BERT-based Transfer Learning Model for COVID-19 Sentiment Analysis on Turkish Instagram Comments

ABSTRACT

First seen inWuhan, China, coronavirus (COVID-19) became a worldwide epidemic. Turkey's first reported case was announced on March 11, 2020—the day the World Health Organization declared COVID-19 is a pandemic. Due to the intense and widespread use of social media during the pandemic, determining social media's role and effect (i.e., positive, negative, neutral) gives us essential information about society's perspective on events. In our study, two datasets (i.e., Dataset1, Dataset2) consisting of Instagram comments on COVID-19 were com posed between different dates of the pandemic, and the change between users' feelings and thoughts about the epidemic was analyzed with Latent Dirichlet Allocation (LDA) and text mining algorithms. The datasets are the first publicly available Turkish datasets on the sentiment analysis of COVID-19, as far as we know. The sentiment analysis of Turkish Instagram comments was performed using machine learning models (i.e., traditional machine learning (TML), deep learning (DL), and Bidirectional Encoder Representations from Transformers (BERT)-based transfer learning). The balanced versions of these datasets (i.e., resDataset1, resDataset2) in the experiments were evaluated with the original ones. Compared with TML models (i.e., Support Vector Machine (SVM), Naïve Bayes (NB), Random Forest (RF)) and DL models (i.e., Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Gated Convolutional Recurrent- Neural Networks (GCR-NN), the BERT-based transfer learning model achieved the highest classification success with 0.7864 macro-averaged F1-score values in resDataset1 and 0.7120 in resDataset2. It has been proven that using a pre-trained language model in Turkish datasets is more successful than other models in terms of classification performance. © Karayiğit, H., Akdagli, A., Acı, Ç. Í.