APPLICATION OF SUPPORT VECTOR MACHINE AND PARTICLE SWARM OPTIMIZATION ALGORITHMS IN SENTIMENT ANALYSIS OF JOBSTREET APPLICATION USAGE

Zahroh, Fatimatuz (2026) APPLICATION OF SUPPORT VECTOR MACHINE AND PARTICLE SWARM OPTIMIZATION ALGORITHMS IN SENTIMENT ANALYSIS OF JOBSTREET APPLICATION USAGE. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 19081010021_cover.pdf Download (639kB)
	Text (BAB 1) 19081010021_bab1.pdf Download (210kB)
	Text (BAB 2) 19081010021_bab2.pdf Restricted to Repository staff only until 23 July 2029. Download (296kB)
	Text (BAB 3) 19081010021_bab3.pdf Restricted to Repository staff only until 23 July 2029. Download (349kB)
	Text (BAB 4) 19081010021_bab4.pdf Restricted to Repository staff only until 23 July 2029. Download (1MB)
	Text (BAB 5) 19081010021_bab5.pdf Download (186kB)
	Text (Daftar Pustaka) 19081010021_daftarpustaka.pdf Download (160kB)

Abstract

Jobstreet app is a job vacancy app with over 10 million downloads that offers various positions in various fields such as accounting, human resources, marketing, communications, services, and many more. In this digital era, the jobstreet app has become a popular choice for job searching. This Android app can be accessed anywhere, anytime, and provides relevant information related to the field you're looking for. The app has a rating of 1 to 5 on the google playstore. However, some users give ratings that don't align with the reviews. However, the jobstreet app also contains negative reviews or sentiment regarding the ratings received from users. And of course, negative reviews can be a factor in users decision to download the jobstreet app. Therefore, the author attempted to conduct research related to sentiment analysis on jobstreet app usage. Sentiment analysis focuses on analyzing and understanding emotions from text reviews that aim to predict, analyze public sentiment, and automatically describe netizens' feelings in a case. The purpose of this study is to determine the positive and negative sentiments on the jobstreet application using the Support Vector Machine algorithm and the Particle Swarm Optimization algorithm in order to determine the accuracy of the algorithm. The Support Vector Machine model without optimization produced an accuracy of 79.42%, a precision of 78.86%, a recall of 74.03%, and an f1-score of 76.34%. After optimization using Particle Swarm Optimization, the model's performance improved. The best model was obtained in Scenario 6 with 400 iterations, resulting in an accuracy of 82.52%, a precision of 85.79%, a recall of 73.16%, and an f1-score of 78.97%. These results indicate that the application of Particle Swarm Optimization can improve accuracy by 3.10 percentage points, precision by 6.99 percentage points, and f1-score by 2.63 percentage points compared to the SVM model without optimization.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Anggraeny, Fetty Tri	NIDN0711028201	fettyanggraeny.if@upnjatim.ac.id
Thesis advisor	Al Haromainy, Muhammad Muharrom	NIDN0701069503	muhammad.muharrom.if@upnjatim.ac.id

Subjects:

Q Science > Q Science (General)
Q Science > QA Mathematics
Q Science > QA Mathematics > QA76.6 Computer Programming
T Technology > T Technology (General)
T Technology > TN Mining engineering. Metallurgy

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Fatimatuz Zahroh Ima

Date Deposited:

23 Jul 2026 01:42

Last Modified:

23 Jul 2026 02:31

URI:

https://repository.upnjatim.ac.id/id/eprint/57828