Not a huge amount of detail was handed over by Instagram in the writing of this article, but I did 
glean one thing;
Instagram identifies accounts that are similar to one another by adapting a common machine learning method known as “word embedding.” Word embedding systems study the order in which words appear in text to measure how related they are. Instagram uses a similar process to determine how related any two accounts are to one another. If it thinks this is similar to an account you’ve already liked, they’ll recommend it to you.
There are no details on what signals are used to identify spam or misinformation. The algorthim details are not revealed. So whilst algorithms are playing an increasingly important role in producing content and mediating the relationships between us and other internet products, precisely how they do that is not made clear to us,
“Such conclusions have led a number of commentators to argue that we are now entering an era of widespread algorithmic governance, wherein algorithms will play an ever-increasing role in the exercise of power, a means through which to automate the disciplining and controlling of societies and to increase the efficiency of capital accumulation.” Kitchin 2017
Reference
Kitchin, R. (2017) Thinking critically about and researching algorithms, Information, Communication & Society, 20:1, 14-29, DOI: 10.1080/1369118X.2016.1154087