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

Abstract

First seen in Wuhan, China, the coronavirus disease (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 the role and effect (i.e., positive, negative, neutral) of social media gives us important information about society's perspective on events. In our study, two datasets (i.e. Dataset1, Dataset2) consisting of Instagram comments on COVID-19 were composed between different dates of the pandemic, and the change between users' feelings and thoughts about the epidemic was analyzed. 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, Deep Learning, and BERT-based Transfer Learning). In the experiments, the balanced versions of these datasets (i.e. resDataset1, resDataset2) were taken into account as well as the original ones. 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 the use of a pre-trained language model in Turkish datasets is more successful than other models in terms of classification performance.

Twenty Years of Machine-Learning-Based Text Classification: A Systematic Review

“…With the recent increase in demand for various Natural Language Processing (NLP) technologies, such as chatbots [3], content classification [4], Sentiment Analysis [5][6][7], hate speech detection [8,9], authorship recognition and attribution [10], product and service recommenders [11,12], text summarization [13,14], email spam detection [15] and phishing detection [16], intent detection [17], and search optimization [18], ML models have presented a huge advantage and have created many opportunities for researchers in the field of text classification.…”

Mengungkap Opini Publik: Pendekatan BERT-based-caused untuk Analisis Sentimen pada Komentar Film

“…Proses ini dilakukan pada tingkat kata dan karakter, memungkinkan model untuk memahami konteks dan hubungan antar-karakter. Metode ini membantu BERT mengatasi kata-kata yang sulit atau morfologi yang berbeda sambil mempertahankan struktur informasi yang penting (Chiorrini et al, 2021;Hutama & Suhartono, 2022;Karayiğit et al, 2022).…”

IPSO-LSTM hybrid model for predicting online public opinion trends in emergencies

“…In recent years, studies on public opinion have primarily concentrated on analyzing [26], spreading [27], warning [28], and supervising it [29]. Public opinion analysis chiefly discusses network events' evolution trend [30], topic classification, and the hot topic comments' emotional tendency detection [31][32][33][34]. The research content of public opinion propagation typically includes the following aspects: public opinion events' development cycle [35], evolution, communication, and influence [36,37].…”