ANALISIS SENTIMEN INSTAGRAM DAN FACEBOOK TERHADAP KONDISI LALU LINTAS DI KOTA PALEMBANG MENGGUNAKAN LONG SHORT TERM MEMORY

IQBAL, M and Sukemi, Sukemi and Oklilas, Ahmad Fali (2025) ANALISIS SENTIMEN INSTAGRAM DAN FACEBOOK TERHADAP KONDISI LALU LINTAS DI KOTA PALEMBANG MENGGUNAKAN LONG SHORT TERM MEMORY. Undergraduate thesis, Sriwijaya University.

	Image RAMA_56201_09011282025089_cover.pdf - Cover Image Available under License Creative Commons Public Domain Dedication. Download (69kB)
	Text RAMA_56201_09011282025089.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9MB) | Request a copy
	Text RAMA_56201_09011282025089_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_56201_09011282025089_0003126604_0015107201_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (885kB)
	Text RAMA_56201_09011282025089_0003126604_0015107201_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (337kB) | Request a copy
	Text RAMA_56201_09011282025089_0003126604_0015107201_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (238kB) | Request a copy
	Text RAMA_56201_09011282025089_0003126604_0015107201_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_56201_09011282025089_0003126604_0015107201_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (194kB) | Request a copy
	Text RAMA_56201_09011282025089_0003126604_0015107201_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (199kB) | Request a copy
	Text RAMA_56201_09011282025089_0003126604_0015107201_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy

Abstract

Penelitian ini bertujuan membangun model klasifikasi kondisi lalu lintas menggunakan data dari sosial media (Instagram dan Facebook) serta data ETLE dengan arsitektur Long Short-Term Memory (LSTM). Dari total 1.251 data sosial media yang dikumpulkan, sebanyak 932 data dipilih berdasarkan kemunculan kata kunci “macet”, “sedang”, dan “lancar”. Data ini kemudian dibagi menjadi data latih (743) dan data uji (150), serta diproses melalui tahapan preprocessing seperti cleaning, case folding, stemming, tokenization, stopword removal, dan normalisasi. Hasil klasifikasi menunjukkan akurasi tinggi pada data sosial media (96%), namun akurasi kategori “lancar” sangat rendah (18,75%) yang menunjukkan bias terhadap kategori “macet”. Sementara itu, hasil klasifikasi pada data ETLE menunjukkan akurasi stabil sebesar 93% tanpa indikasi bias yang signifikan. Evaluasi melalui pencocokan antar dua sumber data menunjukkan tingkat kesesuaian sebesar 82,25%, mencerminkan performa model yang cukup baik dalam kondisi nyata. Penelitian ini menyimpulkan bahwa model cukup andal, namun perlu perbaikan untuk meningkatkan sensitivitas terhadap kategori minoritas.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	LSTM, Sentiment Analysis, Social Media, Natural Language Processing, Text Processing.
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	M.Iqbal M.Iqbal
Date Deposited:	11 Sep 2025 02:09
Last Modified:	11 Sep 2025 02:09
URI:	http://repository.unsri.ac.id/id/eprint/183802

Actions (login required)

View Item