Systems and methods for improving the ranking of news articles

• US 8,332,382 B2
• Filed: 02/24/2012
• Issued: 12/11/2012
• Est. Priority Date: 09/16/2003
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Curtiss, Michael, Bharat, Krishna, Schmitt, Michael
• Primary Examiner(s): PARDO, THUY N
• Application Number:
  US13/404,827
• Publication Number:
  US 20120158711A1
• Time in Patent Office: 291 Days
• Field of Search: 707/721, 707/706, 707/720, 707/723, 707/728, 707/730
• US Class Current: 707/706
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99937 Sorting
• CPC Class Codes: Y10S 707/99942 Manipulating data structure, e.g. compression, compaction, compilation
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A system ranks results. The system may receive a list of links. The system may identify a source with which each of the links is associated and rank the list of links based at least in part on a quality of the identified sources.

Claims

1. A computer-implemented method comprising:

obtaining, in response to receiving a search query, articles and respective scores;

identifying, using one or more processors, for an article of the articles, a source with which the article is associated;

determining, using one or more processors, a score for the source, based on polling one or more users to request the one or more users to provide a metric that represents an evaluation of a source and based on a length of time between an occurrence of an event and publication, by the source, of another article associated with the event; and

adjusting, using one or more processors, the score of the article based on the score for the source.

2. The method of claim 1, where identifying the source includes identifying the source based on an address associated with the article.

3. The method of claim 1, where adjusting the score of the article includes:

determining, using the score for the source, a new score for the article associated with the source; and

adjusting the score of the article based on the determined new score.

4. The method of claim 1, where the score for the source is further based on a usage pattern indicating traffic associated with the source.

5. The method of claim 1, where the score for the source is further based on a number of entities, associated with the source, that are associated with only one article in a cluster of related articles.

6. The method of claim 1, where the score for the source is further based on a value representing international diversity of the source.

7. A system comprising:

one or more server devices to;

receive a search query;

obtain, for the search query, articles and respective scores;

identify, using one or more processors, for an article, a source with which the score is associated;

determine, using one or more processors, a score for the source, the score being based on polling one or more users to request the one or more users to provide a metric that represents an evaluation of a source and based on a length of time between an occurrence of an event and publication, by the source, of another article associated with the event; and

adjust, using one or more processors, the score of the article based on the score for the source.

8. The system of claim 7, where, when identifying the source, the at least one of the one or more server devices is further to identify the source based on an address associated with the article.

9. The system of claim 7, where, when adjusting the score of the article, at least one of the one or more server devices is further to:

determine, using the determined score for the source, a new score for the article associated with the source; and

adjust the score of the article based on the determined new score.

10. The system of claim 7, where the score for the source is further based on a usage pattern indicating traffic associated with the source.

11. The system of claim 7, where the score for the source is further based on a number of entities, associated with the source, that are associated with only one article in a cluster of related articles.

12. The system of claim 7, where the score for the source is further based on a value representing international diversity of the source.

13. A computer-implemented method comprising:

obtaining a list of references to articles;

identifying, using one or more processors, for an article in the list of articles, a source with which the article is associated;

determining, using one or more processors, a score for the source, the score being based on a value representing human opinion of the source, the human opinion being based on a poll of users that identifies user opinions of the sources, the score further being based on a length of time between an occurrence of an event and publication, by the source, of another article associated with the event; and

ranking, using one or more processors, the article in the list of articles based on the score for the source.

14. The method of claim 13, where identifying the source includes identifying the source based on an address associated with the article.

15. The method of claim 13, where the score is further based on a usage pattern indicating traffic associated with the source.

16. The method of claim 13, where the score is further based on a number of entities, associated with the source, that are associated with only one article in a cluster of related articles.

17. The method of claim 13, where the score is further based on a value representing international diversity of the source.

18. A system comprising:

one or more server devices to;

obtain a list of references to articles;

identify, for an article in the list of articles, a source with which the article is associated;

determine, using one or more processors, a score for the source, the score being based on a value representing human opinion of the source, the human opinion being based on a poll of users that identifies user opinions of the sources, the score further being based on a length of time between an occurrence of an event and publication, by the source, of another article associated with the event; and

rank the article in the list of articles based on the score for the source.

19. The system of claim 18, where, when identifying the source, the one or more server devices are further to identify the source based on an address associated with the article.

20. The system of claim 18, where the score is further based on a usage pattern indicating traffic associated with the source.

21. The system of claim 18, where the score is further based on a number of entities, associated with the source, that are associated with only one article in a cluster of related articles.

22. The system of claim 18, where the score is further based on a value representing international diversity of the source.

23. A non-transitory computer-readable medium containing instructions executable by one or more processors, the instructions comprising:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to;

receive a search query;

obtain, for the search query, articles and respective scores;

identify, using one or more processors, for an article, a source with which the score is associated;

determine, using one or more processors, a score for the source, the score being based on polling one or more users to request the one or more users to provide a metric that represents an evaluation of a source and based on a length of time between an occurrence of an event and publication, by the source, of another article associated with the event; and

adjust, using one or more processors, the score of the article based on the score for the source.

24. The computer-readable medium of claim 23, where the one or more instructions that cause the one or more processors to identify the source include one or more instructions that cause the one or more processors to identify the source based on an address associated with the article.

25. The computer-readable medium of claim 23, where the one or more instructions that cause the one or more processors to adjust the score of the article include:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to;

determine, using the determined score for the source, a new score for the article associated with the source; and

adjust the score of the article based on the determined new score.

26. The computer-readable medium of claim 23, where the score for the source is further based on a usage pattern indicating traffic associated with the source.

27. The computer-readable medium of claim 23, where the score for the source is further based on a number of entities, associated with the source, that are associated with only one article in a cluster of related articles.

28. The computer-readable medium of claim 23, where the score for the source is further based on a value representing international diversity of the source.

29. A non-transitory computer-readable medium containing instructions executable by one or more processors, the instructions comprising:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to;

obtain a list of references to articles;

identify, for an article in the list of articles, a source with which the article is associated;

determine, using one or more processors, a score for the source, the score being based on a value representing human opinion of the source, the human opinion being based on a poll of users that identifies user opinions of the sources, the score further being based on a length of time between an occurrence of an event and publication, by the source, of another article associated with the event; and

rank the article in the list of articles based on the score for the source.

30. The computer-readable medium of claim 29, where the one or more instructions that cause the one or more processors to identify the source include one or more instructions that cause the one or more processors to identify the source based on an address associated with the article.

31. The computer-readable medium of claim 29, where the score is further based on a usage pattern indicating traffic associated with the source.

32. The computer-readable medium of claim 29, where the score is further based on a number of entities, associated with the source, that are associated with only one article in a cluster of related articles.

33. The computer-readable medium of claim 29, where the score is further based on a value representing international diversity of the source.