Over a million developers have joined DZone.

The Mathematics of Memes

DZone's Guide to

The Mathematics of Memes

We spend a great portion of our online lives viewing and creating content like memes. Studying the data behind dank memes can help us predict why, when, and how they go viral.

· Big Data Zone ·
Free Resource

The Architect’s Guide to Big Data Application Performance. Get the Guide.

The science behind viral content is something that I’ve touched on a few times over the years, but the huge success wrought by content that hits a nerve means there is no let-up in the amount of interest in the topic.

The latest effort is a study from the University of Manchester, who teamed up with data company Spectra Analytics to examine some of the biggest trends and memes from recent years to try and discover any common themes.

The Science of Memes

The researchers examined 26 different memes in total, dating back to 2011. They were looking for both the impact the meme had and its longevity.

The resulting model is known as "complex contagion" and describes the way behaviors spread as a result of online sharing. The team believes that their math and data-driven approach to the theory of complex contagion provides the first empirical evidence for its impact on society.

“Social influence can lead to behavioral “fads” that are briefly popular but then quickly die out. Various theories and models have been proposed to explain such behaviors, but empirical evidence of their accuracy as real-world predictive tools have been absent so far,” the authors explain.

The researchers hope that their work will not only shed some light on the reasoning behind online fads but will also be invaluable in predicting which trends will take off. This has some obvious advantages for the marketing industry but also any other sector that relies on getting a message across, whether it's political campaigning or public health messaging.

“Complex contagion has predictive power. The fast spread and longer duration of fads driven by complex contagion have important implications for activities such as publicity campaigns and charity drives. If we can predict and control what messages go viral, that is a very powerful tool,” they say. “The significance of the study isn’t simply to understand why we follow fads online but to fully understand social influence and the effect others’ behavior has on our own. Improved understanding of this phenomenon should help to predict various phenomena of interest, from how well public-health interventions will work to the use of “nudges” in public policy.”

The model was put through its paces by predicting the spread of the Ice Bucket Challenge that took the web by storm in 2014. It was able to predict both the impact and the duration of the Ice Bucket Challenge with 95% accuracy.

Check out the video below to see the author talk about the study.

Learn how taking a DataOps approach will help you speed up processes and increase data quality by providing streamlined analytics pipelines via automation and testing. Learn More.

big data ,big data analytics ,predictive analytics

Published at DZone with permission of

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}