Method and apparatus for rating user generated content in search results

• US 7,949,643 B2
• Filed: 04/29/2008
• Issued: 05/24/2011
• Est. Priority Date: 04/29/2008
• Status: Expired due to Fees

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Kawale, Jaya, Pal, Aditya
• Primary Examiner(s): Wong; Don
• Assistant Examiner(s): DANG, THANH HA T
• Application Number:
  US12/111,257
• Publication Number:
  US 20090271391A1
• Time in Patent Office: 1,120 Days
• Field of Search: 707/722, 707/723, 707/724, 707/725, 707/726, 707/727, 707/728, 707/729, 707/730, 707/731, 707/999.005, 707/706, 707/708, 707/748, 707/750, 707/751, 705/14, 705/14.6, 705/347
• US Class Current: 707/706
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Generally, a method and apparatus provides for rating user generated content (UGC) with respect to search engine results. The method and apparatus includes recognizing a UGC data field collected from a web document located at a web location. The method and apparatus calculates: a document goodness factor for the web document; an author rank for an author of the UGC data field; and a location rank for web location. The method and apparatus thereby generates a rating factor for the UGC field based on the document goodness factor, the author rank and the location rank. The method and apparatus also outputs a search result that includes the UGC data field positioned in the search results based on the rating factor.

Claims

1. A method for ranking web documents including user generated content (UGC) with respect to search results generated by a search engine, the search results comprising a set of web documents belonging to a plurality of root categories, the method comprising:

recognizing a UGC data field collected from a web document located at a web location, the web document belonging to at least one root category of the plurality of root categories;

calculating a document goodness factor for the web document, the document goodness factor measuring overall quality of the web document;

calculating an author rank for an author of the UGC data field;

calculating a web location rank for the web location;

generating a rating factor for the UGC data field based on the document goodness factor, the author rank and the web location rank;

boosting the web document in a search result set of web documents to a higher ranking above another web document based on the at least one root category that the web document belongs having more web documents in the result set belonging thereto than the another of the web document in the search set while applying a damping factor in determining whether to boost the web document, the damping factor minimizes penalizing the another web document in the result set as a result of belonging to a root category having less web documents in the result set than the web document, wherein the damping factor is a function of a difference between a number of documents in a first category and a number of documents in a second category divided by a total number of documents in at least the first and the second categories; and

outputting a search result including the UGC data field positioned in the search results based on the rating factor and the damping factor.

2. The method of claim 1, further comprising:

normalizing the document goodness factor, the author rank and the web location rank; and

generating the rating factor for the UGC data field by combining the normalized document goodness factor, the normalized author rank and the normalized web location rank.

3. The method of claim 2, wherein the generation of the rating factor includes supervised learning.

4. The method of claim 1, wherein the document goodness factor is based on document attributes, the document attributes including at least one of:

a user rating;

a frequency of posts before and after the document is posted;

a document'"'"'s contextual affinity with a parent document;

a page click/view number for the document;

assets in the document;

document length;

length of a thread in which the document lies; and

goodness of a child document.

5. The method of claim 1, wherein the author rank is based on author rank attributes, the author rank attributes including at least one of:

a number of relevant posted messages;

a number of irrelevant posted messages;

a total number of root documents post by the author within a prescribed time period;

a total number of replies or comments made by the author; and

a number of groups to which the author is a member.

6. The method of claim 1, wherein the web location rank is based on location rank attributes, the location rank attributes including at least one of:

an activity rate in the web location;

a number of unique users in the web location;

an average document goodness factor of documents in the web location;

an average author rank of users in the web location; and

an external rank of the web location.

7. An apparatus for ranking web documents including user generated content (UGC) with respect to search results generated by a search engine, the search results comprising a set of web documents belonging to a plurality of root categories, the apparatus comprising:

a computer readable medium having executable instructions stored thereon; and

a processing device, in response to the executable instructions, operative to;

recognize a UGC data field collected from a web document located at a web location, the web document belonging to at least one root category of the plurality of root categories;

calculate a document goodness factor for the web document, the document goodness factor measuring overall quality of the web document;

calculate an author rank for an author of the UGC data field;

calculate a web location rank for the web location;

generate a rating factor for the UGC data field based on the document goodness factor, the author rank and the web location rank;

boosting the web document in a search result set of web documents to a higher ranking above another web document based on the at least one root category that the web document belongs having more web documents in the result set belonging thereto than the another of the web document in the search set while applying a damping factor in determining whether to boost the web document, the damping factor minimizes penalizing the another web document in the result set as a result of belonging to a root category having less web documents in the result set than the web document, wherein the damping factor is a function of a difference between a number of documents in a first category and a number of documents in a second category divided by a total number of documents in at least the first and the second categories; and

output a search result including the UGC data field positioned in the search results based on the rating factor and the damping factor.

8. The apparatus of claim 7, the processing device, in response to the executable instructions, is further operative to:

normalize the document goodness factor, the author rank and the web location rank; and

generate the rating factor for the UGC data field by combining the normalized document goodness factor, the normalized author rank and the normalized web location rank.

9. The apparatus of claim 8, wherein the generation of the rating factor includes supervised learning.

10. The apparatus of claim 7, wherein the document goodness factor is based on document attributes, the document attributes including at least one of:

a user rating;

a frequency of posts before and after the document is posted;

a document'"'"'s contextual affinity with a parent document;

a page click/view number for the document;

assets in the document;

document length;

length of a thread in which the document lies; and

goodness of a child document.

11. The apparatus of claim 7, wherein the author rank is based on author rank attributes, the author rank attributes including at least one of:

a number of relevant posted messages;

a number of irrelevant posted messages;

a total number of root documents post by the author within a prescribed time period;

a total number of replies or comments made by the author; and

a number of groups to which the author is a member.

12. The apparatus of claim 7, wherein the web location rank is based on location rank attributes, the location rank attributes including at least one of:

an activity rate in the web location;

a number of unique users in the web location;

an average document goodness factor of documents in the web location;

an average author rank of users in the web location; and

an external rank of the web location.

13. A computer readable medium having executable instructions stored thereon, when read by a processing device, the executable instructions provide a method for ranking web documents including user generated content (UGC) with respect to search results generated by a search engine, the search results comprising a set of web documents belonging to a plurality of root categories, the method comprising:

recognizing a UGC data field collected from a web document located at a web location, the web document belonging to at least one root category of the plurality of root categories;

calculating a document goodness factor for the web document, the document goodness factor measuring overall quality of the web document;

calculating an author rank for an author of the UGC data field;

calculating a web location rank for the web location;

generating a rating factor for the UGC data field based on the document goodness factor, the author rank and the web location rank;

boosting the web document in a search result set of web documents to a higher ranking above another web document based on the at least one root category that the web document belongs having more web documents in the result set belonging thereto than the another of the web document in the search set while applying a damping factor in determining whether to boost the web document, the damping factor minimizes penalizing the another web document in the result set as a result of belonging to a root category having less web documents in the result set than the web document, wherein the damping factor is a function of a difference between a number of documents in a first category and a number of documents in a second category divided by a total number of documents in at least the first and the second categories; and

outputting a search result including the UGC data field positioned in the search results based on the rating factor and the damping factor.

14. The computer readable medium of claim 13, where the method further includes:

normalizing the document goodness factor, the author rank and the web location rank; and

generating the rating factor for the UGC data field by combining the normalized document goodness factor, the normalized author rank and the normalized web location rank.

15. The computer readable medium of claim 13, wherein the document goodness factor is based on document attributes, the document attributes including at least one of:

a user rating;

a frequency of posts before and after the document is posted;

a document'"'"'s contextual affinity with a parent document;

a page click/view number for the document;

assets in the document;

document length;

length of a thread in which the document lies; and

goodness of a child document.

16. The computer readable medium of claim 13, wherein the author rank is based on author rank attributes, the author rank attributes including at least one of:

a number of relevant posted messages;

a number of irrelevant posted messages;

a total number of root documents post by the author within a prescribed time period;

a total number of replies or comments made by the author; and

a number of groups to which the author is a member.

17. The computer readable medium of claim 13, wherein the web location rank is based on location rank attributes, the location rank attributes including at least one of:

an activity rate in the web location;

a number of unique users in the web location;

an average document goodness factor of documents in the web location;

an average author rank of users in the web location; and

an external rank of the web location.