Abstract:
A system and method for generating a reputation score is disclosed. A processing unit processes user activity data from data sources to identify user interactions associated with a user. A categorizing engine categorizes the user interactions into categories. A social bonus engine determines a social bonus score based on social affinity data. A scoring engine computes a first reputation score for the user by combining scores for the categorized user interactions with a social bonus score. A learning engine receives a second set of user interactions and training data and generates a learning result that is used to update the first reputation score.
Abstract:
Methods, systems, and apparatus include computer programs encoded on a computer-readable storage medium, including a method for generating selection criteria. Data indicative of a landing page and data indicative of one or more types of business are received. One or more collections in a plurality of collections are identified, the identified collections being based at least in part on the types of business and including one or more entities. A first group of one or more entities is selected from the one or more identified collections. A second group of one or more entities is identified from the landing page. The first group of entities is compared with the second group of entities. Based on the comparing, selection criteria is generated for one or more content items, wherein the selection criteria is used to identify one or more particular content items in response to receiving a request for information.
Abstract:
A system, computer program product and method for dynamically digesting one or more user notifications based at least in part on one or more rules are disclosed. In some implementations, the system includes a notification receiver module, a rule application module and a notification digestion module. The notification receiver module receives notifications including a first notification. The rule application module obtains rules for determining a send condition including a delay time and a maximum delay time, sets the delay time and the max delay time, determines whether another notification is received within the delay time, resets the delay time responsive to another notification being received within the delay time, and repeats the determination and delay time reset until a send condition occurs. The notification digestion module, responsive to the send condition occurring, digests the notification(s) received prior to the send condition and sends a digested notification to the user.
Abstract:
Methods, systems, and apparatus for selecting content items based on presentation context are presented. In one aspect, a method includes for each of a plurality of content item slots of a resource: obtaining first performance data based on a performance of content items that were presented in a navigational context in the content item slot; obtaining second performance data based on a performance of content items that were presented in a non-navigational context in the content item slot; determining, from the first and second performance data, a navigational performance adjustment factor for the content item slot, the navigational performance adjustment factor indicating, for the content item slot, a performance of content items presented in the navigational context relative to a performance of content items presented in the non-navigational context.
Abstract:
Methods, systems, and media for providing media guidance are provided. In some implementations, a method for providing media guidance is provided, the method comprising: receiving device data from a mobile device associated with a display device; identifying a media content item being presented on the display device; determining a first indication that the mobile device has been interacted with during the presentation of the media content item; storing a first timestamp corresponding to the first indication; determining a second indication that the interaction with the mobile device has ceased; storing a second timestamp corresponding to the second indication; receiving an indication that the media content item is to be played back; determining, using a hardware processor, a first playback position in the media content item based on the first timestamp; and causing the media content item to be presented from the determined first playback position in response to receiving the indication.
Abstract:
Methods, systems, and apparatus include computer programs encoded on a computer-readable storage medium for providing content to a user. A method includes: identifying a first resource, the first resource including one or more links to second, other resources and at least one slot for filling with third party content, wherein first selection criteria are associated with a first slot of the at least one slots; determining for at least one of the second other resources entities associated therewith, including evaluating a page associated with the second other resource to identify entities that are associated with content presented on the page; using the determined entities to either augment or filter the first selection criteria producing enhanced selection criteria; and determining one or more content items for presentation to a user in the first slot, wherein determining includes using the enhanced selection criteria to identify the one or more content items.
Abstract:
The present disclosure relates to systems and methods for refining content selection criteria to facilitate content selection via a computer network. In some embodiments, a tool identifies a first entity used to select content of a first content provider. The first entity can correspond to a canonical stable identifier in a database. The tool can identify a plurality of sets of entities that each comprise the first entity and an additional entity different from the first entity. Each of the plurality of sets of entities can be associated with content of a corresponding content provider. The tool can determine a performance metric for the additional entity. The tool can compare the performance metric with a performance threshold. The tool can associate the additional entity with the content of the first content provider based on the comparison.
Abstract:
Implementations of the disclosed subject matter provide techniques for recommending a song to a user based on the user's application usage information. A method may include receiving an indication of playback of a first song, by a first user, in a media application operating on a first device. It may be determined that a first content item is active on the first device during playback of the first song. An association may be stored of the first content item with the first song. Next, an indication may be received that the first content item is active on the first device. As a result, a second song associated with the first content item, based on the association of the first content item with the first song, may be recommended to the first user.
Abstract:
Systems, device and techniques are disclosed for providing a media item using a media recommendation model. The media recommendation model can be configured to identify a media item based on a received parameter from a mobile device by comparing the received parameter with a parameter associated with the media item. A parameter may correspond to a mobile device movement, time, location or the like and may be provided from a sensor such as a position sensor, an accelerometer, a clock, a barometer, or the like.
Abstract:
A system and method for allocating third-party content impressions among online media formats is provided. An allocation system normalizes the number of impressions of each format so that the durations of each format may be determined so that the expected revenue of the impressions on each format is approximately equal. The allocation system assigns an optimal number of third-party content impressions to a user based on the amount of content the user consumes. The allocation system determines the probabilities of third-party contents of differing durations and formats being served to the user as a function of the user's preferred format and of an optimal amount of third-party contents to be viewed by the user. The allocation system determines whether a given third-party content should be served as a function of the probability.