|
| Business Intelligence Series |
From data-related professionals to book authors on data visualization topics, there are many voices that require from any visualization to tell a story, respectively to conform to storytelling principles and best practices, and this independently of the environment or context in which the respective artifacts are considered. The need for data visualizations to tell a story may be entitled, though in business setups the data, its focus and context change continuously with the communication means, objectives, and, at least from this perspective, one can question storytelling’s hard requirement.
Data storytelling can be defined as "a structured approach for communicating data insights using narrative elements and explanatory visuals" [1]. Usually, this supposes the establishment of a context, respectively a fundament on which further facts, suppositions, findings, arguments, (conceptual) models, visualizations and other elements can be based upon. Stories help to focus the audience on the intended messages, they connect and eventually resonate with the audience, facilitate the retaining of information and understanding the chain of implications the decisions in scope have, respectively persuade and influence, when needed.
Conversely, besides the fact that it takes time and effort to prepare stories and the afferent content (presentations, manually created visualizations, documentation), expecting each meeting to be a storytelling session can rapidly become a nuisance for the auditorium as well for the presenters. Like in any value-generating process, one should ask where the value in storytelling is based on data visualizations and the effort involved, or whether the effort can be better invested in other areas.
In many scenarios, requesting from a dashboard to tell a story is an entitled requirement given that many dashboards look like a random combination of visuals and data whose relationship and meaning can be difficult to grasp and put into a plausible narrative, even if they are based on the same set of data. Data visualizations of any type should have an intentional well-structured design that facilitates visual elements’ navigation, understanding facts’ retention, respectively resonate with the auditorium.
It’s questionable whether such practices can be implemented in a consistent and meaningful manner, especially when rich navigation features across multiple visuals are available for users to look at data from different perspectives. In such scenarios the identification of cases that require attention and the associations existing between well-established factors help in the discovery process.
Often, it feels like visuals were arranged aleatorily in the page or that there’s no apparent connection between them, which makes the navigation and understanding more challenging. For depicting a story, there must be a logical sequencing of the various visualizations displayed in the dashboards or reports, especially when visuals’ arrangement doesn’t reflect the typical navigation of the visuals or when the facts need a certain sequencing that facilitates understanding. Moreover, the sequencing doesn’t need to be linear but have a clear start and end that encompasses everything in between.
Storytelling works well in setups in which something is presented as the basis for one-time or limited in scope sessions like decision-making, fact-checking, awareness raising and other types of similar communication. However, when building solutions for business monitoring and data exploration, there can be multiple stories or no story worth telling, at least not for the predefined scope. Even if one can zoom in or out, respectively rearrange the visuals and add others to highlight the stories encompassed, the value added by taking the information out of the dashboards and performing such actions can be often neglected to the degree that it doesn’t pay off. A certain consistency, discipline and acumen is needed then for focusing on the important aspects and ignoring thus the nonessential.
References:
[1] Brent Dykes, "Effective Data Storytelling:
How to Drive Change with Data, Narrative and Visuals", 2019 [quotes]
