Method and system for social network analysis

• US 8,473,422 B2
• Filed: 11/30/2010
• Issued: 06/25/2013
• Est. Priority Date: 09/12/2007
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Shen, Zeqian, Sundaresan, Neelakantan
• Primary Examiner(s): Ouellette, Jonathan
• Assistant Examiner(s): Kirlin, Amanda
• Application Number:
  US12/957,327
• Publication Number:
  US 20110071953A1
• Time in Patent Office: 938 Days
• Field of Search: 705/319, 705/26.1, 709/224
• US Class Current: 705/319
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Methods and system for social commerce network analysis are described. In one embodiment, a strongly connected component value, an in-component value, an out-component value, a disconnected component value, a tendril value, and a tube value of a social network for a time period may be accessed. A social strength of the social network for the time period may be calculated by combining the strongly connected component value, the in-component value, the out-component value, the disconnected component value, the tendril value, and the tube value. The social strength of the social network for the time period may be utilized for analysis of the social network. The strongly connected component value may have a greatest weight and the disconnected component value may have the lowest weight in the combining.

Claims

1. A method comprising:

retrieving, using one or more processors, a strongly connected component value, an in-component value, an out-component value, a disconnected component value, a tendril value, and a tube value of a social network for a time period;

the strongly connected component value quantifying a number of strongly connected vertices where, for each strongly connected vertex, there is a first path from a first vertex to a second vertex and a second path from the second vertex to the first vertex, the first vertex and the second vertex corresponding to a first user and a second user, respectively, who act as buyers and sellers in transactions between themselves in the social network;

the in-component value quantifying a number of in vertices, each in vertex corresponding to a third user who acts as a seller to the first user;

the out-component value quantifying a number of out vertices, each out vertex corresponding to a fourth user who acts as a buyer from the second user;

the tube value quantifying a number of tube vertices, each tube vertex being between the third user and the fourth user that do not include the first user and the second user;

the tendril value quantifying a number of tendril vertices, each tendril vertex being a buyer from the third user or a seller to the fourth user but have not conducted a transaction with the first user or the second user;

the disconnected component value quantifying a number of vertices that are not quantified by the strongly connected component value, the in-component value, the out-component value, the tendril value, or the tube value;

calculating, by the one or more processors, a social strength of the social network for the time period by applying a weighting factor to each of the strongly connected component value, the in-component value, the out-component value, the disconnected component value, the tendril value, and the tube value and summing the weighted values; and

utilizing the social strength of the social network for the time period for analysis of the social network,

wherein the strongly connected component value has the greatest weight and the disconnected component value has the lowest weight.

2. The method of claim 1, wherein the retrieving comprises:

determining the strongly connected component value in accordance with a graph percentage of a strongly connected component of the social network;

determining the in-component value in accordance with the graph percentage of an in-component of the social network;

determining the out-component value in accordance with the graph percentage of an out-component of the social network;

determining the disconnected component value in accordance with the graph percentage of a disconnected component of the social network;

determining the tendril value in accordance with the graph percentage of one or more tendrils of the social network; and

determining the tube value in accordance with the graph percentage of a tube of the social network.

3. The method of claim 1, wherein the utilizing comprises:

providing the social strength of the social network for the time period for presentation.

4. The method of claim 1, wherein the utilizing comprises:

retrieving the strongly connected component value, the in-component value, the out-component value, the disconnected component value, the tendril value, and the tube value of the social network for an additional time period;

calculating, by the one or more processors, the social strength of the social network for the additional time period by combining the strongly connected component value, the in-component value, the out-component value, the disconnected component value, the tendril value, and the tube value; and

using the social strength of the social network for the time period and the additional time period for analysis of the social network.

5. The method of claim 4, wherein the using comprises:

providing a difference between the social strength of the social network for the time period and the additional time period for presentation.

6. The method of claim 1, wherein the utilizing comprises:

providing the social strength for a plurality of categories in the social network for the time period for presentation;

wherein the social strength is calculated for the plurality of categories in the social network for the time period.

7. The method of claim 6, further comprising:

retrieving the strongly connected component value, the in-component value, the out-component value, the disconnected component value, the tendril value, and the tube value of the social network for an additional time period;

calculating, by the one or more processors, the social strength of the social network for the additional time period by combining the strongly connected component value, the in-component value, the out-component value, the disconnected component value, the tendril value, and the tube value; and

using the social strength for a plurality of categories of the social network for the time period and the additional time period for analysis of the social network,

wherein the social strength is calculated for the plurality of categories in the social network for the time period and the additional time period.

8. The method of claim 1, wherein a weight of the strongly connected component value is double the weight of the in-component and the out-component and the weight of the disconnected component value is half the weight of the in-component and the out-component in the summing.

9. The method of claim 1, wherein the social network is an online marketplace.

10. A method comprising:

retrieving, using one or more processors, a strongly connected component value, an in-component value, an out-component value, a disconnected component value, a tendril value, and a tube value of a social network for a time period;

the strongly connected component value quantifying a number of strongly connected vertices where, for each strongly connected vertex, there is a first path from a first vertex to a second vertex and a second path from the second vertex to the first vertex, the first vertex and the second vertex corresponding to a first user and a second user, respectively, who act as buyers and sellers in transactions between themselves in the social network;

the in-component value quantifying a number of in vertices, each in vertex corresponding to a third user who acts as a seller to the first user;

the out-component value quantifying a number of out vertices, each out vertex corresponding to a fourth user who acts as a buyer from the second user;

the tube value quantifying a number of tube vertices, each tube vertex being between the third user and the fourth user that do not include the first user and the second user;

the tendril value quantifying a number of tendril vertices, each tendril vertex being a buyer from the third user or a seller to the fourth user but have not conducted a transaction with the first user or the second user;

the disconnected component value quantifying a number of vertices that are not quantified by the strongly connected component value, the in-component value, the out-component value, the tendril value, or the tube value;

calculating, by the one or more processors, a social strength of the social network for the time period by applying a weighting factor to each of the strongly connected component value, the in-component value, the out-component value, the disconnected component value, the tendril value, and the tube value and summing the weighted values; and

identifying one or more users associated with the strongly connected component, the strongly connected component value being a value of the strongly connected component for the time period;

modifying an aspect of the social network associated with the one or more users;

retrieving the strongly connected component value, the in-component value, the out-component value, the disconnected component value, the tendril value, and the tube value of the social network for an additional time period, the additional time period being after the modifying of the aspect;

calculating, by the one or more processors, the social strength of the social network for the additional time period by combining the strongly connected component value, the in-component value, the out-component value, the disconnected component value, the tendril value, and the tube value; and

utilizing the social strength of the social network for the time period and the additional time period for analysis in accordance with the modifying of the aspect of the social network.

11. The method of claim 10, wherein the modifying of the aspect comprises:

providing the one or more users with an incentive to have a plurality of other users utilize a feature of the social network.

12. The method of claim 10, wherein the modifying of the aspect comprises:

providing the one or more users with a designated status in the social network.

13. A non-transitory machine-readable medium comprising instructions, which when implemented by one or more processors perform operations, comprising:

retrieving a strongly connected component value, an in-component value, an out-component value, a disconnected component value, a tendril value, and a tube value of a social network for a time period;

the strongly connected component value quantifying a number of strongly connected vertices where, for each strongly connected vertex, there is a first path from a first vertex to a second vertex and a second path from the second vertex to the first vertex, the first vertex and the second vertex corresponding to a first user and a second user, respectively, who act as buyers and sellers in transactions between themselves in the social network;

the in-component value quantifying a number of in vertices, each in vertex corresponding to a third user who acts as a seller to the first user;

the out-component value quantifying a number of out vertices, each out vertex corresponding to a fourth user who acts as a buyer from the second user;

the tube value quantifying a number of tube vertices, each tube vertex being between the third user and the fourth user that do not include the first user and the second user;

the tendril value quantifying a number of tendril vertices, each tendril vertex being a buyer from the third user or a seller to the fourth user but have not conducted a transaction with the first user or the second user;

the disconnected component value quantifying a number of vertices that are not quantified by the strongly connected component value, the in-component value, the out-component value, the tendril value, or the tube value;

calculating a social strength of the social network for the time period by applying a weighting factor to each of the strongly connected component value, the in-component value, the out-component value, the disconnected component value, the tendril value, and the tube value and summing the weighted values; and

utilizing the social strength of the social network for the time period for analysis of the social network,

wherein the strongly connected component value has the greatest weight and the disconnected component value has the lowest weight.

14. The non-transitory machine-readable medium of claim 13, wherein the retrieving includes:

determining the strongly connected component value in accordance with a graph percentage of a strongly connected component of the social network;

determining the in-component value in accordance with the graph percentage of an in-component of the social network;

determining the out-component value in accordance with the graph percentage of an out-component of the social network;

determining the disconnected component value in accordance with the graph percentage of a disconnected component of the social network;

determining the tendril value in accordance with the graph percentage of one or more tendrils of the social network; and

determining the tube value in accordance with the graph percentage of a tube of the social network.

15. The non-transitory machine-readable medium of claim 13, wherein the utilizing includes:

providing the social strength for a plurality of categories in the social network for the time period for presentation;

wherein the social strength is calculated for the plurality of categories in the social network for the time period.

16. A system comprising:

a value access module, have one or more processors, to retrieve a strongly connected component value, an in-component value, an out-component value, a disconnected component value, a tendril value, and a tube value of a social network for a time period;

the strongly connected component value quantifying a number of strongly connected vertices where, for each strongly connected vertex, there is a first path from a first vertex to a second vertex and a second path from the second vertex to the first vertex, the first vertex and the second vertex corresponding to a first user and a second user, respectively, who act as buyers and sellers in transactions between themselves in the social network;

the in-component value quantifying a number of in vertices, each in vertex corresponding to a third user who acts as a seller to the first user;

the out-component value quantifying a number of out vertices, each out vertex corresponding to a fourth user who acts as a buyer from the second user;

the tube value quantifying a number of tube vertices, each tube vertex being between the third user and the fourth user that do not include the first user and the second user;

the tendril value quantifying a number of tendril vertices, each tendril vertex being a buyer from the third user or a seller to the fourth user but have not conducted a transaction with the first user or the second user;

the disconnected component value quantifying a number of vertices that are not quantified by the strongly connected component value, the in-component value, the out-component value, the tendril value, or the tube value;

a social strength calculation module calculating a social strength of the social network for the time period by weighting each of the strongly connected component value, the in-component value, the out-component value, the disconnected component value, the tendril value, and the tube value accessed by the value access module and summing the weighted values; and

a social strength provider module to provide the social strength of the social network for the time period calculated by the social strength calculated module for presentation,

wherein the strongly connected component value has the greatest weight and the disconnected component value has the lowest weight.

17. The system of claim 16, further comprising:

a difference provider module to provide a difference between the social strength of the social network for the time period and an additional time period for presentation, wherein

the value access module further retrieves the strongly connected component value, the in-component value, the out-component value, the disconnected component value, the tendril value, and the tube value of the social network for the additional time period; and

the social strength calculation module further calculates the social strength of the social network for the additional time period by combining the strongly connected component value, the in-component value, the out-component value, the disconnected component value, the tendril value, and the tube value.

18. The system of claim 16, wherein the social network is an online marketplace.