Ever wonder why your dinner shots and saturated sunset scenes aren’t getting the love you think they deserve on Instagram? Well, fret no more, because one nerd over at MIT has cracked the code of public opinion and developed a rudimentary algorithm that predicts the relative popularity of any image.
Of course, this tool has broad implications for website designers, art directors, photographers – hell, even real estate agents – but first, let’s apply it to selfies.
The algorithm, developed by Aditya Khosla, a PhD candidate at MIT’s prestigious Computer Science and Artificial Intelligence Lab, takes into account a variety of social factors to score your potential post on a scale of 1-10. Said Khosla in nerdspeak to The Verge:
It actually represents how many views are expected on your image per day, on average, but in a log scale. What this means: if the score is 5, we expect roughly 2^5 = 32 views on your image per day, or if its 6, roughly 2^6 = 64. However, this metric is not entirely accurate, and the most important thing is the relative score i.e. if A has score higher than B, it’s likely to receive more views.
Pipeline improvements include developing a tool that will automatically adjust images in order to make them more popular, thus taking Instagram even further from the base art of photography and making Internet fame even less prestigious. Slap on a Mayfair filter, and you’re all set up for virility.
