Abstract:
A plurality of media content items associated with a user and stored locally can be identified. Information associated with the plurality can be acquired. The information can include time data, location data, and/or social graph data. It can be determined, based on the information, that a collection of media content items, out of the plurality, are related. A layout customized for the collection can be generated. Moreover, the collection of media content items that are determined to be related can be identified. The collection can be presented as a collage based on the layout customized for the collection. Contextual information associated with the collage can be acquired. The contextual information can include time data, location data, and/or social graph data. A particular virtual overlaying template can be selected based on the contextual information. The collage can be presented in conjunction with the particular virtual overlaying template.
Abstract:
A plurality of media content items associated with a user and stored locally can be identified. Information associated with the plurality can be acquired. The information can include time data, location data, and/or social graph data. It can be determined, based on the information, that a collection of media content items, out of the plurality, are related. A layout customized for the collection can be generated. Moreover, the collection of media content items that are determined to be related can be identified. The collection can be presented as a collage based on the layout customized for the collection. Contextual information associated with the collage can be acquired. The contextual information can include time data, location data, and/or social graph data. A particular virtual overlaying template can be selected based on the contextual information. The collage can be presented in conjunction with the particular virtual overlaying template.
Abstract:
Systems, methods, and non-transitory computer-readable media can detect that a content item has been published. Information about the content item can be acquired. The information about the content item can be analyzed to determine a confidence metric for the content item. In some cases, the confidence metric can indicate a likelihood that the content item is associated with a narrative. It can be determined that the confidence metric for content item satisfies a specified threshold. The content item can be recommended to be included in the narrative.
Abstract:
In one embodiment, a method includes accessing one or more content objects associated with a first user of an online social network; generating a set of tag candidates by extracting one or more n-grams from the content objects, wherein each tag candidate comprises one or more text strings or ideograms from the extracted n-grams; calculating, for each tag candidate of the set of tag candidates, a quality-score for the tag candidate based on an affinity coefficient between the first user and a respective content object from which the n-grams or ideograms comprising the tag candidate were extracted; and sending, to a client system for display, one or more of the tag candidates as suggested tags for the first user, wherein each suggested tag has a quality-score greater than a threshold quality-score.
Abstract:
In one embodiment, a method includes accessing one or more content objects associated with a first user of an online social network; generating a set of tag candidates by extracting one or more n-grams from the content objects, wherein each tag candidate comprises one or more text strings or ideograms from the extracted n-grams; calculating, for each tag candidate of the set of tag candidates, a quality-score for the tag candidate based on an affinity coefficient between the first user and a respective content object from which the n-grams or ideograms comprising the tag candidate were extracted; and sending, to a client system for display, one or more of the tag candidates as suggested tags for the first user, wherein each suggested tag has a quality-score greater than a threshold quality-score.
Abstract:
A plurality of media content items associated with a user and stored locally can be identified. Information associated with the plurality can be acquired. The information can include time data, location data, and/or social graph data. It can be determined, based on the information, that a collection of media content items, out of the plurality, are related. A layout customized for the collection can be generated. Moreover, the collection of media content items that are determined to be related can be identified. The collection can be presented as a collage based on the layout customized for the collection. Contextual information associated with the collage can be acquired. The contextual information can include time data, location data, and/or social graph data. A particular virtual overlaying template can be selected based on the contextual information. The collage can be presented in conjunction with the particular virtual overlaying template.