esquire.png

Esquire Italy: Data-Driven Story  

Over the pandemic, I worked together with Francesco Magnocavallo—Digital Strategy Director at Hearst Italy—on a data-driven story published on Esquire Italy for the column “Barometro Hearst”. The column's purpose is to illuminate readers with data insights and provide them fresh stories hidden into the Italians' social media data related to covid-19.

With my multidisciplinary background, at the intersection of data science and data journalism, I’ve been wondering for a while how to combine artificial intelligence in journalism's practices, to uncover overlooked stories. The collaboration with Esquire offered me the opportunity to build a story upon AI, by utilizing Natural Langue Processing (NLP) techniques.

To discover and build the story I first processed 10 months of Twitter's data, which accounts for millions of tweets. By developing an NLP algorithm and using Topic Modeling techniques, I managed to portrait the digital conversations of the Italian news media outlets occurring on Twitter over the two lockdowns that hit Italy, starting from February 2020.

Nella seconda ondata si parla molto di lavoro e meno di morti: 10 mesi di Covid-19 online al microscopio

My role in the project:

  • Clean, Process, and Analyze Twitter data thru NLP and Topic Modeling Techniques (R language)

  • Visualize data to extract insights (R + d3.js)

  • Build storyline

  • Combine data visualization

  • Write the Story

Year:

2020​

Screenshot 2020-12-20 at 12.49.51.png
3FEE28FF-0124-4AEF-944E-562F73212A35.JPG
Screenshot 2020-12-20 at 12.49.51.png

The process

The process used to craft the story relied mostly on data visualization: it's by first discovering insights in the intricate systems of data by using visualizations that I manage to find the building blocks around which to build the story. 

 

Thru research and reporting, I put the data insights in context and laid out a storyline around the difference in the choice of topics posted on Twitter by the Italian News Media Outlets.

 

Thru the data, I provided Esquire's readers a story that otherwise, without the use of algorithms and data visualization, would remain buried in the social media. 

 

In fact,  the story revealed a big difference in the editorial lines adopted by the Italian news media outlets over the time of the pandemic.

Below, a few insights extracted by the data analysis and used for crafting the story.

Asset 4chart3.png
Asset 1chart3.png
Asset 10chart7.png
Asset 3chart3.png

The story in Italian language is available here