Short Text Classification Using TF-IDF Features and Fast Text Learner

ABSTRACT

The spread of the COVID-19 is a challenge for the health sector. This pandemic created health and financial issues for the whole world. The medical experts are working for the diagnostics and reasons behind the COVID-19 disease and its spread. Some conspiracies are being spread related to the COVID-19 disease and its spread. Such conspiracies can be seen on social media including Twitter. In this research, the conspiracies of the COVID-19 have been analyzed from the public tweets. The tweets of the conspiracies have been filtered from the tweets of the COVID-19 disease, symptoms, and other discussions related to the disease. The analysis of the COVID-19 related tweets resulted into three conspiracy classes, the COVID-19 tweets without any conspiracy and the conspiracies. A model is presented for the classification of tweets into three conspiracy classes with the Matthews Correlation Coefficient (MCC) of 0.294. Copyright 2021 for this paper by its authors.