The “Observatory of an Ecosystem of Emotions” consists of a data visualization generated by the monitoring of predefined hashtags on Twitter themed around the Brazilian presidential election of 2018. We collected tweets that used trending hashtags during controversial campaign moments and applied Digital Methods and Data Science approaches to Sentiment Analysis. We used Processing and VVV to create generative art visualizations based on the contextual mining of the tweets’ text categorized by six emotions: pride, sadness, joy, fear, love and anger.

The facade of “Espaço do Conhecimento” museum at the Federal University of Minas Gerais

This experiment proposed a live data visualization on a large screen on the building’s facade at the University’s “Espaço do Conhecimento” museum. The museum is located at Praça da Liberdade, in Belo Horizonte, a recurring site of political protests in October 2018.

On the left, the VVVV programming interface view. On the right, the visual representation of hashtag frequencies. The mapped hashtags were #LulaLivre and #LulaPresoAmanha and describe opposing political views regarding the arrest of one of the presidential candidates.
On the left, the VVVV programming interface view. On the right, a sentiment analysis applied to the tweets posted with #LulaLivre and #LulaPresoAmanhã. A quantitative analysis of keyword frequency creates a visualization in which each color represents one of the sentiments: pride, sadness, joy, fear, love and anger.

We proposed a live data visualization at the museum’s facade that resulted from geolocated tweets originating from the square perimeter . However, given the sensitive political climate in the country, it was not possible to do a live demonstration of this project. Download research report (in Portuguese).

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.