Abstract: An online system generates a feed of content items for a user subject to a limitation restricting the number of content items including video data (“video content items”) included in the feed. If the user interacts with a video content item the feed, the online system selects candidate video content items based on characteristics of the video content item in the feed and characteristics of the user. The online system determines likelihoods of the user interacting with various candidate video content items and selects candidate video content items based on the determined likelihoods. To present the user with additional video content items, the online system generates an interface including the selected candidate video content items and presents the interface to the user. The interface may be presented in place of the feed or may be presented as within the feed and presents different video content items based on user interactions.

Abstract: An online system customizes video conversations between users of the online system by providing graphics that are likely to interest the users. The online system may present composite views overlaying selected graphics on a video stream, which may be part of an augmented reality (AR) environment. The graphics include, for example, background graphics, masks, props, visual or particular effects, frames or borders, etc. The online system may use a machine learning model to predict whether a user is likely to select or interact with a particular graphic. The online system can also filter or rank graphics according to user affinities or user connections on the online system. Users may be encouraged to interact with the graphics that are customized to their specific interests, which can promote an engaging video conversation or AR experience.

Abstract: An online system customizes video conversations between users of the online system by providing graphics that are likely to interest the users. The online system may present composite views overlaying selected graphics on a video stream, which may be part of an augmented reality (AR) environment. The graphics include, for example, background graphics, masks, props, visual or particular effects, frames or borders, etc. The online system may use a machine learning model to predict whether a user is likely to select or interact with a particular graphic. The online system can also filter or rank graphics according to user affinities or user connections on the online system. Users may be encouraged to interact with the graphics that are customized to their specific interests, which can promote an engaging video conversation or AR experience.

Abstract: An online system customizes video conversations between users of the online system by providing graphics that are likely to interest the users. The online system may present composite views overlaying selected graphics on a video stream, which may be part of an augmented reality (AR) environment. The graphics include, for example, background graphics, masks, props, visual or particular effects, frames or borders, etc. The online system may use a machine learning model to predict whether a user is likely to select or interact with a particular graphic. The online system can also filter or rank graphics according to user affinities or user connections on the online system. Users may be encouraged to interact with the graphics that are customized to their specific interests, which can promote an engaging video conversation or AR experience.

Abstract: An online system generates a feed of content items for a user subject to a limitation restricting the number of content items including video data (“video content items”) included in the feed. If the user interacts with a video content item the feed, the online system selects candidate video content items based on characteristics of the video content item in the feed and characteristics of the user. The online system determines likelihoods of the user interacting with various candidate video content items and selects candidate video content items based on the determined likelihoods. To present the user with additional video content items, the online system generates an interface including the selected candidate video content items and presents the interface to the user. The interface may be presented in place of the feed or may be presented as within the feed and presents different video content items based on user interactions.

Abstract: An online system generates a feed of content items for a user subject to a limitation restricting the number of content items including video data (“video content items”) included in the feed. If the user interacts with a video content item the feed, the online system selects candidate video content items based on characteristics of the video content item in the feed and characteristics of the user. The online system determines likelihoods of the user interacting with various candidate video content items and selects candidate video content items based on the determined likelihoods. To present the user with additional video content items, the online system generates an interface including the selected candidate video content items and presents the interface to the user. The interface may be presented in place of the feed or may be presented as within the feed and presents different video content items based on user interactions.

Abstract: Systems, methods, and non-transitory computer-readable media can identify a source content item for which related content is to be provided. A set of candidate content items associated with the source content item can be selected. The set of candidate content items can be ranked based, at least in part, on a set of engagement signals associated with the set of candidate content items. A subset of highest ranked candidate content items out of the set of candidate content items can be provided as the related content for the source content item.