Abstract: Systems, methods, and non-transitory computer readable media configured to determine a value associated with at least one signal indicative of objectionable material in a content item. The value associated with the at least one signal indicative of objectionable material can be compared with a threshold value associated with the at least one signal. A demotion value can be determined in response to satisfaction of the threshold value associated with the at least one signal.

Abstract: Systems, methods, and non-transitory computer readable media configured to determine a value associated with at least one signal indicative of objectionable material in a content item. The value associated with the at least one signal indicative of objectionable material can be compared with a threshold value associated with the at least one signal. A demotion value can be determined in response to satisfaction of the threshold value associated with the at least one signal.

Abstract: Systems, methods, and non-transitory computer-readable media can train a model to define relatedness ratings for a plurality of terms. A posted content item and a comment to the posted content item are received. A relevance rating for the comment and the posted content item is determined based on the model. The comment is ranked among a plurality of comments based on the relevance rating.

Abstract: Systems, methods, and non-transitory computer-readable media can generate a set of clusters using sample content items in which a set of user features are represented, the sample content items being clustered based at least in part on their similarity to one another; obtain one or more content items that capture a set of user features corresponding to a given user; determine that the user corresponds to a given cluster in the set of clusters based at least in part on the features of the user; and assign an avatar associated with the cluster to the user.

Abstract: In one embodiment, a method includes retrieving comments associated with a content object on a social-networking system, determining a score for each of the comments, where the score is based on one or more signals associated with the comment, the signals are related to one or more audience interactions with the comment, and each of the audience interactions includes an interaction by a respective audience member with the comment. The method further includes ordering the comments based on the respective scores, and presenting the ordered comments to a target user. Each of the audience interactions may include one or more responses to the audience interaction by an author of the comment. The signals may be based on existence of an edge between a user node representing the audience member and a user node representing an author of the comment in a social graph on the social-networking system.

Abstract: Systems, methods, and non-transitory computer-readable media can receive a comment to a posted content item. One or more user interactions with the comment are received. An interaction-to-impression ratio for the comment is determined. The comment is ranked among a plurality of comments based on the interaction-to-impression ratio.

Abstract: Systems, methods, and non-transitory computer readable media configured to determine a value associated with at least one signal indicative of objectionable material in a content item. The value associated with the at least one signal indicative of objectionable material can be compared with a threshold value associated with the at least one signal. A demotion value can be determined in response to satisfaction of the threshold value associated with the at least one signal.

Abstract: A social networking system classifies content items according to their qualities for ranking and selection of content items to present to users within, for example, a newsfeed. Low-quality content items that are unlikely to be interesting or relevant to a user may be distinguished though they may appear to be popular among users in the social networking system. The social networking system identifies within the content items one or more features that are indicators of the quality of the content items. The social networking system can use one or more classifiers to evaluate the content items based on the features, and it can compute a quality metric indicating the quality of a content item based on the result obtained from the classifiers. The quality metric can be used in the ranking and selection of a set of content items to provide to the user.

Abstract: A controller including a temperature feedback mechanism is coupled to a client device. The temperature feedback mechanism is configured to be heated or cooled based on instructions received from the client device and contacts a portion of a user's body. In various embodiments, the temperature feedback mechanism is a Peltier device integrated into the controller. Various applications executing on the client device may implement instructions that, when executed by the client device, heat or cool the controller coupled to the client device to augment other content presented by an application.

Abstract: Systems, methods, and non-transitory computer readable media configured to determine a value associated with at least one signal indicative of objectionable material in a content item. The value associated with the at least one signal indicative of objectionable material can be compared with a threshold value associated with the at least one signal. A demotion value can be determined in response to satisfaction of the threshold value associated with the at least one signal.

Abstract: In one embodiment, a method includes retrieving a plurality of comments associated with a content object on a social-networking system, determining a score for each of the comments, wherein the score is based on one or more signals associated with the comment, and where the signals are related to the identity of an author of the comment or content of the comment, ordering the comments based on the respective scores, and presenting one or more of the ordered comments to a target user. The method may further include excluding one or more of the comments based on a filtering condition. One of the signals may be based on how many times the comment has been (a) liked, (b) hidden, (c) marked as spam, or (d) replied to within a specified period of time. One of the signals may be based on a reputation of the author of the comment.

Abstract: A controller including a temperature feedback mechanism is coupled to a client device. The temperature feedback mechanism is configured to be heated or cooled based on instructions received from the client device and contacts a portion of a user's body. In various embodiments, the temperature feedback mechanism is a Peltier device integrated into the controller. Various applications executing on the client device may implement instructions that, when executed by the client device, heat or cool the controller coupled to the client device to augment other content presented by an application.

Abstract: Some embodiments include a method of detecting and analyzing virally propagating subject matter in a social networking system. The method includes processing user activities in the social networking system through a relevancy filter to identify a subset of user activities that are relevant to a viral propagation study. The social networking system can construct, in response to selecting a user activity as a graph exploration seed, a user activity cascade by exploring the social graph in the social networking system, starting from a social network node corresponding to the user activity. The user activity cascade can comprise social network nodes found during the graph exploration. The social networking system can determine that the user activity cascade is virally propagating based at least upon a total size of the user activity cascade.

Abstract: Systems, methods, and non-transitory computer-readable media can generate a set of clusters using sample content items in which a set of user features are represented, the sample content items being clustered based at least in part on their similarity to one another; obtain one or more content items that capture a set of user features corresponding to a given user; determine that the user corresponds to a given cluster in the set of clusters based at least in part on the features of the user; and assign an avatar associated with the cluster to the user.

Abstract: A social networking system generates stories based on actions of users in the system and provides a newsfeed to users that contain stories that related to one or more of their friends in the system. Although the story ranking algorithm includes a time decay to penalize older stories, stories may actually become stale at different rates. To measure the staleness of a story, the system computes a ratio of a current engagement rate for the story to an average engagement rate for the story. Based on this ratio, the system may filter out stale stories, includes the ratio as a feature in the scoring model, and/or adjust the decay rate.

Abstract: In one embodiment, a method includes retrieving a plurality of comments associated with a content object, determining a score for each of the comments, where the score is based on one or more signals associated with the comment, and where the score is further based on a qualitative analysis of each of one or more impressions related to the comment, and wherein each of the impressions comprises an interaction by a historical user with the comment, ordering the comments based on the respective scores, presenting one or more of the ordered comments to a target user. The qualitative analysis may determine a category of interaction for the impression, the score may be based at least in part on the category of interaction, and the category of interaction may include user input related to the comment, such as a reply to the comment.

Abstract: A social networking system classifies content items according to their qualities for ranking and selection of content items to present to users within, for example, a newsfeed. Low-quality content items that are unlikely to be interesting or relevant to a user may be distinguished though they may appear to be popular among users in the social networking system. The social networking system identifies within the content items one or more features that are indicators of the quality of the content items. The social networking system can use one or more classifiers to evaluate the content items based on the features, and it can compute a quality metric indicating the quality of a content item based on the result obtained from the classifiers. The quality metric can be used in the ranking and selection of a set of content items to provide to the user.

Abstract: Systems, methods, and non-transitory computer-readable media can receive a plurality of comments to a posted content item. Each of the plurality of comments is associated with at least one category of a plurality of categories based on a machine learning model. A first comment of the plurality of comments is selected for inclusion in a comment sample to be presented in a graphical user interface based on the first comment being associated with a first category of the plurality of categories. A second comment of the plurality of comments is selected for inclusion in the comment sample based on the second comment being associated with a second category of the plurality of categories.

Abstract: Systems, methods, and non-transitory computer-readable media can receive a comment to a posted content item. One or more user interactions with the comment are received. An interaction-to-impression ratio for the comment is determined. The comment is ranked among a plurality of comments based on the interaction-to-impression ratio.

Abstract: In one embodiment, a method includes retrieving a plurality of comments associated with a content object on a social-networking system, determining a score for each of the comments, wherein the score is based on one or more signals associated with the comment, and where the signals are related to the identity of an author of the comment or content of the comment, ordering the comments based on the respective scores, and presenting one or more of the ordered comments to a target user. The method may further include excluding one or more of the comments based on a filtering condition. One of the signals may be based on how many times the comment has been (a) liked, (b) hidden, (c) marked as spam, or (d) replied to within a specified period of time. One of the signals may be based on a reputation of the author of the comment.