Why Charts Speak Louder Than Numbers? 📊
DataBites #21
Hey you all!
It’s Josep here again one more week! 👋🏻
This time, we’re diving into the captivating world of Data Visualization—unpacking the why behind its intuitiveness and exploring what makes it so effective.
Stick with me for just 6 minutes—I promise it’ll be time well spent! 🚀
The most important news of the week?
Next Thursday, I’m heading to Madrid to teach the “Data Visualization” module for the Big Data Master’s program at the University of Navarra.
It’s my second year, and I couldn’t be more thrilled to return! 🎉
Given the timing, it feels only fitting that this week’s issue dives into the fundamentals of DataViz.
Now that we’ve caught up, let's dive into the important stuff 👨🏻💻.
Before we dive into today’s topic, I highly recommend checking out my earlier DataViz-focused issues:
Building on these foundational topics, today’s spotlight is on the intuition behind Data Visualization—more specifically, what makes charts so powerful and engaging.
Why does this matter?
We've already recognized the importance of DataViz, but many people still don't understand why visual elements are more intuitive than raw numbers.
Many technical experts often overlook how profoundly our understanding of the world is shaped by the workings of our brains.
Today, let's reconnect with our human side and explore why some charts resonate more intuitively with us than others 💥
And this leads us to today’s main focus…
The Intuition Behind DataViz
But before starting, I want to share the Cheatsheet of the week 👇🏻
Breaking DataViz to Its Basics
There are two main theories behind the intuitiveness of charts - and a final technique that can be quite useful to know! 😉
1. Gestalt Theory
People who work with technology sometimes forget about the human side of things. The Gestalt Principles are rules from psychology that explain precisely this: How our brain sees patterns.
Some of these rules help us understand why we group things that look alike or notice things that stand out.
#1 Similarity
Gestalt similarity means our brain groups things that look alike. This can be because of their position, shape, color, or size.
This is extensively used in heat maps or scatter plots.
#2 Closure
Objects inside a border, like a line or a shared color, look as if they belong together. This makes them stand out from other things we see.
We often use borders or colors in tables and graphs to group data.
#3 Continuity
When individual elements are connected, our eyes think they belong together. Even if they look different, the line makes us see them as a group. This is extensively used in line charts.
#4 Proximity
We think things are in the same group if they are close to each other. To show things belong together, put them close. Using a little space can help separate different groups. This is commonly used in scattering plots or node-link diagrams.
2. The Principle of Proportional Ink
The second rule involves the Principle of Proportional Ink. In many different visualization scenarios, we represent data values by the extent of a graphical element.
It is common practice to use the word ink to refer to any part of a visualization that deviates from the background color. This includes lines, bars, points, shared areas, and text.
For example, in a bar plot, we draw bars that begin at 0 and end at the data value they represent. In this case, the data value is not only encoded in the endpoint of the bar but also in the height or length of the bar.
If we drew a bar that started at a different value than 0, then the length of the bar and the bar endpoint would convey contradicting information.
In all these cases, we need to make sure that there is no inconsistency. This concept has been termed the principle of proportional ink by Bergstrom and West.
“When a shaded region is used to represent a numerical value, the area of that shaded region should be directly proportional to the corresponding value.”
Violations of this principle are quite common when trying to manipulate data, in particular in the popular press and in the world of finance.
Similar issues will happen whenever we use graphical elements such as rectangles, shaded areas of arbitrary shape, or any other elements that have a defined visual extent that can be either consistent or inconsistent with the data value shown.
3. The Pop-Out effect
The pop-out effect stands out as a key technique for highlighting specific data points amidst a sea of information.
This visual phenomenon ensures that certain elements in a dataset instantly grab the observer's attention due to their distinctive features, such as color, shape, or size.
By leveraging this effect, data analysts can draw focus to unusual data behaviors or important outliers that might otherwise be overlooked in a complex visual.
To effectively implement the pop-out effect in your charts:
Use muted colors to represent general trends.
Select a vibrant, contrasting hue for the key data you want to emphasize.
This approach not only enhances the visual appeal of your charts but also aids in quicker data interpretation and decision-making processes.
Whether in a business presentation or an academic report, mastering the pop-out effect can significantly boost the communicative power of your visual data representations.
As data lovers, it’s our art, our language, and our bridge to the whole world.
So next time you craft a chart, remember…
You're not just a data professional, You're a storyteller!
Still with me? 🧐
As fellow data enthusiast, I’m sure you’d be eager to help me shape some impactful KPIs and take this newsletter to the next level!
So here’s how you can help:
👉🏻 I want this newsletter to be truly valuable for you, so please share your feedback!
Additionally, you can let me know any preference for future content or any idea you think might add more value to you!
My latest articles 📝
Unlocking the Power of Geospatial Data 🌍 in DataBites.
A Practical Guide to the Claude API in MLMastery.
6 Language Model Concepts Explained for Beginners in MLMastery.
5 Free APIs for Building AI Applications in MLMastery.
My Favorite Resources! 👨🏻💻
I strongly recommend following AIgents roadmaps if you want to become a full Data Scientist, ML Engineer, or Data Engineer,
You can follow the Data Engineer Zoomcap on GitHub to become a fully proficient Data Engineer.
Want to get more of my content? 🙋🏻♂️
Reach me on:
LinkedIn, X (Twitter), or Threads to get daily posts about Data Science.
My Medium Blog to learn more about Data Science, Machine Learning, and AI.
Just email me at rfeers@gmail.com for any inquiries or to ask for help! 🤓
Remember now that DataBites has an official X (Twitter) account and LinkedIn page. Follow us there to stay updated and help spread the word! 🙌🏻
My dearest friend!
I truly engaged with your articel on dataviz. Now, my question is about how you could use these abilities targeting all people, even those with visual impairments or cognitive. Can you give me a hint on that?
Sincerely,
MONIKA