Data visualization, or the techniques used to visually display or communicate data, is an obvious output of our research or data analysis. The idea is to quickly and clearly display data for purposes of analysis or presentation. Being able to effectively communicate your data to an audience is a necessary part of any project, and the follow tools and techniques can help begin you on your journey to success.
There are many common sense and practical aspects of data visualization that often get left behind in the rush to make a usable graph. The elements that make up a successful visualization do not just include ensuring your data is there, but whether or not your data is interpretable, legible, and visually appealing enough to hold your audience’s attention.
Besides learning what makes a good graph, it is important to have an understanding of what tools will help you create one. There are many considerations that should be weighed when choosing a tool, such as whether that tool is open source, can it make online and/or interactive graphs, and what visual options it can make. For example, there can be many tools to make online-interactive maps that link to box plots, but which one will work best for your data and abilities is important to consider. Specifically, what experience do you have working with software, do you want to code a visualization or use an intuitive interface to make a graph?
There are several tools or software that can be used to make graphs, including Tableau, R, Excel and Python.
The Libraries offer several workshops on tool use for data visualization, including R, Python, and Tableau.
When making a visualization (graph, map, table, etc.) one must keep in mind the following:
1. Keep data clean and clear (the style your data is grabbed to be graphed will impact the final visualization).
2. What story are you trying to tell with your visualization (what do you want your audience to remember tomorrow).
3. Don’t overwhelm your audience (keep the data represented in your graph to the minimum you need to tell your story, don’t clutter your visualization).
4. Who is your audience (what types of graphs does your audience expect, what challenges might your audience have reading your graph).
5. What type of graph should be used (if you are using spatial data you might need a map, if your showcasing clustering of results you may need a scatter plot).
6. Balancing the form and function of your graph (does your graph have an attractive design that does not obscure the message of the data displayed in it).
For help with data or data-related tools, or for any other questions, please contact the University Libraries Data and Publishing Services team.