Abstract:
In one embodiment, a computing system may access a plurality of content items shared by a plurality of first users on an online social network. The computing system may calculate a content score for each of content items shared by a first user on the online social network, where each content score is based at least in part on a proximity coefficient between a second user and the first user that shared the content item, where the proximity coefficient is a weighted combination of multiple subpart proximity coefficients over a period of time. The computing system may send, to a client device of the second user for display, one or more of the content items based at least in part on the calculated content scores.
Abstract:
In one embodiment, a computing system may access an image associated with an online social network, where the image portrays at least a first person. The computing system may determine, for each user in a first set of users, a facial recognition score with respect to the first person portrayed in the image, where the facial recognition score is based on a facial representation associated with each user of the first set of users, where the facial representation associated with each user is compared with the image, and a comparison of a location history of each user with a location associated with the image. The computing system may generate one or more tag suggestions for the first person portrayed in the image based on the determined facial recognition scores.
Abstract:
In one embodiment, a mobile-client system may store location history data during a first time period in its memory, where the location history data comprises a plurality of geographic locations during the first time period and one or more time stamps corresponding to each of the geographic locations. The mobile-client system may detect whether it has a current network connection to an online social network. The mobile-client system may determine whether to transmit the stored location history data to a location server of the online social network, where if it is currently connected to the online social network, then the mobile-client system transmits the location history data to a location server using the current network connection, and if it is not currently connected to the online social network, then the mobile-client system refrains from transmitting the location history data to the location server.
Abstract:
In one embodiment, a mobile client system may determine its location. The mobile client system may store the location in a location history in a memory of the mobile client system, where the location history comprises one or more geographic locations and one or more time stamps corresponding to each of the geographic locations. The mobile client system may detect its current status based at least in part on whether the mobile client system is stationary. The mobile client system may send the location history to a location server of an online social network based at least in part on the current status of the mobile client system and a power requirement for sending the location history to the location server.
Abstract:
User profile information for a user of a social networking system is inferred based on information about user profile of the user's connections in the social networking system. The inferred user profile attributes may include age, gender, education, affiliations, location, and the like. To infer a value of a user profile attribute, the system may determine an aggregate value based on the attributes of the user's connections. A confidence score may also be associated with the inferred attribute value. The set of connections analyzed to infer a user profile attribute may depend on the attribute, the types of connections, and the interactions between the user and the connections. The inferred attribute values may be used to update the user's profile and to determine information relevant to the user to be presented to the user (e.g., targeting advertisements to the user based on the user's inferred attributes).