Penggunaan Ekstraksi Fitur Tf-Idf Dan Fasttext Pada Klasifikasi Sentimen Ulasan Linkedin Dengan Metode Logistic Regression

Wardana, Nabila Sya'bani (2024) Penggunaan Ekstraksi Fitur Tf-Idf Dan Fasttext Pada Klasifikasi Sentimen Ulasan Linkedin Dengan Metode Logistic Regression. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 20081010114_cover.pdf Download (1MB)
	Text (Bab 1) 20081010114_Bab 1.pdf Download (336kB)
	Text (Bab 2) 20081010114_Bab 2.pdf Restricted to Repository staff only until 4 June 2026. Download (1MB) \| Request a copy
	Text (Bab 3) 20081010114_Bab 3.pdf Restricted to Repository staff only until 4 June 2026. Download (905kB) \| Request a copy
	Text (Bab 4) 20081010114_Bab 4.pdf Restricted to Repository staff only until 4 June 2026. Download (1MB) \| Request a copy
	Text (Bab 5) 20081010114_Bab 5.pdf Download (206kB)
	Text 20081010114_Daftar Pustaka.pdf Download (428kB)

Abstract

Professional networking platforms such as LinkedIn have become important social media for individuals to interact, share information and build professional networks. While LinkedIn has provided significant benefits to its users, there are still some limitations. Therefore, it is important to understand user responses to this application. Previous research has shown that sentiment analysis can be an effective tool in understanding user feedback and responses. This research will analyze the sentiment of LinkedIn app user reviews using Logistic Regression method, taking into account the use of TF IDF Feature Extraction and FastText Feature Expansion. Logistic Regression was chosen because it is effective in handling binary sentiment classification problems and has a relatively high training speed. Based on the evaluation metrics, it can be observed that the sentiment classification of LinkedIn user reviews with the Logistic Regression algorithm based on TF-IDF and FastText approaches using the most optimal test result parameters achieved an accuracy of 95.83%, precision of 96.54%, recall of 96.38%, and F1-Score of 93.01%, thus providing insights for LinkedIn developers to improve service quality.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Aditiawan, Firza Prima	0023058605	firzaprima.if@upnjatim.ac.id
Thesis advisor	Sari, Anggraini Puspita	0716088605	anggraini.puspita.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Nabila Sya'bani Wardana

Date Deposited:

04 Jun 2024 08:39

Last Modified:

04 Jun 2024 08:39

URI:

https://repository.upnjatim.ac.id/id/eprint/23812