Methods and systems for calculating, storing, and allowing electronic searches for metadata associated with media titles. The metadata includes scores specific to each actor and each genre of a media title, where the scores indicate the degree to which an actor’s performance in that title corresponds to a particular genre. Electronic searches for particular actors’ performance in a specific genre thus return more accurate results that more correctly reflect how well the actors’ performances reflect that genre.

Systems and methods for providing a first user with recommendations of media assets for inclusion in a playlist for a second user based on the second user's viewing activity. These systems and methods receive, from the second user, an expression of disinterest in a media asset included in the playlist for the second user, update a user profile associated with the second user based on the expression of disinterest, and determine a recommendation for another media asset based on the updated user profile associated with the second user. The systems and methods provide the recommendation to the first user. By recommending media assets that the second user is least likely to object to, these systems and methods reduce the frequency of disruptive requests for media assets from the second user.

Systems and methods are provided herein for displaying recommendations that are temporally relevant to activities of a user and are contextually relevant to a portion of viewed media. This may be accomplished by a media guidance application identifying activities a user has planned, as well as respective times for which each of the plurality of activities was planned to be performed by the user. The media guidance application may filter the activities by determining which of the first plurality of activities has a corresponding respective time that is within a threshold period of time. The media guidance application may then identify characteristics of each filtered activity and of a media asset that the user is consuming at the present moment, and may compute whether the characteristics match. If the characteristics match, the media guidance application may generate for display a recommendation relating to the respective activity.

Systems and methods are provided for managing subscriptions. A media guidance application obtaining viewing patterns of a subscriber and determining a first and second media package of interest to the subscriber. A first and second release schedule are obtained related to media content in the first and second media packages. The media guidance application predicts a first viewing impact of the first subscription and a second viewing impact of the second subscription, for the upcoming time period, wherein the viewing impact indicates a total predicted amount of time spent viewing the media packages in the upcoming time period. An available amount of time for viewing media in the upcoming time period is also determined. The media guidance application generates a subscription recommendation for the upcoming time period based on the first viewing impact, second viewing impact, and available amount of time for viewing media in the upcoming time period.

Systems and methods are disclosed to provide one or more content summaries for one or more media assets, wherein it is determined that consumption associated with a profile of a media asset will begin at a first time and at a second time that is a period of time prior to the first time, it is caused to be provided one or more content summaries for the one or more media assets, wherein the one or more content summaries are selected based at least on a duration of the content summary, such that a duration of the content summary is not greater than the period of time.

This document describes, among other things, systems, methods, devices, and other techniques for using information about how long various videos were presented at client devices to determine subsequent video recommendations and search results. In some implementations, a computing can include a modeling apparatus, a front-end server, a request manager, one or more video file storage devices, a video selector, or a combination of some or all of these. The video selector can select video content for a particular digitized video among a plurality of digitized videos to serve to a computing device responsive to a request. The selection can be based at least in part on how long the particular digitized video has been presented at client devices associated with users having characteristics that match one or more characteristics of the user that submitted the request for video content, as indicated by the modeling apparatus.

Disclosed is a display apparatus comprising: a display; a user input unit; and a processor configured to identify a user's viewing time based on a user's viewing history, create a list of content to be provided within the identified viewing time based on the viewing history and display the created content list on the display, and select at least one piece of content in the content list for viewing schedule based on a user input through the user input unit.

Systems and methods are provided for determining a subset of available paths of an interactive media program to generate for output. One example method includes receiving, at a computing device, the interactive media program, wherein the interactive media program comprises a plurality of alternative segments followed by a common segment and accessing a user profile. A subset of the plurality of alternative segments are identified, based on the user profile. A set of options for output are generated, wherein the set of options enables one of the alternative segments to be selected from the identified subset of the alternative segments. A selection of an option of the set of options is received, wherein the option is a first option and a first segment of the subset of the plurality of alternative segments is generated for output, based on the selected option.

Disclosed is a system for generating personalized recommendations based on dynamic and customized content selections and modeling of the content selections. The system may receive a request with an identifier and a query, and may obtain a particular recommendation configuration based the identifier and the query. The system may retrieve a set of content that satisfies the query and that is identified with at least one content prioritization parameter specified in the particular recommendation configuration, may generate a set of models of one or more model types that model relevance between the set of content and a different event specified in the particular recommendation configuration, and may compute a score for each content in each model based on the modeled relevance. The system may present recommended content in a different order than the set of content based on aggregate scores compiled for each content from the set of models.

In some embodiments, a method receives a first sequence of inputs for processing via a sub-model of a plurality of sub-model. The plurality of sub-models are part of a main model. An input in the sequence of inputs is masked with a masked value to generate a second sequence of inputs. The method processes the second sequence of inputs using the sub-model to generate a sequence of features that correspond to the second sequence of inputs and processes the sequence of features to generate a first output. The first output is processed to generate a second output of the main model. The sub-model is trained based on a feature in the sequence of features that corresponds to the masked input and the second output.