Technology for visualizing clusters of electronic documents

1. A computer-implemented method of generating data visualizations, the method comprising:

accessing a set of clusters, wherein each of the set of clusters includes a portion of a set of electronic documents;

displaying, in a user interface, a first representation of a first cluster of the set of clusters, the first representation having a first size indicative of an amount of the portion of the set of electronic documents included in the first cluster;

displaying, in the user interface, a second representation of a second cluster of the set of clusters, the second representation having a second size indicative of an amount of the portion of the set of electronic documents included in the second cluster, the second representation displayed a first distance from the first representation, the first distance representative of a similarity between the portion of the set of electronic documents included in the first cluster and the portion of the set of electronic documents included in the second cluster;

displaying, in the user interface, a third representation of a third cluster of the set of clusters, the third representation having a third size indicative of an amount of the portion of the set of electronic documents included in the third cluster, the third representation displayed a second distance from the first representation, the second distance representative of a similarity between the portion of the set of electronic documents included in the first cluster and the portion of the set of electronic documents included in the third cluster;

accessing an additional cluster that is a sub-cluster of the second cluster;

displaying, in the user interface, a fourth representation of the additional cluster within the second representation of the second cluster, the fourth representation having a fourth size indicative of an amount of the portion of the set of electronic documents included in the additional cluster, the fourth representation displayed a fourth distance from the first representation, the fourth distance representative of a similarity between the portion of the set of electronic documents included in the first cluster and the portion of the set of electronic documents included in the additional cluster;

displaying, in the user interface, a first line object as a first radial line from the first representation of the first cluster through the second representation of the second cluster and the fourth representation of the additional cluster; and

displaying, in the user interface, a second line object as a second radial line from the first representation of the first cluster through the third representation of the third cluster, wherein the second representation and the third representation at least partially surround the first representation.

2. The computer-implemented method of claim 1 , wherein displaying the first representation of the first cluster of the set of clusters comprises:

displaying the first representation in a center portion of the user interface.

3. The computer-implemented method of claim 2 , further comprising:

receiving a selection to replace the first representation of the first cluster with the second representation of the second cluster;

determining a similarity between the portion of the set of electronic documents included in the second cluster and the portion of the set of electronic documents included in the third cluster;

displaying, in the center portion of the user interface, the second representation of the second cluster;

displaying, in the user interface, the first representation of the first cluster, the first representation displayed the first distance from the second representation; and

displaying, in the user interface, the third representation of the third cluster, the third representation displayed a third distance from the second representation, the third distance representative of the similarity between the portion of the set of electronic documents included in the second cluster and the portion of the set of electronic documents included in the third cluster.

4. The computer-implemented method of claim 1 , further comprising:

analyzing, by a computer processor, the set of electronic documents including:

identifying a set of terms that are included in the set of electronic documents,

determining a set of groupings of the set of terms based on a set of similarities among the set of terms, and

generating the set of clusters corresponding to the set of groupings, each of the set of clusters including the portion of the set of electronic documents according to a respective grouping of the set of groupings.

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

displaying, in the user interface for each of the first cluster, the second cluster, and the third cluster, the set of terms included in the grouping for that cluster.

6. The computer-implemented method of claim 1 , further comprising:

receiving a display modification selection via the user interface; and

modifying, in the user interface according to the display modification selection, display of at least one of the second representation of the second cluster and the third representation of the third cluster.

7. The computer-implemented method of claim 6 , wherein receiving the display modification selection comprises receiving a similarity adjustment with a corresponding similarity metric, and wherein modifying the display comprises:

relocating, in the user interface, (i) the second cluster to a modified first distance from the first cluster according to the similarity metric, and (ii) the third cluster to a modified second distance from the first cluster according to the similarity metric.

8. The computer-implemented method of claim 1 , wherein accessing the set of clusters comprises:

sending, to a server, a query comprising a set of parameters; and

receiving, from the server, data indicative of the set of clusters and reflective of the set of parameters of the query.

9. A system configured to generate data visualizations, comprising:

a user interface;

a memory configured to store non-transitory computer executable instructions; and

a processor interfacing with the user interface and the memory, and configured to execute the non-transitory computer executable instructions to cause the processor to:

access a set of clusters, wherein each of the set of clusters includes a portion of a set of electronic documents,

cause the user interface to display an indication of a percentage of the set of electronic documents that are clustered,

cause the user interface to display a first representation of a first cluster of the set of clusters, the first representation having a first size indicative of an amount of the portion of the set of electronic documents included in the first cluster,

cause the user interface to display a second representation of a second cluster of the set of clusters, the second representation having a second size indicative of an amount of the portion of the set of electronic documents included in the second cluster, the second representation displayed a first distance from the first representation, the first distance representative of a similarity between the portion of the set of electronic documents included in the first cluster and the portion of the set of electronic documents included in the second cluster,

cause the user interface to display a third representation of a third cluster of the set of clusters, the third representation having a third size indicative of an amount of the portion of the set of electronic documents included in the third cluster, the third representation displayed a second distance from the first representation, the second distance representative of a similarity between the portion of the set of electronic documents included in the first cluster and the portion of the set of electronic documents included in the third cluster,

access an additional cluster that is a sub-cluster of the second cluster or the third cluster,

cause the user interface to display a fourth representation of the additional cluster within the second representation of the second cluster, the fourth representation having a fourth size indicative of an amount of the portion of the set of electronic documents included in the additional cluster, the fourth representation displayed a fourth distance from the first representation, the fourth distance representative of a similarity between the portion of the set of electronic documents included in the first cluster and the portion of the set of electronic documents included in the additional cluster,

cause the user interface to display a first line object as a first radial line from the first representation of the first cluster through the second representation of the second cluster and the fourth representation of the additional cluster, and

cause the user interface to display a second line object as a second radial line from the first representation of the first cluster through the third representation of the third cluster, wherein the second representation and the third representation at least partially surround the first representation.

10. The system of claim 9 , wherein to cause the user interface to display the first representation of the first cluster of the set of clusters, the processor is configured to:

cause the user interface to display the first representation in a center portion of the user interface.

11. The system of claim 10 , wherein the processor is further configured to:

receive, via the user interface, a selection to replace the first representation of the first cluster with the second representation of the second cluster,

determine a similarity between the portion of the set of electronic documents included in the second cluster and the portion of the set of electronic documents included in the third cluster,

cause the user interface to display, in the center portion of the user interface, the second representation of the second cluster,

cause the user interface to display the first representation of the first cluster, the first representation displayed the first distance from the second representation, and

cause the user interface to display the third representation of the third cluster, the third representation displayed a third distance from the second representation, the third distance representative of the similarity between the portion of the set of electronic documents included in the second cluster and the portion of the set of electronic documents included in the third cluster.

12. The system of claim 9 , wherein the processor is further configured to:

analyze the set of electronic documents including:

identify a set of terms that are included in the set of electronic documents,

determine a set of groupings of the set of terms based on a set of similarities among the set of terms, and

generate the set of clusters corresponding to the set of groupings, each of the set of clusters including the portion of the set of electronic documents according to a respective grouping of the set of groupings.

13. The system of claim 12 , wherein the processor is further configured to:

cause the user interface to display, for each of the first cluster, the second cluster, and the third cluster, the set of terms included in the grouping for that cluster.

14. The system of claim 9 , wherein the processor is further configured to:

receive, via the user interface, a display modification selection via the user interface, and

cause the user interface to modify, according to the display modification selection, display of at least one of the second representation of the second cluster and the third representation of the third cluster.

15. The system of claim 14 , wherein the display modification selection is a similarity adjustment with a corresponding similarity metric, and wherein to cause the user interface to modify the display, the processor is configured to:

cause the user interface to relocate (i) the second cluster to a modified first distance from the first cluster according to the similarity metric, and (ii) the third cluster to a modified second distance from the first cluster according to the similarity metric.

16. The system of claim 9 , wherein to access the set of clusters, the processor is configured to:

send, to a server via a transceiver, the query comprising a set of parameters, and

receive, from the server via the transceiver, data indicative of the set of clusters and reflective of the set of parameters of the query.