Data visualization is fundamentally an act of communication. While many discussions focus on the technical aspects of creating visualizations, communicating your insights in a clear, relevant and accessible way is essential.
The Georgia Institute of Technology team shared some key lessons, based on their experience building the COVID-19 Event Risk Assessment Planning Tool. These lessons apply to visualizations across many different industries and use cases, whether you are communicating to a handful of executives at your company or out to the world.
In July 2020, Georgia Institute of Technology faculty, scientists, GIS specialists, and graduate students launched a tool that provided real-time, localized information on the estimated risk of COVID-19 exposure by attending an event.
“Over a year ago we had been concerned as early as March 2020 that there were generally underappreciated risks associated with attending even medium to small events. Given that cases were spreading, it was hard to figure out how many cases there really were. All these questions of whether or not the cases were being documented, (and we were fairly certain they were under ascertained, underdocumented) we wanted to translate that in some way to communicate that out to the world - individuals as well as decision makers”
-Joshua Weitz PhD, Professor, Biological Sciences & Physics, Georgia Institute of Technology
Their team presented this risk out to the world through an interactive Shiny application, which allowed users to determine their own risk of encountering someone with COVID at an event in their given location.
What if you were planning on having dinner at a restaurant with 20 people in Ontario, NY? A small wedding with 50 people in Teton, WY? Deciding to go back to your office?
The narrative became personal to the individual user by answering their specific question in a direct metric that they could not only understand but share with others.
In talking with the GA Tech team, it was clear that their empathetic perspective of the audience and communication-focus was crucial to successfully sharing their insights with event planners, policy makers, various news outlets and individuals - adding up to ultimately over 8 million unique users around the world.
Thank you so much to the team at GA Tech for sharing their story with me:
I’ve included a few other helpful communication resources below:
With the vetiver package, data scientists have a streamlined, consistent way to maintain machine learning pipelines. We recently updated our Bike Share prediction application using vetiver and Quarto.
In this post, we walk through the tools and functionality we used to automate survey results reporting.