Systems and methods for generating issue networks

1. A computer program for generating an issue network from a document corpus comprising instructions which, when the program is executed by a computer, cause the computer to carry out steps comprising:

searching the document corpus for a set of documents discussing a starting issue, wherein the starting issue is one of a plurality of normalized issues defined by the document corpus;

determining a set of normalized issues discussed by the set of documents discussing the starting issue, wherein the set of normalized issues also includes the starting issue;

determining instances of co-occurrences of individual normalized issues of the set of normalized issues within individual cases of the set of documents;

linking individual normalized issues of the set of normalized issues based on their co-occurrences within the set of documents, wherein the linked individual normalized issues at least in part define the issue network; and

storing the linked individual normalized issues in a non-transitory computer-readable medium.

2. The computer program of claim 1 , further comprising providing for display a graphical representation of the issue network on a display device, wherein the graphical representation of the issue network comprises nodes representing individual normalized issues of the set of normalized issues, and edges linking the nodes based on the co-occurrences of the individual normalized issues within individual documents within the set of documents.

3. The computer program of claim 2 , wherein each edge provides a visual representation of a strength of a link between two nodes based on a number of co-occurrences between two individual issues represented by the two nodes.

4. The computer program of claim 3 , wherein the visual representation comprises a weighted line representing the edge.

5. The computer program of claim 2 , where in the nodes represent individual normalized issues of the set of normalized issues that co-occur within the individual documents above a co-occurrence threshold.

6. The computer program of claim 1 , further comprising normalizing issues discussed in the document corpus.

7. The computer program of claim 6 , further comprising storing normalized issues in an issue library metadata file.

8. The computer program of claim 6 , wherein normalizing the issues discussed in the document corpus comprises:

semantically linking, by a computing device, documents within the document corpus by pairing reasons-for-citing in citing documents with cited-text-areas in cited documents, wherein a cited-text-area in a cited document is a text area that has a highest similarity value of text present within the cited document;

creating a group of semantically-similar reasons-for-citing and cited-text-areas that are semantically similar to at least one issue; and

storing information regarding groups of semantically-similar reasons-for-citing and cited-text-areas in an issue library metadata entity, wherein each issue library metadata entity is associated with an individual issue.

9. The computer program of claim 1 , further comprising creating at least one issues-by-case metadata file, wherein the searching of the document corpus for the set of documents discussing the starting issue, the determining of the set of normalized issues discussed by the set of documents discussing the starting issue, and the determining of the instances of co-occurrences of individual normalized issues of the set of normalized issues within individual cases of the set of documents comprises searching the at least one issues-by-case metadata file.

10. The computer program of claim 9 , wherein the at least one issues-by-case metadata file comprises at least one entry comprising a case identifier and one or more issue identifiers.

11. A computer program for generating an issue network from a document corpus comprising instructions which, when the program is executed by a computer, cause the computer to carry out steps comprising:

searching the document corpus for a set of documents discussing a starting issue, wherein the starting issue is one of a plurality of normalized issues defined by the document corpus;

determining a set of normalized issues discussed by the set of documents discussing the starting issue, wherein the set of normalized issues also includes the starting issue;

determining instances of co-occurrences of individual normalized issues of the set of normalized issues within individual cases of the set of documents;

linking individual normalized issues of the set of normalized issues based on their co-occurrences within the set of documents, wherein the linked individual normalized issues at least in part define the issue network; and

providing for display a graphical representation of the issue network on a display device, wherein the graphical representation of the issue network comprises nodes representing individual normalized issues of the set of normalized issues, and edges linking the nodes based on the co-occurrences of the individual normalized issues within individual documents within the set of documents.

12. The computer program of claim 11 , wherein each edge provides a visual representation of a strength of a link between two nodes based on a number of co-occurrences between two individual issues represented by the two nodes.

13. The computer program of claim 12 , wherein the visual representation comprises a weighted line representing the edge.

14. The computer program of claim 11 , where in the nodes represent individual normalized issues of the set of normalized issues that co-occur within the individual documents above a co-occurrence threshold.

15. The computer program of claim 11 , further comprising normalizing issues discussed in the document corpus.

16. The computer program of claim 15 , further comprising storing normalized issues in an issue library metadata file.

17. The computer program of claim 15 , wherein normalizing the issues discussed in the document corpus comprises:

semantically linking, by a computing device, documents within the document corpus by pairing reasons-for-citing in citing documents with cited-text-areas in cited documents, wherein a cited-text-area in a cited document is a text area that has a highest similarity value of text present within the cited document;

creating a group of semantically-similar reasons-for-citing and cited-text-areas that are semantically similar to at least one issue; and

storing information regarding groups of semantically-similar reasons-for-citing and cited-text-areas in an issue library metadata entity, wherein each issue library metadata entity is associated with an individual issue.

18. The computer program of claim 11 , further comprising creating at least one issues-by-case metadata file, wherein the searching of the document corpus for the set of documents discussing the starting issue, the determining of the set of normalized issues discussed by the set of documents discussing the starting issue, and the determining of the instances of co-occurrences of individual normalized issues of the set of normalized issues within individual cases of the set of documents comprises searching the at least one issues-by-case metadata file.

19. The computer program of claim 18 , wherein the at least one issues-by-case metadata file comprises at least one entry comprising a case identifier and one or more issue identifiers.

20. The computer program of claim 11 , further comprising storing the linked individual normalized issues in a non-transitory computer-readable medium.