Identify experts and influencers in a social network

• US 8,954,503 B2
• Filed: 03/03/2011
• Issued: 02/10/2015
• Est. Priority Date: 03/03/2011
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Bosworth, Andrew Garrod, Murphy, Michael Patrick
• Primary Examiner(s): Srivastava, Vivek
• Assistant Examiner(s): BUKHARI, SIBTE H
• Application Number:
  US13/040,129
• Publication Number:
  US 20120226748A1
• Time in Patent Office: 1,440 Days
• Field of Search: 709/204
• US Class Current: 709/204
• CPC Class Codes: G06Q 10/103 Workflow collaboration or project management
• CPC Class Codes: H04L 12/1813 for computer conferences, e.g. chat rooms instant messaging H04L51/04; protocols for multimedia communication H04L65/1101; arrangements for multi-party communication H04L65/403; telephonic conference arrangements H04M3/56; television conference systems H04N7/15

Abstract

On embodiment accesses a set of information comprising one or more elements of information relating to a subject matter, wherein the one or more elements of information have been shared among one or more users of a social-networking system; for each element of information, determines a rate of sharing of the element of information among the one or more users and identifies one or more first users who cause the rate of sharing of the element of information to increase; and identifies one or more influencers associated with the subject matter from the one or more first users identified for each element of information.

Claims

1. A method comprising:

by one or more computing devices, for one or more elements of information relating to a subject matter, wherein the elements of information have been shared among a plurality of users of a social-networking system;

by one or more computing devices, for each element of information;

calculating one or more first-order derivatives of a non-zero rate of sharing of the element of information;

identifying, based at least in part on one or more of the first-order derivatives, one or more increases in the non-zero rate of sharing of the element of information among the users, wherein each of the increases comprises a first number of shares of the element of information over a first period of time being less than a second number of shares of the element of information over a second period of time following the first period of time; and

identifying, from the plurality of the users of the social-networking system, one or more first users who caused one or more of the increases in the non-zero rate of sharing, wherein each of the first users shared the element of information at one or more times respectively associated with one or more of the increases in the non-zero rate of sharing; and

by one or more computing devices, identifying one or more influencers associated with the subject matter from the first users identified for one or more of the elements of information.

2. The method of claim 1, wherein for one or more of the elements of information, identifying the first users comprises identifying the first users who caused the non-zero rate of sharing of the element of information to locally increase significantly.

3. The method of claim 1, wherein identifying one or more of the influencers comprises:

for one or more of the first users;

determining a total number of elements of information for which the first user is identified; and

if the total number of elements of information is greater than or equal to a threshold, then selecting the first user as one of the influencers.

4. The method of claim 1, further comprising:

surveying one or more of the users of the social-networking system to identify one or more potential experts associated with the subject matter; and

selecting, from the potential experts, one or more experts associated with the subject matter.

5. The method of claim 1, wherein for one or more of the elements of information:

one or more instances of the element of information are included in a set of information; and

each instance of the element of information corresponds to where the element of information is shared by one or more of the users.

6. The method of claim 5, further comprising:

for one or more of the elements of information, tracing backward a sharing process of the element of information through the instances of the element of information to identify a second user who shared an initial instance of the element of information; and

identifying one or more experts associated with the subject matter from the second user identified for the element of information.

7. The method of claim 6, wherein identifying the experts comprises:

for one or more of the second users;

determining a total number of elements of information for which the second user is identified; and

if the total number of elements of information is greater than or equal to a threshold, then selecting the second user as one of the experts.

8. The method of claim 5, further comprising:

for one or more of the elements of information, tracing backward a sharing process of the element of information through the instances of the element of information to locate an initial instance of the element of information;

identifying one of the influencers who is closest to the initial instance of the element of information along the sharing process of the element of information;

identifying a second user who is directly connected to the one of the influencers within the social-networking system as an author of the element of information; and

identifying one or more experts associated with the subject matter from the second user identified for the element of information.

9. The method of claim 5, further comprising:

for one or more of the elements of information, tracing backward a sharing process of the element of information through the instances of the element of information to identify a second user who shares an initial instance of the element of information;

for one or more of the influencers, determining a number of connections between the influencer and the second user identified for at least one element of information within the social-networking system; and

grouping the influencers based on the number of connections determined for the influencers.

10. The method of claim 1, further comprising:

identifying the subject matter; and

selecting, from information shared by the users of the social-networking system, the elements of information relating to the subject matter to form a set of information.

11. A system comprising:

one or more processors; and

a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to;

for one or more elements of information relating to a subject matter, wherein the elements of information have been shared among a plurality of users of a social-networking system;

calculate one or more first-order derivatives of a non-zero rate of sharing of the element of information;

identify, based at least in part on one or more of the first-order derivatives, one or more increases in the non-zero rate of sharing of the element of information among the users, wherein each of the increases comprises a first number of shares of the element of information over a first period of time being less than a second number of shares of the element of information over a second period of time following the first period of time; and

identify, from the plurality of the users of the social-networking system, one or more first users who caused one or more of the increases in the non-zero rate of sharing, wherein each of the first users shared the element of information at one or more times respectively associated with one or more of the increases in the non-zero rate of sharing; and

identify one or more influencers associated with the subject matter from the first users identified for one or more of the elements of information.

12. The system of claim 11, wherein for one or more of the elements of information, identifying the first users comprises identifying the first users who caused the non-zero rate of sharing of the element of information to locally increase significantly.

13. The system of claim 11, wherein identifying one or more of the influencers comprises:

for one or more of the first users;

determine a total number of elements of information for which the first user is identified; and

if the total number of elements of information is greater than or equal to a threshold, then select the first user as one of the influencers.

14. The system of claim 11, wherein the processors are further operable when executing the instructions to:

survey one or more of the users of the social-networking system to identify one or more potential experts associated with the subject matter; and

select, from the potential experts, one or more experts associated with the subject matter.

15. The system of claim 11, wherein for one or more of the elements of information:

one or more instances of the element of information are included in a set of information; and

each instance of the element of information corresponds to where the element of information is shared by one or more of the users.

16. The system of claim 15, wherein the processors are further operable when executing the instructions to:

for one or more of the elements of information, trace backward a sharing process of the element of information through the instances of the element of information to identify a second user who shared an initial instance of the element of information; and

identify one or more experts associated with the subject matter from the second user identified for the element of information.

17. The system of claim 16, wherein identifying the experts comprises:

for one or more of the second users;

determine a total number of elements of information for which the second user is identified; and

if the total number of elements of information is greater than or equal to a threshold, then select the second user as one of the experts.

18. The system of claim 15, wherein the processors are further operable when executing the instructions to:

for one or more of the elements of information, trace backward a sharing process of the element of information through the instances of the element of information to locate an initial instance of the element of information;

identify one of the influencers who is closest to the initial instance of the element of information along the sharing process of the element of information;

identify a second user who is directly connected to the one of the influencers within the social-networking system as an author of the element of information; and

identify one or more experts associated with the subject matter from the second user identified for the element of information.

19. The system of claim 15, wherein the processors are further operable when executing the instructions to:

for one or more of the elements of information, trace backward a sharing process of the element of information through the instances of the element of information to identify a second user who shares an initial instance of the element of information;

for one or more of the influencers, determine a number of connections between the influencer and the second user identified for at least one element of information within the social-networking system; and

group the influencers based on the number of connections determined for each influencer.

20. The system of claim 11, wherein the processors are further operable when executing the instructions to:

identify the subject matter; and

select, from information shared by the users the social-networking system, the elements of information relating to the subject matter to form a set of information.

21. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

for one or more elements of information relating to a subject matter, wherein the elements of information have been shared among a plurality of users of a social-networking system;

calculate one or more first-order derivatives of a non-zero rate of sharing of the element of information;

identify, based at least in part on one or more of the first-order derivatives, one or more increases in the non-zero rate of sharing of the element of information among the users, wherein each of the increases comprises a first number of shares of the element of information over a first period of time being less than a second number of shares of the element of information over a second period of time following the first period of time; and

identify, from the plurality of users of the social-networking system, one or more first users who caused one or more of the increases in the non-zero rate of sharing, wherein each of the first users shared the element of information at one or more times respectively associated with one or more of the increases in the non-zero rate of sharing; and

identify one or more influencers associated with the subject matter from the first users identified for one or more of the elements of information.

22. The media of claim 21, wherein for one or more of the elements of information, identifying the first users comprises identifying the first users who caused the non-zero rate of sharing of the element of information to locally increase significantly.