Algoritma Multinomial Naïve Bayes Untuk Klasifikasi Sentimen
Pemerintah Terhadap Penanganan Covid-19 Menggunakan Data Twitter

Algoritma Multinomial Naïve Bayes Untuk Klasifikasi Sentimen
Pemerintah Terhadap Penanganan Covid-19 Menggunakan Data Twitter

: opinion, sentiment, twitter, covid-19, multinomial naïve bayes

Currently, the spread of information Covid-19 is spreading rapidly. Not only through electronic media, but this information is
also disseminated by user posts on social media. Due to the user text posted is varies greatly, it’s needs a special approach to
classify these types of posts. This research aims to classify the public sentiment towards the handling of COVID-19. The data
from this study were obtained from the social media application i.e., Twitter. This study uses a derivative of the Naïve Bayes
algorithm, namely Multinomial Nave Bayes to optimize the classification results. Three class labels are used to classify public
sentiment namely positive, negative, and neutral sentiments. The stage starts with text preprocessing; cleaning, case folding,
tokenization, filtering and stemming. Then proceed with weighting using the TF-IDF approach. To evaluate the classification
results, data is tested using confusion matrix by testing accuracy, precision, and recall. From the test results, it is found that
the weighted average for precision, recall and accuracy is 74%. Research shows that the accuracy of the proposed method has
fair classification levels.

Yuyun1
, Nurul Hidayah2
, Supriadi Sahibu3

STMIK Handayani Makassar

30-08-2021

Fajar bagus W

PDF

Indonesia

Text