Selecting Content for Presentation to Social Networking System Users Based On User Engagement with Content

• US 20160358229A1
• Filed: 06/05/2015
• Published: 12/08/2016
• Est. Priority Date: 06/05/2015
• Status: Abandoned Application

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Parrella, Justin Paul, Bhalgat, Anand Sumatilal, Li, Shuo, Pan, Ke, Tang, Yi
• Application Number:
  US14/731,565
• Publication Number:
  US 20160358229A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0275 Auctions
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04W 4/21 for social networking applications

Abstract

A social networking system presents a content feed including organic content items and sponsored content items to a user. To maintain user interaction with the content feed, the social networking system determines probabilities of the user performing various types of interactions with a sponsored content item and accounts for the determined probabilities when selecting content items for presentation via the content feed. For example, the social networking system generates a value for the sponsored content item based on the determined probabilities and determines a score for the sponsored content item based on the value and a bid amount associated with the sponsored content item. When selecting content for the content feed, the social networking system evaluates the sponsored content item based on its associated score. Prior interactions between the user and previously presented content may be used when determining the score for the sponsored content item.

Claims

1. A method comprising:

receiving one or more advertisement requests (“

ad requests”

) at a social networking system, each ad request including a bid amount and an advertisement;

receiving a request to present a content feed to a user of the social networking system, the content feed including one or more content items and one or more advertisements included in one or more ad requests;

retrieving prior interactions by the user with advertisements previously presented to the user by the social networking system;

determining probabilities of the user performing one or more types of interactions from a set of types of interactions with an advertisement in a received ad request based at least in part on the prior interactions by the user with the advertisements and content items previously presented to the user;

determining a value associated with the received ad request based at least in part on the determined probabilities;

determining an expected amount of interaction by the user with the advertisement included in the received ad request based at least in part on the retrieved prior interactions;

generating a score associated with the received ad request by combining the expected amount of interaction by the user with the advertisement included in the received ad request with the bid amount included in the received ad request and with the determined value; and

including the received ad request and score associated with the received ad request in a selection process configured to select content for presentation to the user by the social networking system.

2. The method of claim 1, wherein determining probabilities of the user performing one or more types of interactions from the set of types of interactions with the advertisement in the received ad request based at least in part on the prior interactions by the user with the advertisements and content items previously presented to the user comprises:

identifying advertisements previously presented to the user having at least a threshold number of characteristics matching characteristics of the advertisement in the received ad request;

retrieving types of interactions from the set of types of interactions by the user with the identified advertisements from the retrieved prior interactions by the user; and

determining the probabilities of the user performing the one or more types of interactions form the set of types of interactions based at least in part on the types of interactions from the set of types of interactions by the user with the identified advertisements.

3. The method of claim 1, wherein determining the value associated with the received ad request based at least in part on the determined probabilities comprises:

obtaining a weight associated with each type of interaction in the set of types of interactions;

applying the weights associated with each type of interaction in the set of types of interactions to the probabilities of the user performing each of the one or more types of interactions in the set of types of interactions with the advertisement in the received ad request, a weight associated with a type of interaction in the set applied to a probability of the user performing the type of interaction in the set; and

generating the value by combining the probabilities of the user performing each of the one or more types of interactions in the set after application of the weights.

4. The method of claim 3, wherein a positive weight is associated with one or more types of interactions indicating interest.

5. The method of claim 4, wherein a type of interaction indicating interest is selected from a group consisting of:

indicating a preference for a content item or an and request, sharing the content item or the ad request with an additional user of the social networking system, accessing the content item or the ad request, accessing additional content associated with the content item or the ad request, and any combination thereof.

6. The method of claim 3, wherein a negative weight is associated with one or more types of interactions indicating lack of interest.

7. The method of claim 6, wherein an interaction indicating lack of interest comprises hiding a content item or an ad request.

8. The method of claim 1, wherein generating the score associated with the received ad request by combining the expected amount of interaction by the user with the advertisement included in the received ad request with the bid amount included in the received ad request and with the determined value comprises:

applying a conversion factor to the expected amount of interaction by the user with the advertisement included in the received ad request determined value that results in a common unit of measurement for the bid amount and the determined value; and

combining the bid amount, the determined value, and the expected amount of interaction after application of the conversion factor.

9. The method of claim 8, wherein the conversion factor is based at least in part on a difference between an estimated amount of interaction by the user with the content feed not including the advertisement from the received ad request and an estimated amount of interaction by the user with the content feed including the advertisement from the received ad request.

10. The method of claim 1, wherein generating the score associated with the received ad request by combining the expected amount of interaction by the user with the advertisement included in the received ad request with the bid amount included in the received ad request and with the determined value comprises:

determining a user-specific weight based at least in part on an average bid amount of advertisements previously presented to the user during a specific time interval and an amount of interaction by the user with content presented to the user by the social networking system during the specific time interval;

applying the user specific-weight to the determined value; and

generating the score associated with the received ad request by combining the bid amount included in the received ad request, the expected amount of interaction by the user with the advertisement included in the received ad request, and the determined value after application of the user-specific weight.

11. The method of claim 1, wherein generating the score associated with the received ad request by combining the expected amount of interaction by the user with the advertisement included in the received ad request with the bid amount included in the received ad request and with the determined value comprises:

determining a user-specific weight based at least in part on an average bid amount of advertisements previously presented to additional users having at least a threshold number of characteristics matching characteristics of the user the user during a specific time interval and an amount of interaction by the additional users having at least the threshold number of characteristics matching characteristics of the user with content presented to the additional users by the social networking system during the specific time interval;

applying the user specific-weight to the determined value; and

generating the score associated with the received ad request by combining the bid amount included in the received ad request, the expected amount of interaction by the user with the advertisement included in the received ad request, and the determined value after application of the user-specific weight.

12. The method of claim 1, wherein generating the score associated with the received ad request by combining the expected amount of interaction by the user with the advertisement included in the received ad request with the bid amount included in the received ad request and with the determined value comprises:

determining a user-specific weight based at least in part on an average bid amount of advertisements previously presented to the user during a specific time interval and an amount of interaction by the user with content presented to the user by the social networking system during the specific time interval;

applying the user specific-weight and a scaling factor to the determined value; and

generating the score associated with the received ad request by combining the bid amount included in the received ad request, the expected amount of interaction by the user with the advertisement included in the received ad request, and the determined value after application of the user-specific weight and the scaling factor.

13. A computer program product comprising a computer-readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to:

receive one or more advertisement requests (“

ad requests”

) at a social networking system, each ad request including a bid amount and an advertisement;

receive a request to present a content feed to a user of the social networking system, the content feed including one or more content items and one or more advertisements included in one or more ad requests;

retrieve prior interactions by the user with advertisements previously presented to the user by the social networking system;

determine probabilities of the user performing one or more types of interactions from a set of types of interactions with an advertisement in a received ad request based at least in part on the prior interactions by the user with the advertisements and content items previously presented to the user;

determine a value associated with the received ad request based at least in part on the determined probabilities;

determine an expected amount of interaction by the user with the advertisement included in the received ad request based at least in part on the retrieved prior interactions;

generate a score associated with the received ad request by combining the expected amount of interaction by the user with the advertisement included in the received ad request with the bid amount included in the received ad request and with the determined value; and

include the received ad request and score associated with the received ad request in a selection process configured to select content for presentation to the user by the social networking system.

14. The computer program product of claim 13, wherein determine probabilities of the user performing one or more types of interactions from the set of types of interactions with the advertisement in the received ad request based at least in part on the prior interactions by the user with the advertisements and content items previously presented to the user comprises:

identify advertisements previously presented to the user having at least a threshold number of characteristics matching characteristics of the advertisement in the received ad request;

retrieve types of interactions from the set of types of interactions by the user with the identified advertisements from the retrieved prior interactions by the user; and

determine the probabilities of the user performing the one or more types of interactions form the set of types of interactions based at least in part on the types of interactions from the set of types of interactions by the user with the identified advertisements.

15. The computer program product of claim 13, wherein determine the value associated with the received ad request based at least in part on the determined probabilities comprises:

obtain a weight associated with each type of interaction in the set of types of interactions;

apply the weights associated with each type of interaction in the set of types of interactions to the probabilities of the user performing each of the one or more types of interactions in the set of types of interactions with the advertisement in the received ad request, a weight associated with a type of interaction in the set applied to a probability of the user performing the type of interaction in the set; and

generate the value by combining the probabilities of the user performing each of the one or more types of interactions in the set after application of the weights.

16. The computer program product of claim 13, wherein generate the score associated with the received ad request by combining the expected amount of interaction by the user with the advertisement included in the received ad request with the bid amount included in the received ad request and with the determined value comprises:

apply a conversion factor to the expected amount of interaction by the user with the advertisement included in the received ad request determined value that results in a common unit of measurement for the bid amount and the determined value; and

combine the bid amount, the determined value, and the expected amount of interaction after application of the conversion factor.

17. The computer program product of claim 16, wherein the conversion factor is based at least in part on a difference between an estimated amount of interaction by the user with the content feed not including the advertisement from the received ad request and an estimated amount of interaction by the user with the content feed including the advertisement from the received ad request.

18. The computer program product of claim 13, wherein generate the score associated with the received ad request by combining the expected amount of interaction by the user with the advertisement included in the received ad request with the bid amount included in the received ad request and with the determined value comprises:

determine a user-specific weight based at least in part on an average bid amount of advertisements previously presented to the user during a specific time interval and an amount of interaction by the user with content presented to the user by the social networking system during the specific time interval;

apply the user specific-weight to the determined value; and

generate the score associated with the received ad request by combining the bid amount included in the received ad request, the expected amount of interaction by the user with the advertisement included in the received ad request, and the determined value after application of the user-specific weight.

19. The computer program product of claim 13, wherein generate the score associated with the received ad request by combining the expected amount of interaction by the user with the advertisement included in the received ad request with the bid amount included in the received ad request and with the determined value comprises:

determine a user-specific weight based at least in part on an average bid amount of advertisements previously presented to additional users having at least a threshold number of characteristics matching characteristics of the user the user during a specific time interval and an amount of interaction by the additional users having at least the threshold number of characteristics matching characteristics of the user with content presented to the additional users by the social networking system during the specific time interval;

apply the user specific-weight to the determined value; and

generate the score associated with the received ad request by combining the bid amount included in the received ad request, the expected amount of interaction by the user with the advertisement included in the received ad request, and the determined value after application of the user-specific weight.

20. The computer program product of claim 13, wherein generating the score associated with the received ad request by combining the expected amount of interaction by the user with the advertisement included in the received ad request with the bid amount included in the received ad request and with the determined value comprises:

determine a user-specific weight based at least in part on an average bid amount of advertisements previously presented to the user during a specific time interval and an amount of interaction by the user with content presented to the user by the social networking system during the specific time interval;

apply the user specific-weight and a scaling factor to the determined value; and

generate the score associated with the received ad request by combining the bid amount included in the received ad request, the expected amount of interaction by the user with the advertisement included in the received ad request, and the determined value after application of the user-specific weight and the scaling factor.