Every day on Twitter millions of tweets talking about the latest news are posted. Covid-19 is an hot topic, so there is a huge quantity of tweets concering it. The aim of this project is to analyze the italian tweet about Coronavirus.

The data have been collected by the Italian Association of Computational Linguistic and can be found here: 40wita

In this project 4 different periods have been considered, each one representative of a particular moment of the italian emergency:

• 23 Februrary - 1 March
• 15 March - 22 March
• 19 April - 26 April
• 17 May - 24 May

Below an resume image with some important Covid italian emergency is reported, with the choosen periods highlighted.

For each period some explanatory data analysis has been done, in particular:

• Find the popular hashtags
• Find the protagonists

Then, different tasks have been done:

• Text generation
• Sentimenty Analyis
• Clustering & Topic Modelling

Before performing any tasks, the Preprocessing phase has been carried out.

For a detailed report see Report.pdf