Please use this identifier to cite or link to this item: http://repository.ipb.ac.id/handle/123456789/109508
Title: Analisis Sentimen Pengguna Twitter Terhadap Vaksinasi Covid-19 Di Indonesia Menggunakan Algoritme Support Vector Machine
Other Titles: Sentiment Analysis Of Twitter Users On COVID-19 Vaccination In Indonesia Using Support Vector Machine Algorithm
Authors: Herdiyeni, Yeni
Hardhienata, Medria Kusuma Dewi
Chairunnisa, Qarry Atul
Issue Date: 1-Oct-2021
Publisher: IPB University
Abstract: Kebijakan vaksinasi COVID-19 di Indonesia menimbulkan pro dan kontra. Pemerintah harus mengevaluasi alasan masyarakat yang kontra terhadap kebijakan tersebut, agar program vaksinasi dapat berjalan dengan lancar. Analisis sentimen sebagai cara untuk melihat polaritas opini, memungkinkan untuk mengklasifikasi tanggapan positif, negatif maupun netral di Twitter terkait kebijakan vaksinasi tersebut. Penelitian ini bertujuan untuk mengetahui tanggapan masyarakat terhadap vaksinasi COVID-19 dengan melihat distribusi kata dan membuat model klasifikasi Support Vector Machine (SVM). Analisis sentimen terdiri dari beberapa tahapan yaitu pengumpulan data, praproses data, pembobotan data, analisis data, pembagian data, pemodelan klasifikasi, hyperparameter tuning dan evaluasi model. Model yang dihasilkan menunjukkan performa yang cukup optimal dalam mengklasifikasi sentimen dengan akurasi, presisi, recall dan f1-score sebesar 90%. Hasil analisis yang diperoleh ialah berupa gagasan, keluhan dan saran terhadap vaksinasi COVID-19.
The COVID-19 vaccination policy in Indonesia turns out to be both pros and cons. The government has to evaluate the underlying reason of why some people's are against the policy, so that the vaccination program can run smoothly. Sentiment analysis as a way to see the polarity of opinion, makes it possible to classify positive, negative or neutral responses on Twitter regarding the vaccination policy. This study aims to determine the public's response to COVID-19 vaccination by examining word distribution and creating an Support Vector Machine (SVM) classification model. Sentiment analysis consists of several stages, namely data collection, data preprocessing, data weighting, data analysis, data sharing, classification modeling, hyperparameter tuning and model evaluation. The results of this study are a model with a relatively optimal performance in classifying sentiment with an accuracy, precision, recall and f1-score of 90%. The results of the sentiment analysis obtained are in the form of ideas, complaints and suggestions for the COVID-19 vaccination.
URI: http://repository.ipb.ac.id/handle/123456789/109508
Appears in Collections:UT - Computer Science

Files in This Item:
File Description SizeFormat 
[Cover] G64170014_Qarry Atul Chairunnisa-halaman-1-13.pdf
  Restricted Access
Cover2.28 MBAdobe PDFView/Open
[Full teks]G64170014_Qarry Atul Chairunnisa.pdf
  Restricted Access
Full Text13.46 MBAdobe PDFView/Open
[Lampiran]G64170014_Qarry Atul Chairunnisa-halaman-41-53.pdf
  Restricted Access
Lampiran2.19 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.