Sign in or start a free trial to avail of this feature.
5. Telling Stories with Data
There can sometimes be a disconnect between technically minded data analysts and managers focused on the big picture. This lesson provides some thoughts on how to overcome this potential issue by treating data as a storytelling tool.
The goal of this lesson is to learn how to tell stories with data.
Structuring a Story
Converting data analysis into a story is a great way to overcome any disconnect between technically minded analysts and business-focused executives. The key to keeping people interested in a story is to provide a structure. The notion of storytelling goes back to Aristotle’s time, and he proposed the following structure for a story:
Present an interesting story or statement
Deliver a problem that needs to be solved
Propose a solution to the problem
Explain the benefits of your solution
State a call to action
When creating a story, you need to tailor it to the audience involved. We consider this more fully in the next lesson.
A good story should be objective and unbiased. It should reflect how things actually are, not how you want them to be. You should let your data tell the story, instead of manipulating the data to fit the desired story.
- [Narrator] In the previous lesson, we learned how to create a project scope for a data analysis project. You might have been surprised just how nontechnical the process was. One of the biggest issues that can arise in data analytics is the disconnect between tech savvy analysts and business-focused executives.
If this disconnect isn't understood and dealt with, analysts may find themselves working on something their managers aren't interested in and managers may not know what to do with the work produced by their analysts. In this lesson, we'll learn how to tell stories with data.
This is a great way to overcome the possible disconnect between two groups. Treating data analysis as a story ensures that you relate analysis results in a way that will be both understandable and engaging to your audience. We'll consider three principles for turning your data analysis into a compelling story.
These principles are story structure, audience, and objectivity. In order to keep people interested in any story, you need to have a structure.
The notion of applying a structure to stories goes back to the time of Aristotle.
Even though he didn't work in data analytics, his suggested structure is still relevant. Under Aristotle's structure, you should present an interesting story or statement, deliver a problem that needs to be solved, propose a solution to the problem, explain the benefits of your solution, and state a call to action.
In effect, once you've outlined the background and the problem, you should put forward a solution and only then justify why the solution is appropriate.
Avoid explaining every step you take and every number you crunch before presenting your solution at the end. This approach will not keep any audience engaged. The audience themselves are an important consideration in creating a story.
You need to know their level of expertise, how receptive they are likely to be to your work, and various other factors. In fact, considering the audience is an important enough topic that we'll cover separately in the next lesson.
Finally, your story should be objective and balanced.
Let's discuss some general principles that will help keep your story unbiased.
Your story should include any relevant findings whether they're positive or negative. Presenting only certain elements of the story is both misleading and manipulative neither of which is desirable. After all, a novel will include happy events and sad events.
Similarly, your story should reflect how things really are, not how you'd like them to be. In effect, you should let the data tell the story, not the other way around. Avoid the urge to manipulate the data to fit a specific narrative. Of course, you may have an idea of what the data will tell you but at least some of the time that idea will be challenged. You should be open to accepting a different narrative if the data proposes it.
This concludes our look at storytelling with data.
Stories are beneficial for multiple reasons. They make your data accessible to a wider audience, especially a nontechnical audience. They also make your analysis more engaging to any audience. However, not every story will appeal to every audience. In the next lesson, we'll discuss more about the importance of understanding the audience for your data analysis.