Abstract: In one embodiment, a method includes sending, from an application server to a first set of client systems, instructions for providing a treatment to a first set of users. The method includes determining an average treatment effect of the treatment for the first set of users based on information about user interactions associated with the treatment and a network exposure to the treatment for each user. Network exposure for a user is a measure of other users associated with the user that have been provided the treatment. The method includes modifying the treatment based on the determined average treatment effect. The method includes sending, to a second set of client systems, instructions for providing the modified treatment to a second set of users. The second set of users is a discrete, non-overlapping set of users with respect to the first set.

Abstract: Systems, methods, and non-transitory computer-readable media can generate a set of candidate content items from a plurality of content items that are available in the social networking system for a first user. A corresponding score for each of the candidate content items can be generated based at least in part on one or more social affinity coefficients corresponding to the first user and a respective second user associated with a candidate content item, wherein a social affinity coefficient provides a quantitative measurement of the strength of a relationship between two users. A first set of content items from the set of candidate content items can be determined based at least in part on the respective scores, wherein content items in the first set are included in a content feed provided to the first user.

Abstract: In one embodiment, a method includes accessing a social graph comprising a plurality of nodes and a plurality of edges connecting the nodes, each node corresponding to a user of an online social network, identifying a plurality of clusters in the social graph using graph clustering, providing a treatment to a first set of users based on the clusters, and determining a treatment effect treatment for the users in the first set based on a network exposure to the treatment for each user.

Abstract: To suggest new connections to a user of a social networking system, the system generates a set of candidate users to whom the user has not already formed a connection. The system determines the likelihood that the user will connect to each candidate user if suggested to do so, and it also computes the value to the social networking system if the user does connect to the candidate user. Then, the system computes an expected value score for each candidate user based on the corresponding likelihood and the value. The candidate users are ranked and the suggestions are provided to the user based on the candidate users' expected value scores. The social networking system can suggest other actions to a user in addition to forming a new connection with other users.

Abstract: In one embodiment, a computing device receives an indication of a first user action by a first user. The computing device determines a topic of the first user action based on analyzing content associated with the first user action, and determines whether the first user has a preference to exclude posts associated with the topic or a category associated with the topic. If the first user has not indicated any preference to exclude posts associated with the topic or the category, then the computing device identifies a second user action by a second user and related to the topic, and determines whether the first user has indicated a preference to exclude posts associated with the second user. If the first user has not indicated any preference to exclude posts associated with the second user, the first user is provided with access to the second user action.

Abstract: A mobile device receives ranked news feed stories from a server of a social networking system. The mobile device determines whether to adjust the ranking based on local information generated by applications executing on the mobile device or hardware of the mobile device. Examples of local information of the mobile device include information describing the mobile devices' network connection, geographical location, sensor readings, downloaded data on memory storage, and interactions of software applications executing on the mobile device. For example, if a network co-processor of a mobile device detects a slow network connection, the mobile device lowers the ranking of news feed stories expected to require further use of network bandwidth.

Abstract: A system transmits selected news feed stories to a client device in advance of receiving a request for news feed stories. As a result, stories are immediately available for viewing when a user interacts with the system. The system selects news feed stories to push based on criteria such as a likelihood that a user will interact with a story and the sizes of pushed stories. For example, the system selects news feed stories such that a total size of stories selected does not exceed a threshold value based on local memory at the client device. The system may determine a scheduled time at which the stories are selected and pushed. The scheduled time is based on factors including patterns of network connection speed or past user interactions, for example, a time range of the day during which the user most frequently viewed pushed stories.

Abstract: A social networking system builds a quality controlled and desired population-representative pool of human raters to provide ratings on content items to improve a feed ranking model used for providing its users with more relevant content. The system identifies a pool of candidate human raters for providing ratings on a feed of content items. For each candidate human rater of the pool of candidate human raters, the system presents a feed of content items based on a feed ranking model, obtains ratings on the feed of content items, and determines a score representing the consistency of the obtained ratings, the representativeness of the pool of human raters, or the relevance of the content provided by the ranking model. The system uses the computed scores to modify the ranking model used to present content to its users for improving the relevance of the presented content.

Abstract: A social networking system builds a quality controlled and desired population-representative pool of human raters to provide ratings on content items to improve a feed ranking model used for providing its users with more relevant content. The system identifies a pool of candidate human raters for providing ratings on a feed of content items. For each candidate human rater of the pool of candidate human raters, the system presents a feed of content items based on a feed ranking model, obtains ratings on the feed of content items, and determines a score representing the consistency of the obtained ratings, the representativeness of the pool of human raters, or the relevance of the content provided by the ranking model. The system uses the computed scores to modify the ranking model used to present content to its users for improving the relevance of the presented content.

Abstract: A social networking system builds a quality controlled and desired population-representative pool of human raters to provide ratings on content items to improve a feed ranking model used for providing its users with more relevant content. The system identifies a pool of candidate human raters for providing ratings on a feed of content items. For each candidate human rater of the pool of candidate human raters, the system presents a feed of content items based on a feed ranking model, obtains ratings on the feed of content items, and determines a score representing the consistency of the obtained ratings, the representativeness of the pool of human raters, or the relevance of the content provided by the ranking model. The system uses the computed scores to modify the ranking model used to present content to its users for improving the relevance of the presented content.

Abstract: In one embodiment, a computing device receives an indication of a first user action by a first user. The computing device determines a topic of the first user action based on analyzing content associated with the first user action, and determines whether the first user has a preference to exclude posts associated with the topic or a category associated with the topic. If the first user has not indicated any preference to exclude posts associated with the topic or the category, then the computing device identifies a second user action by a second user and related to the topic, and determines whether the first user has indicated a preference to exclude posts associated with the second user. If the first user has not indicated any preference to exclude posts associated with the second user, the first user is provided with access to the second user action.

Abstract: A social networking system selects and presents content items to a user via a feed. Additionally, the social networking system predicts heights associated with various content items, such as content items selected for presentation via the feed. Characteristics of a content item (e.g., a type of content included in the content item, a language of the content item, and a number of comments associated with the content item) as well as characteristics of a client device associated with the user are used to predict a height associated with the content item. When selecting content items for presentation to the user, the social networking system accounts for the predicted heights of various content items to increase the likelihood of the user interacting with content items presented via the feed.

Abstract: A social networking system selects and presents content items to a user via a feed. Additionally, the social networking system predicts heights associated with various content items, such as content items selected for presentation via the feed. Characteristics of a content item (e.g., a type of content included in the content item, a language of the content item, and a number of comments associated with the content item) as well as characteristics of a client device associated with the user are used to predict a height associated with the content item. When selecting content items for presentation to the user, the social networking system accounts for the predicted heights of various content items when ordering the content items in the news feed.

Abstract: In one embodiment, a computing device receives an indication of a first user action by a first user. The computing device determines a topic of the first user action based on analyzing content associated with the first user action, and determines whether the first user has a preference to exclude posts associated with the topic or a category associated with the topic. If the first user has not indicated any preference to exclude posts associated with the topic or the category, then the computing device identifies a second user action by a second user and related to the topic, and determines whether the first user has indicated a preference to exclude posts associated with the second user. If the first user has not indicated any preference to exclude posts associated with the second user, a reference associated with the second user action is sent to the first user.

Abstract: Systems, methods, and non-transitory computer readable media configured to create objects associated with links to content items shared within a social networking system, the content items from content sources. Content sources having pages on the social networking system fanned by a user are determined. Objects associated with (links to) content items from the content sources having content source representations, such as pages, on the social networking system fanned by the user are collected. An aggregate score for a collected object associated with a link is determined based on popularity of a content item associated with the link within the social networking system and interest of the user in the content item. The collected object associated with the link is provided to be ranked for potential presentation of the link to the user based on satisfaction of a threshold.

Abstract: A social networking system generates a newsfeed for a user to view when accessing the social networking system. Candidate stories associated with users of the social networking system are selected and an expected value score for each candidate story is determined. An expected value score is based on the probability of a user performing various types of interactions with a candidate story and a numerical value for each type of interaction. The numerical value for a type of interaction represents a value to the social networking system of the type of interaction. Based on the expected value scores, the candidate stories are ranked and the ranking used to select candidate stories for the newsfeed.

Abstract: A social networking system generates a newsfeed for a user to view when accessing the social networking system. Candidate stories associated with users of the social networking system are selected and an expected value score for each candidate story is determined. An expected value score is based on the probability of a user performing various types of interactions with a candidate story and a numerical value for each type of interaction. The numerical value for a type of interaction represents a value to the social networking system of the type of interaction. Based on the expected value scores, the candidate stories are ranked and the ranking used to select candidate stories for the newsfeed.

Abstract: A social networking system generates a newsfeed for a user to view when accessing the social networking system. Candidate stories associated with users of the social networking system are selected and attributes of each story are determined. The candidate stories are ranked so that the ranking of a candidate story having one or more common attributes with another candidate story is modified. This reduces the likelihood of the newsfeed presenting candidate stories with common attributes proximate to each other.

Abstract: In one embodiment, a method includes accessing a social graph comprising a plurality of nodes and a plurality of edges connecting the nodes, each node corresponding to a user of an online social network, identifying a plurality of clusters in the social graph using graph clustering, providing a treatment to a first set of users based on the clusters, and determining a treatment effect treatment for the users in the first set based on a network exposure to the treatment for each user.

Abstract: In one embodiment, a method includes accessing a social graph comprising a plurality of nodes and a plurality of edges connecting the nodes, each node corresponding to a user of an online social network, identifying a plurality of clusters in the social graph using graph clustering, providing a treatment to a first set of users based on the clusters, and determining a treatment effect treatment for the users in the first set based on a network exposure to the treatment for each user.