Analisis Sentimen Persepsi Hidup Sehat Masyarakat Indonesia Berdasarkan Komentar Instagram Menggunakan Algoritma BERT dan LSTM

Putri, Audiva Tartila Daning (2024) Analisis Sentimen Persepsi Hidup Sehat Masyarakat Indonesia Berdasarkan Komentar Instagram Menggunakan Algoritma BERT dan LSTM. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 20081010172-cover.pdf Download (671kB)
	Text (BAB 1) 20081010172-bab1.pdf Download (91kB)
	Text (BAB 2) 20081010172-bab2.pdf Restricted to Repository staff only until 20 September 2026. Download (976kB) \| Request a copy
	Text (BAB 3) 20081010172-bab3.pdf Restricted to Repository staff only until 20 September 2026. Download (1MB) \| Request a copy
	Text (BAB 4) 20081010172-bab4.pdf Restricted to Repository staff only until 20 September 2026. Download (3MB) \| Request a copy
	Text (BAB 5) 20081010172-bab5.pdf Download (9kB)
	Text (Daftar Pustaka) 20081010172-daftarpustaka.pdf Download (155kB)
	Text (Lampiran) 20081010172-lampiran.pdf Restricted to Repository staff only Download (137kB) \| Request a copy

Abstract

Perception of a healthy lifestyle is crucial for both physical and mental well-being, especially with the rising cases of Non-Communicable Diseases (NCDs) in Indonesia caused by poor dietary habits and lack of physical activity. Social media platforms like Instagram have become essential tools for raising public awareness about healthy lifestyles through educational content. This study aims to analyze the sentiment of the Indonesian public towards healthy living using comment data from Instagram posts by the Ministry of Health of the Republic of Indonesia (@ayosehat.kemkes). The methodology includes data collection, preprocessing, labeling, and splitting the data into training, validation, and test sets. A combined BERT-LSTM model is applied to classify sentiments into positive, negative, and neutral, with BERT as the feature extraction tool and LSTM for classification. The best model in the first testing scenario with an 80:10:10 data split achieved an accuracy of 89.20%, precision of 89.49%, recall of 89.20%, and an F1-score of 88.74%. The analysis results show that neutral sentiment dominates at 50.4%, followed by positive sentiment at 43%, and negative sentiment at 6.6%, indicating that the public tends to have a positive perception of healthy lifestyles, with a 36.4% difference between positive and negative sentiment. Visualization and word association analysis reveal that positive sentiment includes appreciation and commitment towards healthy living.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Via, Yisti Vita	NIDN0025048602	yistivia.if@upnjatim.ac.id
Thesis advisor	Haromainy, Muhammad Muharrom Al	NIDN0701069503	muhammad.muharrom.if@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics
Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Audiva Tartila Daning Putri

Date Deposited:

20 Sep 2024 03:59

Last Modified:

20 Sep 2024 03:59

URI:

https://repository.upnjatim.ac.id/id/eprint/29665