PENERAPAN ALGORITMA NAIVE BAYES PADA ANALISA SENTIMEN TWITTER TERHADAP OPINI PUBLIK BADAN PANGAN NASIONAL

PRIMA, ANDHIKA (2024) PENERAPAN ALGORITMA NAIVE BAYES PADA ANALISA SENTIMEN TWITTER TERHADAP OPINI PUBLIK BADAN PANGAN NASIONAL. S1 thesis, Universitas Mercu Buana Jakarta.

	Text (HAL COVER) 01 COVER.pdf Download (443kB)
	Text (ABSTRAK) 02 ABSTRAK.pdf Download (31kB)
	Text (BAB I) 03 BAB 1.pdf Restricted to Registered users only Download (87kB)
	Text (BAB II) 04 BAB 2.pdf Restricted to Registered users only Download (189kB)
	Text (BAB III) 05 BAB 3.pdf Restricted to Registered users only Download (158kB)
	Text (BAB IV) 06 BAB 4.pdf Restricted to Registered users only Download (452kB)
	Text (BAB V) 07 BAB 5.pdf Restricted to Registered users only Download (29kB)
	Text (DAFTAR PUSTAKA) 08 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (92kB)
	Text (LAMPIRAN) 09 LAMPIRAN.pdf Restricted to Registered users only Download (1MB)

Abstract

This research focuses on an application the Naïve Bayes algorithm to analyze Twitter sentiment towards the National Food Agency (NFA). In the digital era, social media, especially Twitter, has become the main channel for people to express opinions related to government agencies. The Naïve Bayes algorithm is used to classify sentiment into positive or negative. With steps involving data crawling, preprocessing, automatic data labeling using InSet Lexicon, word weighting with TF-IDF, data splitting, and classification with the Naïve Bayes algorithm with 4 tests of split data 90:10, 80:20, 70:30 and 60:40. The classification performance results show the best results in the first test with a 90:10 split data distribution of 80.47% accuracy, 81.60% precision, 71.78% recall, and 76.67% F1 score. The Naïve Bayes algorithm classified a total of 1,093 data. From these results, 453 positive sentiments (41.4%) while 640 negative sentiments (58.6%) based on 20% testing data. Keywords: Classification, Naïve Bayes, Sentiment Analysis, Twitter, National Food Agency, Penelitian ini fokus pada penerapan algoritma Naïve Bayes untuk menganalisis sentimen Twitter terhadap Badan Pangan Nasional (BAPANAS). Dalam era digital, media sosial, khususnya Twitter, menjadi saluran utama masyarakat untuk menyampaikan opini terkait instansi pemerintah. Algoritma Naïve Bayes digunakan untuk mengklasifikasikan sentimen menjadi positif atau negatif. Dengan langkah-langkah yang melibatkan crawling data, preprocessing, pelabelan data otomatis menggunakan InSet Lexicon, pembobotan kata dengan TF-IDF, data splitting, dan klasifikasi dengan algoritma Naïve Bayes dengan 4 Kali Pengujian dari data split 90:10, 80:20, 70:30 dan 60:40. Hasil peforma klasifikasi menunjukan hasil terbaik pada pengujian pertama dengan pembagian data split 90:10 sebesar accuracy 80.47%, precision 81.60%, recall 71.78% , dan F1 score 76.67%. Algoritma Naïve Bayes mengklasifikasikan sebanyak 1.093 data. Dari hasil tersebut, 453 sentimen positif (41.4%) sementara 640 sentimen negatif (58.6%) berdasarkan data testing sebanyak 20%. Kata Kunci: Klasifikasi, Naïve Bayes, Analisa Sentimen, Twitter, Badan Pangan Nasional,

Actions (login required)

View Item