposited:

24 Jul 2024 02:09

Last Modified:

24 Jul 2024 02:11

URI:

https://repository.upnjatim.ac.id/id/eprint/27235