Techniques are described for machine learning-based generation of target segments is leveraged in a digital medium environment. A segment targeting system generates training data to train a machine learning model to predict strength of correlation between a set of users and a defined demographic. Further, a machine learning model is trained with visit statistics for the users to predict the likelihood that the users will visit a particular digital content platform. Those users with the highest predicted correlation with the defined demographic and the highest likelihood to visit the digital content platform can be selected and placed within a target segment, and digital content targeted to the defined demographic can be delivered to users in the target segment.

Example embodiments provide systems and methods for crowdsourced skipping of media content portions. In an example method, a plurality of content tags are received from a plurality of media content devices over a communication network. Each of the plurality of content tags may designate a location within a media content item. The content tags are processed to generate aggregated content tags for the media content item. The aggregated content tags may designate one or more portions of the media content item for modified playback. The aggregated content tags for the media content item are transmitted over the communication network to a first media content device separate from the plurality of media content devices.

The present disclosure relates to a method, apparatus, and system for realizing dynamic scheduling for a cinema and controlling playing of a movie. In particular, embodiments of the present invention relate to dynamic scheduling of content presentation in a cinema by collecting user preferences of a plurality of users, wherein the user preference specifies at least a movie that a user desires to watch, a time for watching the movie, a cinema for watching the movie, and a number of people watching the movie; generating, based on the collected user preferences, a respective dynamic schedule for at least one cinema of a plurality of cinemas according to one of a plurality of scheduling schemes; and transmitting the generated respective dynamic schedule to at least one second electronic apparatus corresponding to the at least one cinema.

An electronic device including a display device configured to render first content. The electronic device is communicably coupled to the display device and controls one or more imaging devices to receive one or more images from the one or more imaging devices. The electronic device further determines a first position of one or more living objects within a pre-defined region from the display device, based on the received one or more images and the rendered first content. The electronic device further controls an orientation of the display device towards the determined first position of the one or more living objects.

Systems and methods for determining, based on recommendations provided by users that have consumed a media asset, which consumption options may be configured on a media device such that when configured enhance the user viewing experience for a specific media asset. The method includes accessing comments posted by other users that have consumed the media asset. The comments are analyzed to determine a consumption option recommendation. If the number of comments meet a threshold value, then the system either automatically configures the media device or configures the media device upon user approval with the recommended consumption option. The recommendation to configure a consumption option on the media device is made only if the recommendation is supported by the media device. The system also detects through audio and image analysis which users are consuming the media asset and accordingly configures the consumption options to their preferences.

A method, a computer program product, and a computer system for filtering content based on user state is disclosed. Exemplary embodiments include associating a user with one or more cohorts and extracting one or more features from a content retrieved by the user. Moreover, exemplary embodiments may further include determining whether at least one of the one or more features conflict with at least one of the one or more cohorts.

An example apparatus includes an advertisement determiner to identify a first plurality of respondents that received an addressable advertisement and a second plurality of respondents that received a linear advertisement based on combined program tuning data and reference advertisement data; a calculator to calculate a first average commercial minute rating for the addressable advertisement based on first duration weighted impressions associated with the first plurality of respondents and a second average commercial minute rating for the linear advertisement based on second duration weighted impressions associated with the second plurality of respondents; and a communication interface to transmit the first average commercial minute rating and the second average commercial minute rating for crediting the addressable advertisement and the linear advertisement with audience viewership metrics.

A device implementing the subject system may include at least one processor configured to obtain a first preference profile corresponding to a first user, a second preference profile corresponding to a second user, and a group preference profile corresponding to a user group that includes the first and second users. The at least one processor may be further configured to generate an aggregate preference profile based at least in part on the first preference profile, the second preference profile, and the group preference profile and to identify content items based at least in part on the aggregate preference profile. The at least one processor may be further configured to rank the content items and provide, for display on a content output device, at least one indication of at least one of the ranked content items as a recommendation for the user group.

A system for utilizing models derived from offline historical data in online applications is provided. The system includes a processor and a memory storing machine-readable instructions for determining a set of contexts of the usage data, and for each of the contexts within the set of contexts, collecting service data from services supporting the media service and storing that service data in a database. The system performing an offline testing process by fetching service data for a defined context from the database, generating a first set of feature vectors based on the fetched service data, and providing the first set to a machine-learning module. The system performs an online testing process by fetching active service data from the services supporting the media streaming service, generating a second set of feature vectors based on the fetched active service data, and providing the second set to the machine-learning module.

An online system presents content in videos to users. Content providers may value having their content injected into videos from certain sources more than others. This preferences is quantified as a brand value score. The brand value score is determined as a function of user engagement with a source of the video and, to account for brand value, the system performs a two-stage auction. First, the system determines whether to inject any content into a video by determining a distribution of brand value of videos per demand for videos in a previous period and filling a projected demand for the content in a current period to determine a brand value threshold. Then, any videos having a brand value above the threshold are eligible for the second stage of the selection process where the system performs an auction where projected benefit of presenting the content is compared to projected loss.