ANALISIS SENTIMEN MENGENAI PELAYANAN INTERNET SERVICE PROVIDER DI INDONESIA PADA MEDIA SOSIAL DENGAN MEMBANDINGKAN HASIL KINERJA ALGORITMA KLASIFIKASI NAÏVE BAYES DAN SUPPORT VECTOR MACHINE

AFRIZAL, MOHAMAD (2022) ANALISIS SENTIMEN MENGENAI PELAYANAN INTERNET SERVICE PROVIDER DI INDONESIA PADA MEDIA SOSIAL DENGAN MEMBANDINGKAN HASIL KINERJA ALGORITMA KLASIFIKASI NAÏVE BAYES DAN SUPPORT VECTOR MACHINE. S1 thesis, Universitas Mercu Buana.

Preview	Text (HAL COVER) 01 Cover.pdf Download (610kB) | Preview
Preview	Text (ABSTRAK) 02 Abstrak.pdf Download (22kB) | Preview
	Text (BAB 1) 03 Bab 1.pdf Restricted to Registered users only Download (110kB)
	Text (BAB 2) 04 Bab 2.pdf Restricted to Registered users only Download (88kB)
	Text (BAB 3) 05 Bab 3.pdf Restricted to Registered users only Download (108kB)
	Text (BAB 4) 06 Bab 4.pdf Restricted to Registered users only Download (96kB)
	Text (BAB 5) 07 Bab 5.pdf Restricted to Registered users only Download (143kB)
	Text (DAFTAR PUSTAKA) 08 Daftar Pustaka.pdf Restricted to Registered users only Download (83kB)
	Text (LAMPIRAN) 09 Lampiran.pdf Restricted to Registered users only Download (165kB)

Abstract

In suppressing the spread of COVID-19, the Indonesian government has established a PSBB policy or Large-Scale Social Restrictions. Many aspects and areas affected by the policy include education and offices. APJII or the Association of Indonesian Internet Service Providers explained that there was an increase in the number of internet users in Indonesia from last year's penetration of 64% to 73.7%. One of the reasons for this increase was the COVID-19 pandemic. On the Twitter platform, they often find various kinds of public responses that they give about the services of the Internet Service Provider, both negative and positive. In this study, sentiment analysis was conducted to determine public opinion on the performance of Internet Service Providers. The method used is the Naïve Bayes classification algorithm and Support Vector Machine assisted by RapidMiner and Python tools. The experimental results show that the Support Vector Machine algorithm provides the highest accuracy values of 93% and 92% for the two data tested, both Indihome and Firstmedia. Key words: Internet, Naïve Bayes, Support Vector Machine, Sentiment, Algorithm Dalam menekan penyebaran COVID-19 pemerintah Indonesia menetapkan kebijakan PSBB atau Pembatasan Sosial Berskala Besar. Banyak aspek dan bidang yang terdampak dari kebijakan tersebut diantaranya adalah pendidikan dan perkantoran. APJII atau Asosiasi Penyelenggara Jasa Internet Indonesia menjelaskan bahwa terjadi kenaikan jumlah pengguna internet di Indonesia dari tahun yang lalu penetrasi sebesar 64% menjadi 73,7%. Kenaikan tersebut salah satunya disebabkan karena Pandemi COVID-19. Pada platform Twitter, sering dijumpai berbagai macam tanggapan masyarakat yang mereka lontarkan mengenai pelayanan dari Internet Service Provider tersebut baik negatif maupun positif. Pada penelitian ini dilakukan analisa sentimen untuk mengetahui pendapat masyarakat terhadap kinerja Internet Service Provider. Metode yang digunakan adalah algoritma klasifikasi Naïve Bayes dan Support Vector Machine dengan dibantu oleh tools RapidMiner dan Python. Hasil eksperimen menunjukkan bahwa algoritma Support Vector Machine memberikan nilai akurasi paling tinggi yaitu 93% dan 92% untuk dua data yang diuji baik Indihome maupun Firstmedia. Kata kunci: Internet, Naïve Bayes, Support Vector Machine, Sentimen, Algoritma

Actions (login required)

View Item