Computer-implemented system and method for populating clusters of documents

1. A computer-implemented system for populating clusters of documents, comprising:

a presentation module to place a set of clusters in a display in relation to a common origin;

a document selection module to select one of a plurality of unclustered documents in the display and to determine an angle θ of the document from the common origin;

a cluster placement module to compute for each cluster, an angle σ of the cluster relative to the common origin;

a placement calculation module to determine a difference between the document angle θ and one such cluster angle σ;

a predetermined variance applied to the difference; and

a clustering module to place the document into the cluster when the difference is less than the variance.

2. A system according to claim 1 , further comprising:

a cluster generator to form the clusters based on themes.

3. A system according to claim 1 , further comprising:

a theme generator to generate the themes, comprising:

a frequency determination module to determine a frequency of each term within each unclustered document;

a theme mapping module to map the frequencies of the terms across all the unclustered documents; and

a theme determination module to apply a predetermined range of frequencies to the mapped frequencies and to designate those terms that fall within the threshold as the themes for the unclustered documents.

4. A system according to claim 1 , further comprising:

a vector placement module to position the clusters along one or more vectors extending from the common origin.

5. A system according to claim 4 , further comprising:

a theme identification module to identify the clusters along a common vector having a similar theme.

6. A system according to claim 5 , further comprising:

a cluster designation module to designate the clusters along the common vector as having a theme similar to those clusters located along other vectors positioned at a small cosign rotation from the common vector.

7. A system according to claim 1 , further comprising:

a radius determination module to determine a radius of each cluster, wherein the radius reflects a relative number of documents included in that cluster.

8. A system according to claim 1 , further comprising:

a finalization module to finalize the clusters, comprising at least one of:

a merge module to merge two or more of the clusters into a single cluster;

a split module to split a single cluster into two or more clusters; and

a removal module to remove minimal and outlier clusters.

9. A system according to claim 1 , wherein the clusters each comprise one of a circular and a non-circular shape within the display.

10. A system according to claim 1 , further comprising:

an cluster update module to redetermine the cluster angle σ for one such cluster following at least one of placement of a document into and removal of a document from that cluster.

11. A computer-implemented method for populating clusters of documents, comprising:

placing a set of clusters in a display in relation to a common origin;

selecting one of a plurality of unclustered documents in the display and determining an angle θ of the document from the common origin;

computing for each cluster, an angle σ of the cluster relative to the common origin;

determining a difference between the document angle θ and one such cluster angle σ;

applying a predetermined variance to the difference; and

placing the document into the cluster when the difference is less than the variance.

12. A method according to claim 11 , further comprising:

forming the clusters based on themes.

13. A method according to claim 11 , further comprising:

generating the themes, comprising:

determining a frequency of each term within each unclustered document;

mapping the frequencies of the terms across all the unclustered documents;

applying a predetermined range of frequencies to the mapped frequencies; and

designating those terms that fall within the threshold as the themes for the unclustered documents.

14. A method according to claim 11 , further comprising:

positioning the clusters along one or more vectors extending from the common origin.

15. A method according to claim 14 , further comprising:

identifying the clusters along a common vector as having a similar theme.

16. A method according to claim 15 , further comprising:

designating the clusters along the common vector as having a theme similar to those clusters located along other vectors positioned at a small cosign rotation from the common vector.

17. A method according to claim 11 , further comprising:

determining a radius of each cluster, wherein the radius reflects a relative number of documents included in that cluster.

18. A method according to claim 11 , further comprising:

finalizing the clusters, comprising at least one of:

merging two or more clusters into a single cluster;

splitting a single cluster into two or more clusters; and

removing minimal and outlier clusters.

19. A method according to claim 11 , wherein the clusters each comprise one of a circular and a non-circular shape within the display.

20. A method according to claim 11 , further comprising:

redetermining the cluster angle σ for one such cluster following at least one of placement of a document into and removal of a document from that cluster.

21. A non-transitory computer readable storage medium storing code for executing on a computer system to perform the method according to claim 11 .