550,000 tweets in 72 hours

Nicole Halmi
Jan 9, 2015 · 4 min read

Neon finds top images from #CES2015

By the end of day 3 of CES 2015, there were over 550,000 tweets with the conference hashtag #CES2015. With 150,000 people walking around with cameras in their back pockets, it’s no wonder that over 200,000 images were tweeted. Cutting through the #CES noise on Twitter to find the images that tell the best stories is not something that you could do by hand.

We decided to put our automated image selection platform to the test. Neon was able to algorithmically sift through hundreds of thousands of images in a matter of minutes. Our platform then assigned each image a Neon score based on our perceptual models of how the human brain sees and feels about images.

So, what are the best images from #CES2015?

While these images might seem unrelated, they all draw from the underlying principles of perception and human cognition known to generate image engagement and emotional responses (which you can also read more about in TechCrunch).

Brightness

“Off screen” engagement

Instability

Faces

Shape and curvature

Color gradients

Not all of the images that we pulled from Twitter were as engaging as the ones above. To illustrate this, we surfaced a few of the images that received a low Neon image score. Most of these images were too uniform in color, too blurry, or too text-heavy.

How did we do it?

We used Twitter’s API to collect images tweeted with the hashtag #CES2015. Neon’s image software then automatically ranked and scored the images. The Neon score predicts emotional engagement and the likelihood that an image will be clicked.

Neon is the fully automated image selection platform for monetizing digital content. Neon’s proprietary scientific solution increases revenue for leading online news, sports, entertainment media publishers, advertisers and marketers.

Neon: Images you care about.

www.neon-lab.com

Image credits:

https://twitter.com/TheGoToMom/status/552909942609301504/photo/1

https://twitter.com/TogetherNBCU/status/552515656500129792/photo/1

https://twitter.com/vcstar/status/552195788340609024/photo/1

https://twitter.com/TheNextWeb/status/553016872816615425/photo/1

https://twitter.com/jesseberger/status/552968829110718465/photo/1

https://twitter.com/NickCannon/status/552982233624363009/photo/1

https://twitter.com/verge/status/552871732420546560/photo/1

https://twitter.com/sandeepmadhukar/status/552354473914679303

https://twitter.com/FibaroUS/status/551493143921963008

https://twitter.com/VirtuixOmni/status/552879109374619648/photo/1

Neon Open

Open Source AI that predicts emotion from images

Medium is an open platform where 170 million readers come to find insightful and dynamic thinking. Here, expert and undiscovered voices alike dive into the heart of any topic and bring new ideas to the surface. Learn more

Follow the writers, publications, and topics that matter to you, and you’ll see them on your homepage and in your inbox. Explore

If you have a story to tell, knowledge to share, or a perspective to offer — welcome home. It’s easy and free to post your thinking on any topic. Write on Medium

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store