May 18, 2012
When a new user joined Twitter’s microblogging service they are given a set of recommendations that are fairly similar to everyone else’s recommendations, that’s because Twitter has no way of knowing your interests to make better recommendations. Now Twitter is testing a new feature in some countries that dives into your browser history and makes recommendations accordingly.
In a blog post on Thursday Othman Laraki, Twitter’s director of growth and international business wrote:
“After all, even though millions of people love Justin Bieber, FC Barcelona or Kim Kardashian, not everyone using Twitter may want to follow them.”
Twitter buttons and widgets are located on millions of sites which means the company will be able to use data collected from their own pieces of already installed technology to gather information for the recommendation engine.
As Laraki explains:
“By recognizing which accounts are frequently followed by people who visit popular sites, we can recommend those accounts to others who have visited those sites within the last ten days.” read more