Abstract:
The present disclosure describes techniques for configuring a call-to-action (CTA) interface for a particular user of a social networking system (SNS) by emphasizing an option included with the CTA interface based on a machine learning system. The machine learning system may be used to determine to emphasize a first user-selectable option instead of a second user-selectable option (sometimes referred to as an emphasization determination). The emphasization determination may indicate a prediction of an intent of a user to select the first user-selectable option (e.g., an intent for the user to register an account with the SNS or to login to an account of the SNS). Based on the emphasization determination, an interface (e.g., a graphical user interface) may be configured to emphasize the first user-selectable option, and the interface may be sent to a user device for presentation to the user.
Abstract:
The present disclosure relates generally to taxonomies. More particularly, techniques are described for receiving a taxonomy as input, automatically generating data structures representing the taxonomy, determining content that is relevant to different concepts of the taxonomy, and generating an interface that enables users to access and navigate through the taxonomy-related content. The taxonomy specification may specify a taxonomy for a domain including various concepts related to the domain and hierarchical relationships between the concepts. Based on the taxonomy specification, a taxonomy structure may be generated for the taxonomy, the taxonomy structure including multiple taxonomy nodes corresponding to the multiple concepts. Content stored by a social networking system (SNS) may be searched to identify content relevant to each taxonomy node. Using relevant content identified, multiple web pages may be built with for the multiple taxonomy nodes in the taxonomy structure.
Abstract:
Techniques to optimize messages sent to a user of a social networking system. In one embodiment, information about the user may be collected by the social networking system. The information may be applied to train a model for determining likelihood of a desired action by the user in response to candidate messages that may be provided for the user. The social networking system may provide to the user a message from the candidate messages with a selected likelihood of causing the desired action.
Abstract:
Techniques to optimize messages sent to a user of a social networking system. In one embodiment, information about the user may be collected by the social networking system. The information may be applied to train a model for determining likelihood of a desired action by the user in response to candidate messages that may be provided for the user. The social networking system may provide to the user a message from the candidate messages with a selected likelihood of causing the desired action.
Abstract:
Techniques to optimize messages sent to a user of a social networking system. In one embodiment, information about the user may be collected by the social networking system. The information may be applied to train a model for determining likelihood of a desired action by the user in response to candidate messages that may be provided for the user. The social networking system may provide to the user a message from the candidate messages with a selected likelihood of causing the desired action.
Abstract:
In one embodiment, a method includes receiving a search query from a user of an online social network and searching multiple verticals to identify multiple sets of objects in each vertical, respectively, that match the search query, and wherein each vertical stores one or more objects associated with the online social network. The method also includes ranking, for each set of identified objects from a vertical, each identified object in the set of identified objects. The method further includes blending the multiple sets of identified objects from each vertical to form a set of blended search results that includes a threshold number of identified objects, the blending including an iterative process performed at least the threshold number of iterations. Each iteration of the iterative blending process includes determining a blender score for each top-ranked identified object in each set of identified objects.