Analyzing user comments on Covid-19 pandemic with word2vec technique

Abstract

In Covid-19 pandemic, people spend more time at home than before the pandemic. Due to this reason, more time is spent on the internet than before. People expressed their views and assessments about Covid-19 pandemic on social media. Within the scope of this study, we collected people’s comments on different topics about Covid-19 pandemic on the internet and we evaluated them using Word2Vec technique. With this technique, vectors of words in a document are calculated and the semantic relationship between words is captured. The collected data include March and April data, so we compared the results of the two months. As a result of this study, many different results were found about people’s views and opinions about the pandemic. The results of this study can be used in the future as automatic psychological evaluation studies with natural language processing techniques. And the trained model will be shared on internet platforms.