Analisis Sentimen Pengguna Media Sosial X Terhadap Penggunaan Kecerdasan Artifisial Dalam Desain Grafis Menggunakan Metode Naïve Bayes

Annisa, Nur (2025) Analisis Sentimen Pengguna Media Sosial X Terhadap Penggunaan Kecerdasan Artifisial Dalam Desain Grafis Menggunakan Metode Naïve Bayes. S1 Sistem Informasi thesis, STMIK Widya Cipta Dharma.

	Text 2141050-S1-Jurnal.pdf Restricted to Repository staff only Download (249kB) | Request a copy
	Text 2141050-S1-Sistem Informasi.pdf Restricted to Repository staff only Download (3MB) | Request a copy

Abstract

Penggunaan kecerdasan artifisial (AI) dalam berbagai bidang, termasuk desain grafis, telah menimbulkan beragam respons masyarakat, khususnya di media sosial. Fenomena ini menarik untuk dianalisis guna mengetahui pandangan publik terhadap penggunaan AI dalam industri kreatif. Penelitian ini bertujuan melakukan analisis sentimen terhadap komentar pengguna media sosial X (Twitter) terkait penggunaan kecerdasan artifisial dalam desain grafis. Data dikumpulkan menggunakan teknik scraping dengan Twitter Auth Token untuk memperoleh komentar yang relevan. Proses pengolahan data mengikuti tahapan Knowledge Discovery in Database (KDD) yang mencakup preprocessing, ekstraksi fitur dengan TF-IDF, dan klasifikasi menggunakan algoritma Naïve Bayes. Sentimen diklasifikasikan ke dalam tiga kelas: positif, negatif, dan netral. Hasil klasifikasi menunjukkan bahwa sentimen negatif paling dominan, diikuti oleh sentimen positif dan netral. Model masih mengalami kesulitan dalam mengenali sentimen netral, sebagaimana terlihat dari confusion matrix dan evaluasi performa. Pelabelan menggunakan kamus lexicon Inset menghasilkan 9 komentar negatif (52,8%), 78 positif (43,3%), dan 7 netral (3,9%). Sementara itu, hasil pelabelan manual menunjukkan 99 komentar negatif (55,0%), 28 positif (15,6%), dan 53 netral (29,4%). Model yang dikembangkan mencapai akurasi sebesar 75%. Temuan ini diharapkan menjadi referensi dalam pengembangan sistem analisis sentimen, khususnya terkait respons masyarakat terhadap tren penggunaan AI dalam industri kreatif. ============================================================ The use of artificial intelligence (AI) in various fields, including graphic design, has sparked diverse responses from the public, particularly on social media. This phenomenon is worth analyzing to understand public perceptions of AI usage in the creative industry. This study aims to conduct sentiment analysis on user comments from the social media platform X (formerly Twitter) regarding the use of artificial intelligence in graphic design. Data was collected using scraping techniques with a Twitter Auth Token to obtain relevant comments. The data processing followed the stages of Knowledge Discovery in Database (KDD), including preprocessing, feature extraction using TF-IDF, and classification using the Naïve Bayes algorithm. Sentiment labels were divided into three categories: positive, negative, and neutral. The classification results showed that negative sentiment was the most dominant, followed by positive and neutral sentiments. The model struggled to accurately detect neutral sentiments, as indicated by the confusion matrix and performance evaluation. Labeling using the Inset lexicon dictionary resulted in 95 negative comments (52.8%), 78 positive (43.3%), and 7 neutral (3.9%). Meanwhile, manual labeling yielded 99 negative comments (55.0%), 28 positive (15.6%), and 53 neutral (29.4%). The developed model achieved an accuracy of 75%. These findings are expected to serve as a reference for developing sentiment analysis systems, particularly in understanding public responses to the growing use of AI in creative industries.

Item Type:	Thesis (S1 Sistem Informasi)
Additional Information:	Pembimbing 1 : Ita Arfyanti, S.Kom., M.M. Pembimbing 2 : Yunita, S.E., M.M
Uncontrolled Keywords:	Analisis Sentimen, Artificial Intelligence, Lexicon InSet, Desain Grafis, Knowledge Discovery in Database (KDD)
Subjects:	Q Science > QA Mathematics > QA76 Computer software
Divisions:	Sistem Informasi
Depositing User:	Ms Nur Annisa
Date Deposited:	12 Aug 2025 01:03
Last Modified:	12 Aug 2025 01:03
URI:	http://repository.wicida.ac.id/id/eprint/6247

Actions (login required)

View Item