Methods and apparatus to deliver targeted advertising are disclosed. An example apparatus includes processor circuitry to: obtain user behavior information corresponding to interaction with a first media object from a user, the first media object including a first customizable media object element and a second customizable media object element independent of the first customizable media object element; analyze a performance of the first media object based on the user behavior information; and update at least one of a user profile of the user or a group profile corresponding to the user using a machine learning model to adjust ratings of the first customizable media object element and the second customizable media object element based on a comparison of the performance of the first media object to a second custom object including at least one of the first customizable media object element or the second customizable media object element.

Methods, systems, and apparatus, including computer programs encoded on a computer-readable storage medium, are described for providing content. A method includes transmitting an audio content item that is presented to a user of a personal digital assistant through a speaker; receiving digital information that includes spoken information that was submitted through the personal digital assistant by the user and converted into the digital information, the received digital information including data specifying one or more other users with which the audio content item is to be shared; annotating the audio content item with an annotation including at least some of the digital information and data specifying that the user is the source of the annotation; and transmitting the audio content item and the annotation to the one or more other users with which the audio content is to be shared as specified by the digital information.

Aspects of the present disclosure relate to machine learning techniques for continuous implementation and training of a machine learning system for identifying the natural language meaning of visual content. A computer vision model or other suitable machine learning model can predict whether a given descriptor is associated with the visual content. A set of such models can be used to determine whether particular ones of a set of descriptors are associated with the visual content, with the determined descriptors representing a meaning of the visual content. This meaning can be refined based on a multi-armed bandit tracking and analyzing interactions between the visual content and users associated with certain personas related to the determined descriptors.

A method includes receiving a voice request to generate synthesized voiceover speech for a target advertisement having one or more advertising campaign attributes. The method also includes generating, based on the one or more advertising campaign attributes, a voiceover script that includes a sequence of text for the synthesized voiceover speech. The method also includes generating, using a text-to-speech (TTS) system, the synthesized voiceover speech. The TTS system is configured to receive, as input, the sequence of text for the voiceover script and generate, as output, the synthesized voiceover speech. Here, the synthesized voiceover speech has speech characteristics specified by a target TTS vertical. The method also includes overlaying the synthesized voiceover speech on the target advertisement.

A facility for constructing an advertising message in connection with a web page is described. The facility obtains text associated with the web page, and uses the obtained text to generate a query. The facility uses the generated query to select a stock photography image, and generates an advertising message that incorporates the selected stock photography image.

Embodiments of the present disclosure provide methods, systems, apparatuses, and computer program products for adaptively generating an initial electronic bid value for a new digital content object.

Devices and methods are provided for using an interactive wrapper for media content. A method may include identifying, by a first device, a software container including a call to action. The method may include identifying non-interactive advertising content. The method may include generating an interactive advertisement by adding the advertising content to the software container, and sending the interactive advertisement to a second device for presentation. The method may include receiving an indication of a user interaction with the interactive advertisement, and determining, based on the user interaction, an action. The method may include sending data associated with the action to the second device or a third device for presentation.

In implementations of multi-item influence maximization, a computing device can obtain updates to a user association graph that indicates social correspondence between users, and obtain updates to a user-item graph that indicates user correspondence with one or more items. The computing device includes an influence maximization module that can update an item association graph that indicates item correspondence of each item with one or more other items, where the item association graph can be updated based on the user-item graph that indicates the user correspondence with one or more of the items. The influence maximization module can then iteratively determine a resource allocation for each of the users to maximize user influence of multiple items that are associated in the item association graph and based on the social correspondence between the users, as well as assign a variable portion of the resource allocation to any number of the users.

Electronic correspondence that includes one or more promotions may be generated for presenting to a consumer. In order to determine whether to present the electronic correspondence to the consumer, the promotions included in the electronic correspondences may be analyzed in terms of a probability the consumer will accept the promotions, a relevance level between the promotions and attributes of the consumer, a relevance level between the promotions and the consumer, a relevance level between the promotions and a set of goals or rules, among other similar terms. After the analysis, a determination may be made whether to send the electronic correspondence to the consumer. Similarly, the analysis may compare multiple electronic correspondences, and determine, based on the comparison, which of the multiple electronic correspondences to send to the consumer.

Electronic correspondence that includes one or more promotions may be generated for presenting to a consumer. In order to determine whether to present the electronic correspondence to the consumer, the promotions included in the electronic correspondences may be analyzed in terms of a probability the consumer will accept the promotions, a relevance level between the promotions and attributes of the consumer, a relevance level between the promotions and the consumer, a relevance level between the promotions and a set of goals or rules, among other similar terms. After the analysis, a determination may be made whether to send the electronic correspondence to the consumer. Similarly, the analysis may compare multiple electronic correspondences, and determine, based on the comparison, which of the multiple electronic correspondences to send to the consumer.