On the bottom of CBC Lite story pages users will see a “More Stories Like This” feature which may display some other recent articles related to the story just read.
Whenever a new article is published within CBC an algorithm will get word counts on that article and we use those word counts to find other articles with similar words, the theory being that the more two articles share words, the more likely they are to be related in content.
Unfortunately, with the size and scale of these articles it would quickly become quite computationally expensive to compare every article to every other article. Luckily there are some optimizations that can be made to approximate this similarity at the benefit of being able to make these calculations very quickly and efficiently. Specifically, the minhash algorithm is used, which groups like content together to be presented to the user.
For those curious, you can read more here on the minhash algorithm.