Systems and methods for improving the ranking of news articles

• US 20050060312A1
• Filed: 09/16/2003
• Published: 03/17/2005
• Est. Priority Date: 09/16/2003
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Schmitt, Michael, Bharat, Krishna, Curtiss, Michael
• Granted Patent: US 7,577,655 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• 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 method for ranking results, comprising:

receiving a list of links;

identifying, for each of the links, a source with which the link is associated; and

ranking the list of links based at least in part on a quality of the identified sources.

2. The method of claim 1 wherein the identifying a source includes:

identifying the source based at least in part on a uniform resource locator (URL) associated with the link.

3. The method of claim 1 wherein at least some of the identified sources are news sources.

4. The method of claim 1 wherein the ranking includes:

retrieving a source rank value for each identified source, the source rank value being based at least in part on one or more of a number of articles produced by the identified source during a first time period, an average length of an article produced by the identified source, an amount of important coverage that the identified source produces in a second time period, a breaking news score, network traffic to the identified source, a human opinion of the identified source, circulation statistics of the identified source, a size of a staff associated with the identified source, a number of bureaus associated with the identified source, a number of original named entities in a group of articles associated with the identified source, a breadth of coverage by the identified source, a number of different countries from which traffic to the identified source originates, and a writing style used by the identified source.

5. The method of claim 1 wherein the list of links is a ranked list of links, and

wherein the ranking includes:

adjusting the ranked list of links based at least in part on a quality of the identified sources.

6. The method of claim 1 wherein the links include links to on-line news articles.

7. The method of claim 1 further comprising:

determining the list of links based at least in part on one or more of a search query, a topic, a list of one or more keywords, a geographical area, and a set of documents.

8. A system for adjusting a ranking of search results, comprising:

means for receiving a list of objects;

means for identifying, for each object in the list, a source to which the object is associated; and

means for ranking the list of objects based at least in part on the sources with which the objects are associated.

9. A server comprising:

a memory configured to store quality indicators for a plurality of sources; and

a processor configured to;

receive a list of objects,

identify a source with which each of the objects is associated, and

rank at least one object in the list of objects based at least in part on the quality indicator associated with the source with which the one object is associated.

10. A computer-readable medium containing instructions for controlling at least one processor to perform a method for ranking a list of objects retrieved in response to a search query, the method comprising:

identifying a source with which each of the retrieved objects in the list of objects is associated; and

ranking at least one object in the list of objects based at least in part on a quality indicator associated with the source with which the one object is associated.

11. A method for determining a quality of a news source, the method comprising:

determining one or more metric values for the news source based at least in part on at least one of a number of articles produced by the news source during a first time period, an average length of an article produced by the news source, an amount of important coverage that the news source produces in a second time period, a breaking news score, an amount of network traffic to the news source, a human opinion of the news source, circulation statistics of the news source, a size of a staff associated with the news source, a number of bureaus associated with the news source, a number of original named entities in a group of articles associated with the news source, a breadth of coverage by the news source, a number of different countries from which network traffic to the news source originates, and a writing style used by the news source; and

generating a quality value for the news source based at least in part on the determined one or more metric values.

12. The method of claim 11 wherein the determining includes:

determining a plurality of metric values for the news source.

13. The method of claim 12 wherein the generating includes:

multiplying each metric value in the plurality of metric values by a factor to create a plurality of adjusted metric values, and

adding the plurality of adjusted metric values to obtain the quality value.

14. The method of claim 13 wherein the plurality of metric values includes a predetermined number of highest metric values for the news source.

15. The method of claim 12 wherein the generating includes:

normalizing each metric value in the plurality of metric values, and

adding the plurality of normalized metric values to obtain the quality value.

16. The method of claim 15 wherein the plurality of metric values includes a predetermined number of highest metric values for the news source.

17. The method of claim 12 wherein the generating includes:

adding the plurality of metric values for the news source to produce a total value,

obtaining the quality value by dividing the total value by a quantity of metric values in the plurality of metric values.

18. The method of claim 17 wherein the plurality of metric values includes a predetermined number of highest metric values for the news source.

19. The method of claim 12 wherein the generating includes:

determining, for each metric value in the plurality of metric values, a percentile score relative to a highest value for that metric,

adding the percentile scores to obtain the quality value.

20. The method of claim 19 wherein the plurality of metric values includes a predetermined number of highest metric values for the news source.

21. The method of claim 11 further comprising:

repeating the determining and generating for a plurality of other sources, at least one of the plurality of other sources including a different news source; and

storing the quality values for the news source and the plurality of other sources.

22. The method of claim 11 further comprising:

using the quality value to rank an object associated with the news source.

23. The method of claim 11 wherein the determining includes:

determining an importance metric value representing the amount of important coverage that the news source produces in a second time period, and

wherein the determining an importance metric includes;

determining, for each article produced by the news source during the second time period, a number of other non-duplicate articles on a same subject produced by other news sources to produce an importance value for the article, and

adding the importance values to obtain the importance metric value.

24. The method of claim 11 wherein the determining includes:

determining a breaking news metric value representing the breaking news score, and

wherein the determining a breaking news metric value includes;

identifying, for at least one article produced by the news source, a first time value at which the at least one article was published by the news source,

identifying a second time value that an initial article published on a same subject as the at least one article,

subtracting the second time value from the first time value to determine a difference time value,

comparing the difference time value to a threshold value, and

assigning a value to the breaking news metric value based at least in part on the comparing.

25. The method of claim 24 wherein the determining a breaking news metric value further includes:

identifying a group of articles from other news sources that are on a same subject as the at least one article,

multiplying the value by a quantity proportional to a size of the group of articles from the other news sources prior to assigning the value to the breaking news metric value.

26. The method of claim 11 wherein in determining the one or more metric values, non-duplicate articles are weighted differently than duplicate articles.

27. A server comprising:

a memory; and

a processor configured to;

determine one or more metric values for a news source based at least in part on at least one of a number of articles produced by the news source during a first time period, an average length of an article produced by the news source, an amount of important coverage that the news source produces in a second time period, a breaking news score, an amount of network traffic to the news source, a human opinion of the news source, circulation statistics of the news source, a size of a staff associated with the news source, a number of bureaus associated with the news source, a number of original named entities in a group of articles associated with the news source, a breadth of coverage by the news source, a number of different countries from which network traffic to the news source originates, and a writing style used by the news source,

determine a quality value for the news source based at least in part on the determined one or more metric values, and

store the quality value in the memory.

28. A computer-readable medium containing instructions for controlling at least one processor to perform a method for determining a quality of sources, the method comprising:

determining, for each source of a plurality of sources, one or more metric values based at least in part on at least one of a number of articles produced by the source during a first time period, an average length of an article produced by the source, an amount of important coverage that the source produces in a second time period, a breaking news score, an amount of network traffic to the source, a human opinion of the source, circulation statistics of the source, a size of a staff associated with the source, a number of bureaus associated with the source, a number of original named entities in a group of articles associated with the source, a breadth of coverage by the source, a number of different countries from which network traffic to the source originates, and a writing style used by the source; and

determining a quality value for each source of the plurality of sources based at least in part on the determined one or more metric values for the source.

29. A method for providing search results, the method comprising:

receiving a list of objects;

identifying a source with which each of the objects in the plurality of objects is associated;

determining a quality of each of the identified sources; and

ranking each object of the plurality of objects based at least in part on the determined quality of the source with which the object is associated.

30. The method of claim 29 wherein the determining a quality of each of the identified sources includes:

determining, for each of the identified sources, one or more metric values based at least in part on at least one of a number of articles produced by the source during a first time period, an average length of an article produced by the source, an amount of important coverage that the source produces in a second time period, a breaking news score, an amount of network traffic to the source, a human opinion of the source, circulation statistics of the source, a size of a staff associated with the source, a number of bureaus associated with the source, a number of original named entities in a group of articles associated with the source, a breadth of coverage by the source, a number of different countries from which network traffic to the source originates, and a writing style used by the source, and

generating a quality for each of the identified sources based at least in part on the determined one or more metric values for the source.

31. The method of claim 29 wherein the plurality of objects includes on-line news articles.