Generating and using socially-curated brains

1. A system, comprising:

one or more memory units operable to store a plurality of tweets; and

one or more processing units operable to:

determine, from the stored plurality of tweets, a first group of tweets, each tweet of the first group of tweets comprising a link to a link object on the Internet;

apply a filter to the first group of tweets in order to determine a plurality of filtered tweets;

retrieve a copy of each of the link objects linked to by the plurality of filtered tweets;

generate, using the retrieved copies of the link objects linked to by the plurality of filtered tweets, a matrix comprising a plurality of vectors;

produce a singular value representation of the matrix by performing Singular Value Decomposition (SVD) on the matrix;

store the singular value representation of the matrix in the one or more memory units; and

perform a query using at least a portion of the singular value representation of the matrix:

wherein applying the filter to the first group of tweets in order to determine the plurality of filtered tweets comprises:

selecting tweets from the first group of tweets that include links to link objects that have been linked to by a predetermined number of other tweets; and

selecting tweets from the first group of tweets that have been retweeted a predetermined number of times or have been retweeted by a predetermined number of users.

2. The system of claim 1 , wherein the link objects comprise one or more of:

webpages;

Portable Document Format (PDF) documents;

text documents;

posts to social-media websites;

videos;

music; and

images.

3. The system of claim 1 , wherein the plurality of tweets are retrieved using a feed from a social-networking website.

4. A computer-implemented method, comprising:

determining a plurality of social objects, each social object comprising a link to a link object on a network;

applying a filter to the determined social objects in order to determine a plurality of filtered social objects;

retrieving a copy of each of the link objects linked to by the plurality of filtered social objects;

generating, using the retrieved copies of the link objects linked to by the plurality of filtered social objects, a matrix comprising a plurality of vectors;

generating a singular value representation of the matrix by performing Singular Value Decomposition (SVD) on the matrix;

storing the singular value representation of the matrix in one or more memory units; and

performing a query using at least a portion of the singular value representation of the matrix;

wherein applying the filter to the determined social objects in order to determine the plurality of filtered social objects comprises:

selecting social objects with links to link objects that have been linked to in other social objects a first predetermined number of times; and

selecting social objects that have been re-posted a second predetermined number of times or have been re-posted by a predetermined number of users.

5. The computer-implemented method of claim 4 , wherein the plurality of social objects comprises one or more of:

tweets;

messages associated with a corporate network;

posts to a social-network; and

blogs.

6. The computer-implemented method of claim 4 , wherein the network comprises one of:

the Internet; and

a network of a corporation.

7. The computer-implemented method of claim 4 , further comprising:

presenting results of the query to a user using a graphical user interface.

8. The computer-implemented method of claim 4 , wherein applying the filter to the determined social objects in order to determine the plurality of filtered social objects further comprises one or more of:

selecting social objects that have been up-voted or liked a third predetermined number of times;

selecting social objects that have been shared a fourth predetermined number of times; and

selecting social objects associated with a predefined topmost percentage of users of a social network according to number of social connections within the social network.

9. The computer-implemented method of claim 4 , wherein the link objects comprise one or more of:

webpages;

Portable Document Format (PDF) documents;

text documents;

posts to social-media websites;

videos;

music; and

images.

10. The computer-implemented method of claim 4 , wherein the plurality of social objects are determined from a feed from a social network.

11. A non-transitory computer-readable medium comprising software, the software when executed by one or more processing units operable to perform operations comprising:

determining a plurality of social objects, each social object comprising a link to a link object on a network;

applying a filter to the determined social objects in order to determine a plurality of filtered social objects;

retrieving a copy of each of the link objects linked to by the plurality of filtered social objects;

generating, using the retrieved copies of the link objects linked to by the plurality of filtered social objects, a matrix comprising a plurality of vectors;

generating a singular value representation of the matrix by performing Singular Value Decomposition (SVD) on the matrix;

storing the singular value representation of the matrix in one or more memory units; and

performing a query using at least a portion of the singular value representation of the matrix;

wherein applying the filter to the determined social objects in order to determine the plurality of filtered social objects comprises:

selecting social objects with links to link objects that have been linked to in other social objects a first predetermined number of times; and

selecting social objects that have been re-posted a second predetermined number of times or have been re-posted by a predetermined number of users.

12. The non-transitory computer-readable medium of claim 11 , wherein the plurality of social objects comprises one or more of:

tweets;

messages associated with a corporate network;

posts to a social-network; and

blogs.

13. The non-transitory computer-readable medium of claim 11 , wherein the network comprises one of:

the Internet; and

a network of a corporation.

14. The non-transitory computer-readable medium of claim 11 , further comprising:

presenting results of the query to a user using a graphical user interface.

15. The non-transitory computer-readable medium of claim 11 , wherein applying the filter to the determined social objects further comprises one or more of:

selecting social objects that have been up-voted or liked a third predetermined number of times; and

selecting social objects that have been shared a fourth predetermined number of times.

16. The non-transitory computer-readable medium of claim 11 , wherein the link objects comprise one or more of:

webpages;

Portable Document Format (PDF) documents;

text documents;

posts to social-media websites;

videos;

music;

images.

17. The non-transitory computer-readable medium of claim 11 , wherein the plurality of social objects are determined from a feed from a social network.

18. The non-transitory computer-readable medium of claim 11 , wherein:

the plurality of social objects are associated with a plurality of users of a social network; and

applying the filter to the determined social objects further comprises selecting social objects associated with a predefined topmost percentage of users of the social network according to number of social connections within the social network.