WEB CONTENT CHARACTERIZATION BASED ON SEMANTIC FOLKSONOMIES ASSOCIATED WITH USER GENERATED CONTENT

• US 20100010982A1
• Filed: 07/09/2008
• Published: 01/14/2010
• Est. Priority Date: 07/09/2008
• Status: Abandoned Application

• Current Assignee: Oath Inc. (Verizon Communications Inc.)
• Original Assignee: Oath Inc. (Verizon Communications Inc.)
• Inventors: Josifovski, Vanja, Pang, Bo, Gabrilovich, Evgeniy, Broder, Andrei Z.
• Application Number:
  US12/169,761
• Publication Number:
  US 20100010982A1
• Time in Patent Office: Days
• US Class Current: N/A
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking

Abstract

The present invention is directed towards a method and system for characterizing web content based on capturing semantics of folksonomies relating to content entities of user generated content. The method and system includes determining a plurality of tags that describe a plurality of content entities and determining a co-occurrence of the tags. The method and system further includes generating weighted vectors based on the determined co-occurrence of tags and characterizing the content entity based on the weight vectors. Thereby, the characterization of the content entity may be used for any number of suitable purposes, including, by way of example, improving search results and associated advertising relevancy.

Claims

1. A method for characterizing web content based on capturing semantics of folksonomies relating to content entities of user generated content (UGC), the method comprising:

determining a plurality of tags that describe a plurality of the content entities;

determining a co-occurrence of the tags;

generating weighted vectors based on the determined co-occurrence of tags; and

characterizing the content entity based on the weighted vectors.

2. The method of claim 1 further comprising:

receiving a search request including at least one search term; and

determining the content entities based on the search request.

3. The method of claim 2 further comprising:

accessing an advertising database using the content entity characterization; and

receiving an advertisement from the advertising database, the advertisement selected based on the content entity characterization.

4. The method of claim 3 further comprising:

inserting the advertisement in a page display including the content entity.

5. The method of claim 4, wherein a page display includes a search results page.

6. The method of claim 1, wherein the determination of co-occurrence of tags includes:

generating a square matrix, each column including at least one of the tags and each row including the same at least one of the tags; and

incrementing a counter value for each of the matrix entries for each co-occurrence of tags.

7. The method of claim 6 further comprising:

generating the weighted vectors using the counter values for each of the matrix entries.

8. The method of claim 7, wherein the generation of the weighted vectors includes a TFIDF weighting scheme.

9. The method of claim 1, wherein the tags include more then one word.

10. The method of claim 1 further comprising:

accessing a self-learning resource in determining the co-occurrence of the tags.

11. A system for characterizing web content based on capturing semantics of folksonomies relating to content entities of user generated content (UGC), the system comprising:

a memory device having executable instructions stored therein; and

a processing device, in response to the executable instructions;

operative to;

determine a plurality of tags that describe a plurality of the content entities;

determine a co-occurrence of the tags;

generate weighted vectors based on the determined co-occurrence of tags; and

characterize the content entity based on the weighted vectors.

12. The system of claim 11, the processing device, in response to further executable instructions, further operative to:

receive a search request including at least one search term; and

determine the content entities based on the search request.

13. The system of claim 12 further comprising:

an advertising database; and

the processing device further operative to;

access the advertising database using the content entity characterization; and

receive an advertisement from the advertising database, the advertisement selected based on the content entity characterization.

14. The system of claim 13, the processing device further operative to:

insert the advertisement in a page display including the content entity.

15. The system of claim 14, wherein a page display includes a search results page.

16. The system of claim 11, wherein the determination of co-occurrence of tags includes:

generating a square matrix, each column including at least one of the tags and each row including the same at least one of the tags; and

incrementing a counter value for each of the matrix entries for each co-occurrence of tags.

17. The system of claim 16, the processing device further operative to:

generate the weighted vectors using the counter values for each of the matrix entries.

18. The system of claim 17, wherein the generation of the weighted vectors includes a TFIDF weighting scheme.

19. The system of claim 11, wherein the tags include more then one word.

20. The system of claim 11 further comprising:

a self-learning resource in operative communication with the processing device; and

the processing device further operative to access the self-learning resource in determining the co-occurrence of the tags.