Data Visualization: The future of data visualization
By Will Towler
Data visualization is entering a new era. Emerging sources of intelligence, theoretical developments and advances in multidimensional imaging are reshaping the potential value that analytics and insights can provide, with visualization playing a key role. The principles of effective data visualization won’t change. However, nextgen technologies and evolving cognitive frameworks are opening new horizons, moving data visualization from art to science.
Looking back, much attention has been given to the principles of effective data visualization, such as substance, context and actionability. As timeless tenets that will continue to be important, regardless of medium or format, a brief review seems in order:
- As with any form of communication, effectively conveying a message with data requires that it be substantive. And while creative visuals can enhance interest and memory, embellishment can’t make up for lack of substance. According to purist Edward Tufte, “Every single pixel should testify directly to content.” Learn more.
- Visualization should be accurate and contextual. David McCandless’s Billion Dollar O’Gram provides an example of how greater meaning can be added by incorporating the bigger picture. According to McCandless, “Absolute figures in a connected world don’t give you the whole picture. They’re not as true as they could be. We need relative figures that are connected to other data so that we can see a fuller picture.” Learn more.
- More than anything else, data visualization should facilitate decision-making, a goal that is difficult to achieve for many. According to a recent KPMG study, while data and analytics are deemed increasingly important to organizations, generating actionable insights remains a top challenge. Learn more.
Figure 1: Billion Dollar O’Gram. Source: David McCandless http://informationisbeautiful.net
|Figure 2: Pre-Internet sociogram. Source: Journal of Social Structure|
Looking forward, nextgen technologies and evolving cognitive frameworks will boost the role that data visualization can play in organizations and society. Consider the Internet of Things, Network and Complexity Theories, and recent developments in multidimensional visualization:
The Internet has transformed the way we visualize information through a better understanding of networks and an explosion in profile, behavioral and attitudinal data. Sociograms, for example, have gone from relatively simple graphs to multifaceted relational maps, as illustrated in Figure 2 and Figure 3, courtesy of the Journal of Social Structure and the Leadership Learning Community.
The Internet of Things is expected to have a similar impact, with billions of connected devices capturing human and machine activity. Fully capitalizing on the data generated will require further advances in our ability to synthesize and display spatiotemporal activities.
Network Theory has been in use for decades, with its earliest applications largely in social structure analysis. More recently, Network Theory is being applied to understand relationships and interactions in a variety of domains, such as crime prevention and disease management. Dirk Brockmann and Dirk Helbling’s work modeling the spread of infectious diseases provides an example of the power that Network Theory holds.
In their article, “The Hidden Geometry of Complex, Network-Driven Contagion Phenomena,” in Science magazine, the authors wrote:
Figure 3: Internet-age sociogram. Source: Leadership Learning Community
Figure 4: Global spread of infectious diseases. Source: Science (http://www.uvm.edu/~cdanfort/csc-reading-group/brockmann-science-2013.pdf)
“The global spread of epidemics, rumors, opinions, and innovations are complex, network-driven dynamic processes. The combined multiscale nature and intrinsic heterogeneity of the underlying networks make it difficult to develop an intuitive understanding of these processes, to distinguish relevant from peripheral factors, to predict their time course, and to locate their origin. However, we show that complex spatiotemporal patterns can be reduced to surprisingly simple, homogeneous wave propagation patterns.”
By providing insight into the workings of dynamic systems with interdependent elements, Complexity Theory can help us identify trends that might lead to unexpected tipping points such as environmental disasters. Complexity Theory can also support the decoding of intricate structural dependencies such as economic and market forces. In “The Atlas Of Economic Complexity,” for example, the work of Cesar Hidalgo, Ricardo Hausmann and project members illustrates how understanding the composition of a country’s cumulative industrial knowledge can explain economic development in ways not possible through more traditional linear econometric frameworks.
Figure 5: Depiction of economic complexity. Source: The Observatory of Economic Complexity; http://atlas.media.mit.edu/atlas/
The vast majority of data visualizations today are two-dimensional. However, that’s changing with creative use of color and size, combination of space and time, and advanced computer graphics. For instance, neuroscientists Emmanuelle Tognoli and Scott Kelso developed a five-dimensional model known as the 5-D colorimetric technique, that provides a dynamic and comprehensive view of brain activity through spatiotemporal display and color coding. Another example is Microsoft’s Holograph, an interactive 3-D platform that can render static and dynamic images above or below a plane for more natural exploration and manipulation of complex data. And commentary from team members Curtis Wong and David Brown posted on Microsoft News suggests that Holograph may one day allow users to actually reach inside a visual and interact with it.
Figure 6: The 5-D colorimetric technique. Source: Florida Atlantic University, Center for Complex Systems and Brain Sciences; http://www.ccs.fau.edu/hbbl3/?p=1013
Figure 7: Microsoft’s Holograph, an interactive 3-D platform. Source: Microsoft; http://microsoft-news.com/microsoft-research-talks-about-holograph-an-interactive-3-d-data-visualization-research-platform/
As the world becomes increasingly interconnected and interdependent, opportunities to generate value through data visualization will only increase. The Internet of Things will have a profound effect on the role that data visualization can play in organizations and society, improving our ability to understand how humans and machines interact with each other and the environment. Application of evolving cognitive frameworks, such as Network and Complexity Theories, will help us better reflect dynamic and intricate structural dependencies. And advances in multidimensional visualization will allow us to more effectively synthesize and explore spatiotemporal conditions.
The Internet of Things
Tens of billions of devices will be connected to the Internet in the next decade. From smart appliances and wearables to automobile sensors and environmental monitors, the Internet of Things will provide unprecedented insight into what’s happening around us. High-throughput, interconnected data streams will help us improve safety, drive operational efficiencies and better understand consumer demand.
In the words of Kevin Ashton, who first coined the term “the Internet of Things” in his seminal 2009 RFID Journal article, “The Internet of Things has the potential to change the world, just as the Internet did. Maybe even more so.”
Network Theory builds on Graph Theory, which applies algorithms to understand and model pair-wise relationships between objects. Network Theory examines relationship symmetry, with the existence of asymmetric relationships providing grounds to predict the likely spread of information (social network analysis), dissect complex disorders (biological network analysis), find the shortest path between two points (network optimization) and identify target objects based on their behavior (link analysis).
Complexity Theory posits that many systems are characterized by complex, non-linear interactions that evolve dynamically and often unpredictably. Known as the “butterfly effect,” small perturbations in one state (“here”) can result in large repercussions in a seemingly unrelated state (“there”). According to Complexity Theory, it’s impossible to predict with certainty a future state, but it is possible to understand the structure and potential states of complex systems.
The adage “a picture is worth a thousand words” gained credence from our ability to process visuals more easily than text. Visualization has also been shown to improve learning and recall, and can portray complex concepts and relationships more easily than can text. Recent developments in computer graphics are making possible visualizations that enable the integration, manipulation and exploration of dynamic multidimensional data sets. Multidimensional visualizations allow users to not only examine data from new perspectives but also interact with it more effectively.
Will Towler (firstname.lastname@example.org) is an analytics and insights specialist. The views expressed in this article are those of the author and do not necessarily represent the views of an employer or business partners.