Instruction and training in data science tend to focus on the analysis of data through the prioritization of learning skills in both programming and statistics. However, the presentation of data is just as important as the programming of a dataset. After data is collected and analyzed, the process of visualizing the dataset allows a data science professional or analyst to share their findings with individuals both within and outside of their industry. A field unto itself, there are also a variety of data visualization tools and techniques that can be used by data scientists to present and communicate these findings.
Yet, even as data scientists learn new tools and techniques to visualize a dataset, that doesn’t always mean that these findings are easily understood by their audience. Acting as an accompaniment to traditional graphs and charts, data storytelling provides additional context and comprehension to these methods of data visualization. Data science professionals should not only embrace their role as scientists, but storytellers with knowledge and understanding of how to use narration, rhetoric, and other communication skills to get their point across.
What is Data Visualization?
Data visualization is the visual representation of information and data, usually through graphs and charts. Most data visualizations include a model or image of statistical analysis or specific data findings, and within data science, there are many graphs and models that are commonly used to communicate these interpretations. Some of the most common data visualizations show the plotting of data points, either in clusters, groupings, or spread along a line indicating a relationship between variables or aspects of a dataset. Unfortunately, when graphs or charts are used to visualize statistical analysis, these graphics tend to include little explanation about the meaning or key takeaways from that graph.
For example, when looking at a graph of regression analysis, there is usually a title, perhaps an equation, and the label for the variables on the x-y axis. There might not be any additional information about what the slope of a line means or the implications of the relationship between the independent and dependent variables. While data visualization is commonly used to create more context and a deeper understanding of a researcher’s findings, this same visualization can also further confuse the outcomes or meaning behind the data.
How is Data Storytelling Different from Visualization?
While data visualization and storytelling are often discussed in conjunction with each other, there are slight differences between the two. In contrast to the creation of data visualizations, data storytelling is focused on presenting information to an audience by using various communication methods and creative contexts. Moving from the process of data visualization to data storytelling requires an understanding of the argument that you want to create and the message that you want your audience to take away from the presentation of data findings.
Similar to the process of data cleaning and organization, data storytelling also requires the process of looking at your data and deciding what needs to be included in any visualizations and what does not need to be included. Data storytelling is focused on presenting data in a way that is easily accessible and comprehensible. Through the process of selecting the best method of visualization, a data science professional should focus on presenting data in a way that is neat, organized, and doesn’t overwhelm the viewer with information that is difficult to understand or that makes it hard to find the conclusions or major takeaways.
Through a variety of rhetorical devices, data storytelling signals to the viewer what the data means and why it matters. This could be as simple as creating headlines and captions within your graphs and charts that explain the key points or the purpose of specific aspects of your visualization. Another method of data storytelling relies on less traditional graphs, such as infographics and interactive charts, which ensure that the most important findings stand out to the audience.
The Importance of Storytelling in Data Visualization
Data storytelling acts as a complement to data visualization by creating a narrative around the numbers that you are presenting. When using data for predictive analytics and forecasting, it is helpful to provide a more in-depth explanation for not only the how of data-analysis, but the why behind it. Although a graph can communicate research findings in and of itself, creating an argument or deeper understanding in conjunction with the graph ensures that you get your point across. This is important because data science professionals can forget that not everyone has training in, or knowledge of, the visualization of information and data.
While a chart of linear regression or some other form of statistical analysis is easily understood by those with training in data science, for those outside of the field these graphics and visualizations can appear to be just dots on a line. When presenting data findings to a diverse audience, it is important to present these findings using language and markers that are accessible to multiple groups. This could be as simple as including captions and markers indicating the meaning behind a datapoint or graphic, as well as working with different colors, images, and symbols that are highly recognizable and communicate the findings presented in multiple ways.
In this sense, combining both data visualization and storytelling is useful within the world of business and finance, as well as the development, advertisement, and marketing of products. Within these industries, data science professionals are expected to present their research in a way that is convincing and compelling so that the stakeholders in a project will be invested in the outcomes or deliverables of the findings. By learning how to present data in a way that not only visualizes the findings but also tells a story, data science professionals can ensure that the presentation of data is effective at garnering the preferred response.
Interested in learning more about the presentation of data?
While the role of data science is closely tied to data analytics and making predictions, it is only through the presentation of data to an audience that these key insights and findings can be understood. Noble Desktop offers multiple data visualization courses which offer instruction in specific data visualization tools and software which support the move from the simple presentation of numbers to a greater understanding of narrative. The Tableau Bootcamp teaches students how to make a variety of graphs, charts, and interactive data visualizations. In addition to these data visualization courses, Noble Desktop also offers data science classes that include hands-on experience with data science tools and software which can be used to present and visualize data.