Analisis Sentimen Warga Indonesia Terhadap Penanganan Kasus COVID-19 Menggunakan Metode Naïve Bayes Dan Support Vector Machine (SVM)

Lestari, Dhany Nastiti (2021) Analisis Sentimen Warga Indonesia Terhadap Penanganan Kasus COVID-19 Menggunakan Metode Naïve Bayes Dan Support Vector Machine (SVM). Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[img] Text
06211740000060-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2023.

Download (1MB) | Request a copy

Abstract

Kehidupan masyarakat zaman sekarang mengalami banyak perubahan akibat dari perkembangan ilmu pengetahuan dan teknologi. Masyarakat menjadi lebih reaktif menanggapi fenomena disekitar, termasuk berita, kebijakan, serta upaya-upaya pemerintah menanggulangi pandemi COVID-19. Feedback masyarakat mengenai upaya-upaya pemerintah menanggulangi bencana dapat dijadikan bahan evaluasi untuk meningkatkan kinerja. Untuk mendapatkan hasil yang dapat dilihat secara jelas maka digunakan proses klasifikasi terhadap opini-opini masyarakat menjadi opini dengan sentimen positif serta sentimen negatif. Data teks yang didapat dari tweet masyarakat Indonesia akan di preprocessing menggunakan tokenisasi, case folding, serta penghapusan stopwords. Data hasil preprocessing akan dilakukan ektraksi fitur Term Frequency-Inverse Document Frequency (TF-IDF), dengan satu term adalah sebuah n-grams dan akan dilakukan klasifikasi menggunakan metode naïve Bayes dan Support Vector Machine (SVM). Hasil dari klasifikasi sentiment menunjukkan bahwa metode SVM lebih baik daripada Naïve Bayes, khususnya SVM dengan menggunakan kernel radial basis karena memiliki F1-score, recall, dan accuracy yang lebih tinggi. =================================================================================================== Life in our current society undergoes many changes as a result of the development of science and technology. People have become more reactive in responding to phenomena around them, including news, policies, and government efforts to tackle the COVID-19 pandemic. Public feedback regarding the government's efforts to cope with disasters can be used as evaluation material to improve performance. To get results that can be seen clearly, a classification process is used to classify public opinions into opinions with positive sentiments and negative sentiments. Text data obtained from Indonesian people's tweets will be preprocessed using tokenization, case folding, and removal of stop words. The data from the preprocessing will be extracted with Term Frequency-Inverse Document Frequency (TF-IDF), with one term being n-grams and will be classified using the Nave Bayes method and Support Vector Machine (SVM). The results of the sentiment classification show that the SVM method is better than Naïve Bayes, especially SVM using a radial basis kernel because it has a higher mean F1-score, recall, and accuracy.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: COVID-19, Feature Extraction, Naïve Bayes, Preprocessing, SVM. COVID-19, Ekstraksi Fitur, Naïve Bayes, Preprocessing, SVM.
Subjects: Q Science > Q Science (General) > Q325.5 Machine learning.
Q Science > QA Mathematics > QA279.5 Bayesian statistical decision theory.
T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models.
Divisions: Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User: Dhany Nastiti Lestari
Date Deposited: 31 Aug 2021 13:37
Last Modified: 31 Aug 2021 13:37
URI: https://repository.its.ac.id/id/eprint/91616

Actions (login required)

View Item View Item