ANALISIS SENTIMEN BERBASIS ASPEK TERHADAP FASILITAS SEA GAMES 2023 MELALUI MEDIA TWITTER MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE

AZKA LUTHFAN RUDIANA, . (2024) ANALISIS SENTIMEN BERBASIS ASPEK TERHADAP FASILITAS SEA GAMES 2023 MELALUI MEDIA TWITTER MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE. Sarjana thesis, UNIVERSITAS NEGERI JAKARTA.

	Text Cover.pdf Download (2MB)
	Text BAB 1.pdf Download (583kB)
	Text BAB 2.pdf Restricted to Registered users only Download (617kB) | Request a copy
	Text BAB 3.pdf Restricted to Registered users only Download (633kB) | Request a copy
	Text BAB 4.pdf Restricted to Registered users only Download (628kB) | Request a copy
	Text BAB 5.pdf Restricted to Registered users only Download (365kB) | Request a copy
	Text DAFTAR PUSTAKA.pdf Download (305kB)
	Text LAMPIRAN.pdf Restricted to Registered users only Download (983kB) | Request a copy

Abstract

ABSTRAK Southeast Asian Games (SEA Games) merupakan festival multi-olahraga yang diadakan setiap dua tahun sekali di Asia Tenggara, dengan SEA Games ke-32 tahun 2023 diselenggarakan di Kamboja. Penyelenggaraan acara ini menjadi sorotan publik khususnya pada media sosial Twitter terkait kesiapan fasilitasnya, seperti lampu podium yang mati dan kamar atlet yang bocor, yang menimbulkan beragam tanggapan dari masyarakat. Analisis sentimen berbasis aspek terhadap fasilitas SEA Games 2023 ini menggunakan algoritma Support Vector Machine (SVM) untuk mengidentifikasi persepsi publik mengenai sentimen positif dan negatif serta aspek kebersihan, kelengkapan, dan kenyamanan dari fasilitas yang diberikan. Data diambil dari tweet di Twitter, menghasilkan 555 data bersih. Model SVM diuji dengan K-Fold Cross Validation (K=10), menghasilkan akurasi 93,16%, presisi 90,94%, recall 83,96%, dan F1-score 85,58%. Performa model terbaik per fold terjadi pada fold ke-5 dengan akurasi 98,21%, recall 99%, dan F1-score 95,64%. Nilai presisi terbaik terjadi pada fold ke-6 sebesar 98,03%. Untuk aspek kenyamanan, akurasi mencapai 95,15%, presisi 90%, dan F1-score 80,81%, sedangkan nilai recall terbaik diperoleh dari aspek kebersihan sebesar 85%. ***** ABSTRACT The Southeast Asian Games (SEA Games) is a biennial multi-sport event held in Southeast Asia, with the 32nd SEA Games in 2023 hosted by Cambodia. The event's organization drew public scrutiny, particularly on social media platform Twitter, regarding the preparedness of its facilities, such as malfunctioning podium lights and leaking athlete accommodations, eliciting various responses from the public. This aspect-based sentiment analysis of SEA Games 2023 facilities employs the Support Vector Machine (SVM) algorithm to identify public perceptions of positive and negative sentiments and aspects of cleanliness, completeness, and comfort of the provided facilities. The data was collected from tweets on Twitter, resulting in a clean dataset of 555 entries. The SVM model was tested using K-Fold Cross Validation (K=10), yielding an accuracy of 93.16%, a precision of 90.94%, a recall of 83.96%, and an F1-score of 85.58%. The best model performance per fold occurred in the 5th fold, with an accuracy of 98.21%, a recall of 99%, and an F1-score of 95.64%. The highest precision was achieved in the 6th fold, at 98.03%. For the comfort aspect, the accuracy reached 95.15%, precision was 90%, and F1-score was 80.81%, while the best recall value was obtained from the cleanliness aspect, at 85%.

Item Type:	Thesis (Sarjana)
Additional Information:	1). Dr. Widodo, S.Kom., M.Kom. ; 2). Ressy Dwitias Sari, S.T, M.T.I.
Subjects:	Teknologi dan Ilmu Terapan > Teknik Komputer
Divisions:	FT > S1 Pendidikan Teknik Informatika Komputer
Depositing User:	Users 23662 not found.
Date Deposited:	25 Jul 2024 01:53
Last Modified:	25 Jul 2024 01:53
URI:	http://repository.unj.ac.id/id/eprint/46468

Actions (login required)

View Item