Abstract: Exemplary embodiments relate to techniques for notifying existing users when a new user joins a messaging service (or returns from a period of inactivity). A top n number of existing users acquainted with the new user may be selected and may be encouraged to message the new user. The existing users may be selected using a messaging coefficient that indicates a likelihood that a message will result in a meaningful conversation, and a number of other factors that prevent the existing users from becoming inundated with notifications. The number n may be selected based on an amount of display space available to the new user in a messaging application. When inviting the existing users to contact the new user, a new thread may be automatically created and bumped to the top of the new user's thread list.

Abstract: Exemplary embodiments relate to techniques for notifying existing users when a new user joins a messaging service (or returns from a period of inactivity). A top n number of existing users acquainted with the new user may be selected and may be encouraged to message the new user. The existing users may be selected using a messaging coefficient that indicates a likelihood that a message will result in a meaningful conversation, and a number of other factors that prevent the existing users from becoming inundated with notifications. The number n may be selected based on an amount of display space available to the new user in a messaging application. When inviting the existing users to contact the new user, a new thread may be automatically created and bumped to the top of the new user's thread list.

Abstract: Exemplary embodiments relate to techniques for presenting and targeting media in communications services. Media, such as live events, updates on a topic of interest, or digests of news sites or other content providers may be surfaced to a user in a number of ways; for example, an article view relating to the topic, a messaging view showing message threads, a media view showing interesting pieces of media, or in an active conversation based on analysis of a conversation and trending topics, such as news events. A system may suggest recipients that may be interested in discussing the content. The recipients may be presented in a ranked order based, for example, on an affinity or relationship of the recipients to a publisher of the content. Publishers may add or remove topics, and may set an end-time at which updates cease. The updates may be presented in a messaging thread.

Abstract: Exemplary embodiments relate to techniques for notifying existing users when a new user joins a messaging service (or returns from a period of inactivity). A top n number of existing users acquainted with the new user may be selected and may be encouraged to message the new user. The existing users may be selected using a messaging coefficient that indicates a likelihood that a message will result in a meaningful conversation, and a number of other factors that prevent the existing users from becoming inundated with notifications. The number n may be selected based on an amount of display space available to the new user in a messaging application. When inviting the existing users to contact the new user, a new thread may be automatically created and bumped to the top of the new user's thread list.

Abstract: Systems, methods, and non-transitory computer-readable media according to certain aspects can receive at least one message sent by a user of a social networking system to a page provided by the social networking system, where the page is associated with an entity. A training data set including a plurality of messages can be determined, and the training data set can indicate an intent classification for each of the plurality of messages. The intent classification can be indicative of an intent associated with a particular message. A machine learning model may be trained based at least in part on the training data set. A first intent classification for the at least one message can be determined, based at least in part on the machine learning model.