Methods and systems useful for identifying the most influent social media users in query-based social data streams

• US 9,514,226 B2
• Filed: 04/30/2013
• Issued: 12/06/2016
• Est. Priority Date: 04/30/2012
• Status: Active Grant

• Current Assignee: uberVU Ltd. (Hootsuite, Inc.)
• Original Assignee: uberVU Ltd. (Hootsuite, Inc.)
• Inventors: Oane, Vladimir, Sandulescu, Bogdan
• Primary Examiner(s): Morrison, Jay
• Application Number:
  US13/874,454
• Publication Number:
  US 20130304726A1
• Time in Patent Office: 1,316 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: G06Q 10/101 Collaborative creation, e.g. joint development of products or services
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

The present invention relates to novel methods and implementing systems that afford a user the ability to analyze a certain stream of data, e.g., independent of size, and identify the people that influence the conversation.

Claims

1. A system comprising:

a non-transitory machine-readable medium having instructions stored thereon for execution by a processor to perform a method for identifying the most influent social media users in query-based social data streams comprising the steps of

interfacing with one or more streaming social data sources;

collecting one or more mentions that match a search query;

storing said mentions on a first server;

enhancing said mentions with additional information to produce enhanced mentions, wherein each enhanced mention is assigned an author node;

storing said enhanced mentions on a second server;

filtering said enhanced mentions into filtered streams;

creating a conversation graph from said filtered streams;

calculating influence scores from said conversation graph by iteratively assigning an influence score to each author node of each mention by computing the outreach of one author node towards the rest of the graph based on the individual probabilities found on each author node edge that the next connected node will amplify an action of said author node; and

outputting the most influent social media users.

2. The system of claim 1, wherein the instructions stored on the machine-readable medium are online software or offline software.

3. The system of claim 1, wherein the software is an online application.

4. The system of claim 3, wherein the software is a web-based application.

5. The system of claim 3, wherein the software is a cloud-based application.

6. The system of claim 1, wherein the software is an offline application.

7. The system of claim 1, wherein the data sources are selected from the group consisting of social networks, websites where an author can be uniquely identified, and any combination thereof.

8. The system of claim 1, wherein the machine-readable medium is selected from the group consisting of magnetic media, punched cards, paper tapes, optical disks, barcodes, magnetic ink characters, and solid state devices.

9. The system of claim 1, wherein the method further comprises the step of identifying an influent social media user.

10. The system of claim 1, wherein the method further comprises the step of reporting one or more of the most influent social media users.

11. The system of claim 1, wherein the first server is the same as the second server.

12. The system of claim 1, wherein the step of collecting the mentions further comprises establishing a search inquiry.

13. The system of claim 1, wherein the step of collecting the mentions may be limited by prescribed time interval or may be continual.

14. A method for identifying the most influent social media users in query-based social data streams comprising the steps of

interfacing with one or more streaming social data sources;

collecting one or more mentions that match a search query;

storing said mentions on a first server;

enhancing said mentions with additional information to produce enhanced mentions, wherein each enhanced mention is assigned an author node;

storing said enhanced mentions on a second server;

filtering said enhanced mentions into filtered streams;

creating a conversation graph from said filtered streams;

calculating influence scores from said conversation graph by iteratively assigning an influence score to each author node of each mention by computing the outreach of one author node towards the rest of the graph based on the individual probabilities found on each author node edge that the next connected node will amplify an action of said author node; and

outputting the most influent social media users,

such that the most influent social media users for the streaming social data sources are identified.

15. The method of claim 14, wherein the method further comprises the step of identifying an influent social media user.

16. The method of claim 14, wherein the method further comprises the step of reporting one or more of the most influent social media users.

17. The method of claim 14, wherein the first server is the same as the second server.

18. The method of claim 14, wherein the step of collecting the mentions further comprises establishing a search inquiry.

19. The method of claim 14, wherein the step of collecting the mentions may be limited by prescribed time interval or may be continual.

20. The method of claim 14, wherein the data sources are selected from the group consisting of social networks, websites where an author can be uniquely identified, and any combination thereof.