Editor’s Note: Be sure to attend Alan’s talk on this idea of telling human stories with data at ODSC Europe this November 19 – 22 in London! Register now for “Bringing Data to the Masses Through Visualization.”

If you’re reading this and you’re part of the ODSC community, the chances are you’re an expert in the data you work with. You understand the methodologies required to make the data robust and meaningful, and you are already using tools to visualize data for yourself to better see patterns and relationships. Communicating the meaning of the data to non-experts, however, brings new challenges.

[Related Article: Why Effective and Ethical AI Needs Human-Centered Design]

I work with government departments, corporations, startups and charities on developing their data visualization practice–from the simplest PowerPoint slide through to complex, interactive dashboards–and I consistently find that this storytelling aspect of data science is the one that causes the most problems.

Non-experts in data are often your most important stakeholders: senior leaders, colleagues in non-data roles, investors, customers, regulators, donors, or members of the public. Convincing them of the importance and urgency of a data pattern or trend is what drives change, alters behavior, prompts actions and gets decisions made.

Over my time working with different organizations, I’ve come to rely on a simple three-part framework for creating data visualizations that are compelling for human audiences—telling human stories with data. It’s not a guaranteed formula for success, but in my experience when a visualization isn’t working, it’s because one of these elements has either been poorly defined, or not discussed at all.


With visualizations, there is a natural tendency to start with the data and work out from there. This makes intuitive sense–but actually we need to jump ahead and think about our audience, and the context in which they’re going to receive the information.

Human beings have different prior experience, knowledge, and motivations–depending on their background and role. They may be domain experts, but not data experts. They will be looking at your visualization from the perspective of what it means for them–so present the data in a way that makes that easy to see and understand. Remember, you’re probably not trying to simply win an argument–you’re trying to win people over. This requires empathy.

Format also matters here. There is no single ideal way to visualize a data set. The output should and will look completely different depending on whether it’s a presentation slide, a poster, an image on social media, an online interactive, or long, printed report.

If you have multiple, diverse audiences, you’ll probably need to create a separate data communication for each one. If you’re trying to aim something at ‘everyone’ it’s likely that it won’t resonate with anyone. Defining your audience at the start of the process makes it much easier to decide what data to include (and what you should leave out), what format will work best, and how much contextual information they will need.


Once you’ve established ‘who’ you’re talking to, you need to define ‘what’ you’re telling them. You should be able to write the story (or key message) down as a single, short sentence. This should be the title that sits above your visualization–rather than the title being the name of the data set.

From a big piece or research or large data set, you’re likely to have multiple stories–but tell them one at a time. Put simply, ten slides with one clear chart per slide is much better than one slide with ten charts piled on top of each other.

Talking in terms of stories can make data scientists nervous–they worry about cherry-picking, being biased, or not showing the whole picture. But a crucial part of your role is to act as an expert filter, and separate the signal from the noise. Think about what you would be comfortable verbally telling somebody about the data set–your story just needs to match (not exceed) that level of confidence.

There’s a reason you’ve taken people’s time and attention and asked them to look at this data–tell them what that reason is. If you’re not sure what the key message is, the person you’re communicating with has no chance of understanding it.


This is the “why” part of the equation: we are showing you this data because we think you need to do X. You could be prompting a decision, asking a question, specifying a specific action, or cajoling your audience into some kind of behavior change–but there has to be a reason why you’re presenting them with this data in the first place.

This is another thing that can cause concern for data scientists–particularly if you feel that your role is to provide insight, not dictate the decision-making. Your rank and role within the organization will determine whether the action is an order, a recommendation, or a suggestion.

But in nearly every case, you can flag up the patterns, trends, anomalies, areas of concern, or potential opportunities–and then simply recommend that resource and attention from the senior team should be directed towards those areas.

In Summary: Telling Human Stories with Data

This simple three-part framework (Audience, Story, Action) gives you a mini brief to work to when you’re building a visualization that needs to communicate effectively to non-experts.

[Related Article: 3 Things Your Boss Won’t Care About in Your Data Visualizations]

Obviously, there are additional complexities and nuances that come with applying this in practice, and I’ll be expanding on these in my talk at the ODSC Europe in November.

Editor’s Note: Be sure to attend Alan’s talk on this idea of telling human stories with data at ODSC Europe this November 19 – 22 in London! Register now for “Bringing Data to the Masses Through Visualization.”