IP Library › Granted Patent US 10,275,535
Granted Patent B1
US 10,275,535 · App. 15/169,179 · Granted Apr 30, 2019

Obtaining user feedback from social media data

Inventor: Kurt Trauth (San Antonio, TX)
Assignee: United Services Automobile Association (USAA)
G06F17/30867G06F17/30371G06F17/30489
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,275,535
App. No.
15/169,179
Granted
Apr 30, 2019
Kind
B1
Abstract

Obtaining user feedback from a social networking service can include obtaining multiple social media posts provided on at least one social networking service, the multiple social media posts being associated with an entity, applying a pronoun filter to the multiple social media posts to obtain a filtered set of social media posts, each social media post in the filtered set including at least one pronoun from a pronoun list, and analyzing the filtered set of social media posts to identify trends or sentiments related to the entity.

Claims (71)

1. A computer-implemented method comprising:

obtaining, by at least one processor, search results comprising a plurality of social media posts provided on at least one social networking service, wherein each social media post of the plurality of social media posts comprises a reference to a business entity;

applying, by the at least one processor, a pronoun filter to the plurality of social media posts to obtain a filtered set of social media posts, each social media post in the filtered set comprising at least one pronoun from a pronoun list;

identifying, among the filtered set of social media posts, at least one social media post that has shared an original content item;

identifying a user who published the at least one social media post on the at least one social networking service;

determining that the identified user corresponds to a target audience;

identifying an application programming interface (API) offered by the at least one social media networking service;

sending, to the at least one social networking service, a query that conforms with the API to obtain at least one of (i) times associated with social media posts previously published by the identified user, or (ii) times when the identified user has engaged with social media posts published by other users, wherein the query comprises a username of the identified user;

analyzing the obtained times to determine a time frame during which the identified user routinely accesses the at least one social networking service; and

targeting a second content item to the identified user during the determined time frame.

2. The method of claim 1 , wherein the reference to the business entity comprises at least one of a name of the business entity, a username associated with the business entity, a nickname associated with the business entity, or an adaptation of the name of the business entity.

3. The method of claim 1 , wherein at least one of the plurality of social media posts is published on an interface of the at least one social networking service, the interface being managed by the business entity.

4. The method of claim 1 , wherein obtaining the search results comprises:

sending at least one query to the at least one social networking service through the API to request social media posts that are provided on the social media networking service and that comprise a reference to the business entity; and

retrieving, in response to sending the query, the plurality of social media posts.

5. The method of claim 1 , further comprising removing, from the search results, duplicate social media posts.

6. The method of claim 1 , further comprising, removing, from the search results, social media posts comprising a hyperlink.

7. The method of claim 1 , wherein the pronoun list comprises the pronouns “I,” “I'm,” “I'll,” “I've,” “me,” “my,” and “mine.”

8. The method of claim 1 , wherein analyzing the filtered set of social media posts comprises:

performing natural language processing on the filtered set of social media posts; and

identifying, based on an output of the natural language processing, sentiment expressed in each social media post of the filtered set of social media posts.

9. The method of claim 1 , wherein the original content item is a content item that the business entity originally published on the at least one social networking service.

10. The method of claim 1 , wherein the original content item comprises content related to a predetermined topic of interest.

11. The method of claim 1 , wherein identifying a user who published the at least one social media post comprises identifying a username associated with the at least one social media post.

12. The method of claim 1 , wherein determining that the identified user corresponds to a target audience comprises: determining that a size of the user's social network exceeds a specified threshold.

13. The method of claim 1 , wherein determining that the identified user corresponds to a target audience comprises:

generating an influence score for the identified user based on at least one of (i) types of engagement activities that other users have performed responsive to social media posts previously published by the identified user, or (ii) an indicator of how many times the other users have performed engagement activities responsive to social media posts previously published by the identified user on the at least one social networking service; and

determining that the identified user corresponds to a target audience based on the generated influence score.

14. A non-transitory computer-readable medium coupled to at least one computer having instructions stored thereon which, when executed by the at least one computer, cause the at least one computer to perform operations comprising:

obtaining search results comprising a plurality of social media posts provided on at least one social networking service, wherein each social media post of the plurality of social media posts comprises a reference to a business entity;

applying a pronoun filter to the plurality of social media posts to obtain a filtered set of social media posts, each social media post in the filtered set comprising at least one pronoun from a pronoun list; identifying, among the filtered set of social media posts, at least one social media post that has shared an original content item;

identifying a user who published the at least one social media post on the at least one social networking service;

determining that the identified user corresponds to a target audience;

identifying an application programming interface (API) offered by the at least one social media networking service;

sending, to the at least one social networking service, a query that conforms with the API to obtain at least one of (i) times associated with social media posts previously published by the identified user, or (ii) times when the identified user has engaged with social media posts published by other users, wherein the query comprises a username of the identified user;

analyzing the obtained times to determine a time frame during which the identified user routinely accesses the at least one social networking service; and

targeting a second content item to the identified user during the determined time frame.

15. The computer-readable medium of claim 14 , wherein the reference to the business entity comprises at least one of a name of the business entity, a username associated with the business entity, a nickname associated with the business entity, or an adaptation of the name of the business entity.

16. The computer-readable medium of claim 14 , wherein at least one of the social media posts is published on an interface of the social networking service, the interface being managed by the business entity.

17. The computer-readable medium of claim 14 , wherein

obtaining the search results comprises:

sending at least one query to the at least one social networking service through the API to request social media posts that are provided on the at least one social media networking service and that comprise a reference to the business entity; and

retrieving, in response to sending the query, the plurality of social media posts.

18. The computer-readable medium of claim 14 , further comprising removing, from the search results, duplicate social media posts.

19. The computer-readable medium of claim 14 , further comprising, removing, from the search results, social media posts comprising a hyperlink.

20. The computer-readable medium of claim 14 , wherein the pronoun list comprises the pronouns “I,” “I'm,” “I'll,” “I've,” “me,” “my,” and “mine.”

21. The computer-readable medium of claim 14 , wherein analyzing the filtered set of social media posts comprises:

performing natural language processing on the filtered set of social media posts; and

identifying, based on an output of the natural language processing, sentiment expressed in each social media post of the filtered set of social media posts.

22. A system comprising:

at least one computer; and

a computer-readable medium coupled to the at least one computer having instructions stored thereon which, when executed by the at least one computer, cause the at least one computer to perform operations comprising;

obtaining search results comprising a plurality of social media posts provided on at least one social networking service, wherein each social media post of the plurality of social media posts comprises a reference to a business entity;

applying a pronoun filter to the plurality of social media posts to obtain a filtered set of social media posts, each social media post in the filtered set comprising at least one pronoun from a pronoun list; identifying, among the filtered set of social media posts, at least one social media post that has shared an original content item;

identifying a user who published the at least one social media post on the at least one social networking service;

determining that the identified user corresponds to a target audience;

identifying an application programming interface (API) offered by the at least one social media networking service;

sending, to the at least one social networking service, a query that conforms with the API to obtain at least one of (i) times associated with social media posts previously published by the identified user, or (ii) times when the identified user has engaged with social media posts published by other users, wherein the query comprises a username of the identified user;

analyzing the obtained times to determine a time frame during which the identified user routinely accesses the at least one social networking service; and

targeting a second content item to the identified user during the determined time frame.

23. The system of claim 22 , wherein the reference to the business entity comprises at least one of a name of the business entity, a username associated with the business entity, a nickname associated with the business entity, or an adaptation of the name of the business entity.

24. The system of claim 22 , wherein at least one of the plurality of social media posts is published on an interface of the social networking service, the interface being managed by the business entity.

25. The system of claim 22 , wherein obtaining the search results comprises:

sending at least one query to the at least one social networking service through the API to request social media posts that are provided on the social media networking service and that comprise a reference to the business entity; and

retrieving, in response to sending the query, the plurality of social media posts.

26. The system of claim 22 , further comprising removing, from the search results, duplicate social media posts.

27. The system of claim 22 , further comprising, removing, from the search results, social media posts comprising a hyperlink.

28. The system of claim 22 , wherein the pronoun list comprises the pronouns “I,” “I'm,” “I'll,” “I've,” “me,” “my,” and “mine.”

29. The system of claim 22 , wherein analyzing the filtered set of social media posts comprises:

performing natural language processing on the filtered set of social media posts; and

identifying, based on an output of the natural language processing, sentiment expressed in each social media post of the filtered set of social media posts.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 22, 2017
From: TRAUTH, KURT
To: UNITED SERVICES AUTOMOBILE ASSOCIATION (USAA)
Reel/Frame 041680/0921 →
Continuity (1)
Provisional Application 62170903 · Jun 4, 2015
Cited By (2)
US 12,579,149 US 12,627,620