KOMPARASI NAÏVE BAYES DENGAN SVM PADA ANALISIS SENTIMEN PENGGUNA INDIHOMECARE

PUTRI, FESA RIZKY (2023) KOMPARASI NAÏVE BAYES DENGAN SVM PADA ANALISIS SENTIMEN PENGGUNA INDIHOMECARE. S1 thesis, Universitas Mercu Buana Bekasi.

Preview	Text 41519210075 - FESA RIZKY PUTRI - 01 Cover.pdf Download (292kB) | Preview
Preview	Text 41519210075 - FESA RIZKY PUTRI - 02 Abstrak.pdf Download (75kB) | Preview
	Text 41519210075 - FESA RIZKY PUTRI - 03 BAB 1.pdf Restricted to Registered users only Download (108kB)
	Text 41519210075 - FESA RIZKY PUTRI - 04 BAB 2.pdf Restricted to Registered users only Download (182kB)
	Text 41519210075 - FESA RIZKY PUTRI - 05 BAB 3.pdf Restricted to Registered users only Download (144kB)
	Text 41519210075 - FESA RIZKY PUTRI - 06 BAB 4.pdf Restricted to Registered users only Download (353kB)
	Text 41519210075 - FESA RIZKY PUTRI - 07 BAB 5.pdf Restricted to Registered users only Download (69kB)
	Text 41519210075 - FESA RIZKY PUTRI - 08 Daftar Pustaka.pdf Restricted to Registered users only Download (136kB)
	Text 41519210075 - FESA RIZKY PUTRI - 09 Lampiran.pdf Restricted to Registered users only Download (1MB)

Abstract

Analisis sentimen dilakukan untuk memberikan suatu penilaian terhadap opini pengguna internet pada media sosial. Salah satu media sosial yang sering mendapatkan sentimen yaitu twitter. Opini yang dikemukakan di akun twitter @Indihomecare memiliki sentimen positif dan negatif. Tujuan menganalisis terhadap pengguna layanan Internet Indihome pada Twitter menggunakan Naïve Bayes Classifier dan Support Vector Machine. Berdasarkan hasil pengujian model klasifikasi Naïve Bayes Classifier akurasinya mencapai 83,70% dan klasifikasi Support Vector Machine akurasinya mencapai 93,80%. Hasil analisis sentimen menunjukkan bahwa algoritma yang berbeda pada proses klasifikasi dapat menghasilkan prediksi yang juga berbeda. Dari hasil perbandingan kedua metode tersebut menunjukkan metode Support Vector Machine lebih baik dari pada Naïve Bayes Classifier. Kata Kunci: Analisis Sentimen, Nive Bayes, Support Vector Machine Sentiment analysis is done to provide an assessment of internet users' opinions on social media. One of the social media that often gets sentiment is twitter. Opinions expressed on the @Indihomecare twitter account have positive and negative sentiments. The purpose of this research is to analyze Indihome Internet service users on Twitter using Naïve Bayes Classifier and Support Vector Machine. Based on the test results of the Naïve Bayes Classifier classification model, the accuracy reached 83.70% and the Support Vector Machine classification accuracy reached 93.80%. The sentiment analysis results show that different algorithms in the classification process can produce different predictions. From the comparison of the two methods, it shows that the Support Vector Machine method is better than the Naïve Bayes Classifier. Keywords: Sentiment Analysis, Nive Bayes, Support Vector Machine

Actions (login required)

View Item