Abstract: Technology for media item and user language classification is disclosed. Media item classification may use models for associating language identifiers or probability distributions for multiple languages with linguistic content. User language classification may define user language models for attributing to users indications of languages they speak read, and/or write. The text classifications and user classifications may interact because the probability that given text is in a particular language may depend on a determined likelihood the user who produced the text speaks that language, or conversely, a user interacting with text in a particular language may increase the likelihood they understand that language. Some embodiments use language-tagged social media content to train n-gram classifiers for use with other social media content.

Abstract: A system identifies unconnected content items of high quality and provides the unconnected content items for display to a user. The method comprises receiving several content items posted on pages of a social networking system. The system then determines a subset of those content items (e.g., high quality content items). A topic is then extracted from each of the subset of content items. The topic is mapped to one or more related pages of the social networking system that represent an expanded set of pages associated with the content item. For each of the related pages, a user is identified who is connected to the related page. Finally, the content item (e.g., a high quality content item) is provided to the user for display in the user's newsfeed.

Abstract: Technology for media item and user language classification is disclosed. Media item classification may use models for associating language identifiers or probability distributions for multiple languages with linguistic content. User language classification may define user language models for attributing to users indications of languages they speak read, and/or write. The text classifications and user classifications may interact because the probability that given text is in a particular language may depend on a determined likelihood the user who produced the text speaks that language, or conversely, a user interacting with text in a particular language may increase the likelihood they understand that language. Some embodiments use language-tagged social media content to train n-gram classifiers for use with other social media content.

Abstract: A social networking system selects a set of groups for presentation to a user of the social networking system. To select groups, the social networking system determines scores for various groups representing a likelihood of the user interacting with the groups. The social networking system may identify a set of groups based on interactions between the user and various groups occurring during a specific time interval and determine scores for groups in the set. When determining a score for a group, the social networking system accounts for times associated with interactions between the user and various groups. Based on the scores, one or more groups are selected and presented to the user. Additionally, the social networking system may identify a time to present the selected one or more groups to the user based on prior user interactions with various groups.

Abstract: A social networking system selects a set of groups for presentation to a user of the social networking system. To select groups, the social networking system determines scores for various groups representing a likelihood of the user interacting with the groups. The social networking system may identify a set of groups based on interactions between the user and various groups occurring during a specific time interval and determine scores for groups in the set. When determining a score for a group, the social networking system accounts for times associated with interactions between the user and various groups. Based on the scores, one or more groups are selected and presented to the user. Additionally, the social networking system may identify a time to present the selected one or more groups to the user based on prior user interactions with various groups.

Abstract: Technology for media item and user language classification is disclosed. Media item classification may use models for associating language identifiers or probability distributions for multiple languages with linguistic content. User language classification may define user language models for attributing to users indications of languages they speak read, and/or write. The text classifications and user classifications may interact because the probability that given text is in a particular language may depend on a determined likelihood the user who produced the text speaks that language, or conversely, a user interacting with text in a particular language may increase the likelihood they understand that language. Some embodiments use language-tagged social media content to train n-gram classifiers for use with other social media content.

Abstract: A social networking system selects a set of groups for presentation to a user of the social networking system. To select groups, the social networking system determining scores for various groups representing a likelihood of the user interacting with the groups. When determining a score for a group, the social networking system accounts for a likelihood of the user providing content to the group as well as the user accessing or viewing content associated with the group. Based on the scores, one or more groups are selected and presented to the user. Additionally, the social networking system may apply one or more diversity rules so that the selected groups have a variety of characteristics.

Abstract: The social networking system monitors implicit interactions between a user and objects of the social networking system with which the user has not established a connection. Based on the implicit interactions between the user and an object, the social networking system identifies a soft connection between the user and the object. The social networking system may then identify soft connections to include in a candidate list of soft connections to recommend to the user. The social networking system may also extract signals from the set of candidate list of soft connections, and may use the extracted signals to rank the soft connections in the list of candidate soft connections. The social networking system may then recommend soft connections to the user based on the rank associated with the soft connections in the candidate list of soft connections.

Abstract: A system identifies unconnected content items of high quality and provides the unconnected content items for display to a user. The method comprises receiving several content items posted on pages of a social networking system. The system then determines a subset of those content items (e.g., high quality content items). A topic is then extracted from each of the subset of content items. The topic is mapped to one or more related pages of the social networking system that represent an expanded set of pages associated with the content item. For each of the related pages, a user is identified who is connected to the related page. Finally, the content item (e.g., a high quality content item) is provided to the user for display in the user's newsfeed.

Abstract: Systems, methods, and non-transitory computer readable media configured to determine whether a candidate content item may be presented in response to an indication of approval by a user regarding a seed content item according to a first technique. It is determined whether the seed content item may be presented in response to an indication of approval by the user regarding the candidate content item according to a second technique. Features, including a reciprocity feature based on the determining whether a candidate item may be presented and the determining whether the seed content item may be presented, are processed to generate a probability that the user will interact with the candidate content item.

Abstract: Systems, methods, and non-transitory computer-readable media can determine a content item to be promoted to one or more users of the social networking system. At least one seed content item in the social networking system that is similar to the content item to be promoted can be determined. A set of interests can be determined based at least in part on the at least one seed content item. One or more interests in the set can be determined as suggestions for promoting the content item to users, wherein promoting the content item using a first interest causes the content item to be presented to users of the social networking system that are associated with the first interest.

Abstract: Systems, methods, and non-transitory computer-readable media can determine a profile model for a page that is accessible through the social networking system, the profile model describing one or more modal characteristics of users of the social networking system that have fanned the page. A determination can be made that the page should be recommended to a first user of the social networking system based at least in part on the profile model. At least one page recommendation that references the page can be provided to the first user.

Abstract: An online system, such as a social networking system, recommends pages of content to users. The recommendation is presented in a recommendation unit presenting one or more representations of pages to a user. Additionally, the user may interact with the recommendation unit to change representations of pages presented by the recommendation unit. A representation of a page presented by the recommendation unit includes content from one or more content items on the page selected based on interaction with the content items on the page and types of content included in content items on the page (e.g., image data, video data, destination address). Representations of different pages may differ based on the types of content included in content items selected from the different pages.

Abstract: Systems, methods, and non-transitory computer-readable media can determine a plurality of candidate entities for recommendation to a user of a social networking system. A predicted activity objective value model configured to calculate activity stores for candidate entities is established. The activity score is indicative of the probability of future activity on the social networking system by a candidate entity. A first activity score is determined for each of the plurality of candidate entities based on the predicted activity object value model and a first set of feature values. A second activity score is determined for each of the plurality of candidate entities based on the predicted activity object value model and a second set of feature values that is different from the first set of feature values. A first entity is selected of the plurality of candidate entities based on the first and second activity scores.

Abstract: Systems, methods, and non-transitory computer-readable media can determine respective rates at which one or more types of content items were presented to users of the social networking system over a period of time. Each content item can be associated with a respective bid. Further, content items are presented through impression opportunities based at least in part on a real-time bidding auction. A determination is made that the respective rates measured over the period of time are inconsistent with a specified mix of the types of content items to be presented. The respective bids associated with content items of at least a first type are adjusted by a corresponding bid weight, wherein the bids are adjusted to enforce the specified mix.

Abstract: Systems, methods, and non-transitory computer-readable media can determine respective geographic locations of a set of users associated with a page that is accessible through a social network. At least one centroid for the page can be generated based at least in part on the respective geographic locations of the set of users. At least one area of influence of the page can be determined based at least in part on the centroid.

Abstract: Systems, methods, and non-transitory computer-readable media can determine a respective embedding for each entity in a set of entities that are accessible through the social networking system, wherein each embedding is learned based at least in part on one or more sessions of connections formed between users and entities of the social networking system. One or more candidate entities that are related to a first entity can be determined based at least in part on the respective embeddings for the candidate entities and the first entity. At least a first candidate entity from the one or more candidate entities can be provided as a recommendation to a user that formed a connection with the first entity.

Abstract: Systems, methods, and non-transitory computer-readable media can determine at least one web site that is of interest to a user of the social networking system. One or more pages can be determined based at least in part on the web site, the one or more pages being accessible through the social networking system. At least one page recommendation that references at least one of the one or more pages can be provided to the user.

Abstract: A social networking system recommends objects, such as pages, of the social networking system to users of the social networking system based on the location of the user. The social networking system obtains location information identifying the location of the user. Based on the location of the user, the social networking system identifies levels of geographical partitions encompassing the location of the user. For each level of geographical partitions, the social networking system accesses relevant objects of the social networking system with connections to users located within the level of geographical partitions. The social networking system may have determined a term frequency-inverse document frequency (tf-idf) value for each relevant object. Based on the number of connections and the tf-idf value associated with each relevant object, the social networking system merges the relevant objects accessed at each level into a set of relevant objects to recommend to the user.

Abstract: A social networking system selects a set of groups for presentation to a user of the social networking system. To select groups, the social networking system determining scores for various groups representing a likelihood of the user interacting with the groups. When determining a score for a group, the social networking system accounts for a likelihood of the user providing content to the group as well as the user accessing or viewing content associated with the group. Based on the scores, one or more groups are selected and presented to the user. Additionally, the social networking system may apply one or more diversity rules so that the selected groups have a variety of characteristics.