There are many analytical tools that can show how the content you post on social networks performs.
Analytics help you learn what type of content is shared and viewed, but imagine if there was an app that could tell you how popular a post would be, before you send it into news feeds and timelines?
MIT student Aditva Khosla says he, and his team of researchers, have created an algorithm that can tell you if the photo you post on Instagram will be well-liked or not.
“While some images get millions of views, others are completely ignored. Even from the same users, different photographs receive different number of views. This begs the question: What makes a photograph popular?” asks Khosla.
2.3 million photos on Flickr
In carrying out his research, Khosla analysed 2.3 million photos on Flickr for content (e.g., the colour, the subject of the photo, texture) and social context (how many followers a user has, how many tags a photo has, the number of photos in the account).
What Khosla and his team discovered was that cooler colors (greens and blues) tend to do worse than warmer colors (more reds) and photos with objects are more popular than ones without objects. They then set about writing a photo popularity algorithm that you can test here.
The image above scored 4.862 on the photo popularity test, which is a good score. See the site for more details. The photos above were taken by Claire Durkin.
