Abstract: Systems, methods, and non-transitory computer-readable media can receive an indication that a user of a social networking system has interacted with a first media content item on the social networking system. A set of potential media content items is compiled based on media content item similarity criteria indicative of a similarity of each potential media content item to the first media content item. The set of potential media content items is ranked based on ranking criteria, and filtered based on filtering criteria. One or more similar media content item recommendations are presented to the user via a graphical user interface, the one or more similar media content item recommendations based on the ranking and the filtering.

Abstract: Systems, methods, and non-transitory computer-readable media can receive an indication that a user of a social networking system has interacted with a first account of the social networking system. A set of potential accounts is compiled based on account similarity criteria indicative of a similarity of each potential account to the first account. The set of potential accounts is ranked based on a machine learning model, and filtered based on filtering criteria. One or more similar account recommendations are presented to the user via a graphical user interface, the one or more similar account recommendations based on the ranking and the filtering.