Method and system for performing topic creation for social data

• US 10,002,187 B2
• Filed: 11/26/2014
• Issued: 06/19/2018
• Est. Priority Date: 11/26/2013
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Oracle International Corporation (Oracle Corporation)
• Inventors: McCandless, Timothy P., Setayesh, Mehrshad
• Primary Examiner(s): Fan, Shiow-Jy
• Application Number:
  US14/555,042
• Publication Number:
  US 20150149463A1
• Time in Patent Office: 1,301 Days
• CPC Class Codes: G06F 16/3326 using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/35 Clustering; Classification

Abstract

Disclosed is a system, method, and computer program product for performing theme analysis and creating topics with regards to social data. A user interface is provided that allows the user to view and interact with to view and control the process/mechanism or creating topics. The topic creation process can be facilitated and automated using a volatility index.

Claims

1. A method implemented with a processor, comprising:

generating a user interface that displays analysis results identified from within one or more social media data sources, the user interface comprising;

(a) a first interface portion of the user interface comprising a list of one or more analysis results identified from within one or more social media data sources, an individual analysis result from among the one or more analysis results being selectable to display a set of terms associated with a selected individual analysis result in a second interface portion,

(b) the second interface portion of the user interface comprising the set of terms, a first interface control, and a second interface control, the set of terms associated with the selected individual analysis result, the first interface control constraining a search to include themes that correspond to the selected individual analysis result, the second interface control constraining the search to exclude the themes that correspond to the selected individual analysis result, and

(c) a third interface portion of the user interface comprising a set of one or more semantic filters selected according to the second interface portion;

receiving a search criteria to perform a search of content from the one or more social media data sources;

performing the search of the content from the one or more social media data sources to generate the list of the one or more analysis results, a volatility index corresponding to a level of commonality between two or more themes being generated for the one or more analysis results, the volatility index usable to automatically control creation of a new topic based at least in part upon a threshold value established for the volatility index, the level of commonality between the two or more themes is calculated by computing centroids for the two or more themes and determining distances between the centroids;

displaying the list of one or more analysis results identified from within one or more social media data sources pertaining to the search criteria in the first interface portion of the user interface;

receiving a selection of the first or second interface control in the second interface portion of the user interface corresponding to an application of a semantic filter, the semantic filter constraining the search of the content from the one or more social media data sources by;

(a) adding the semantic filter to definition parameters for the new topic if the first interface control is selected;

(b) adding the semantic filter to the set of one or more semantic filters in the third interface portion of the user interface if the second interface control is selected; and

(c) performing a modified search of the content with application of the semantic filter, the modified search updating the list of one or more analysis results identified from within one or more social media data sources in the first interface portion of the user interface to either remove or add results in the first interface portion that pertain to the semantic filter; and

creating the new topic based at least in part on the definition parameters, wherein the new topic corresponds to the search criteria and the semantic filter.

2. The method of claim 1, wherein the search criteria comprises a search term.

3. The method of claim 1, wherein the semantic filter comprises a filter to at least include themes more like a selected theme or to exclude themes less like the selected theme.

4. The method of claim 1, wherein the first interface portion further comprises a sorted list comprising the one or more analysis results such that an analysis result corresponding to the largest number of items is placed at a top of the sorted list, the analysis result comprising a numerical value identifying a number of items that pertain to a search term, the individual analysis result that is selected being visually differentiated from the one or more analysis results.

5. The method of claim 1, wherein the one or more sources comprise social media sources.

6. The method of claim 1, wherein the new topic is stored as a vector value corresponding to the search criteria and the semantic filter.

7. The method of claim 1, wherein snippets are obtained from the content, and the snippets are analyzed to generate search results.

8. The method of claim 7, wherein the snippets comprise a set of terms on either side of an occurrence of a word of interest within the content.

9. The method of claim 7, wherein at least some of the snippets comprise a sentence or paragraph boundary.

10. The method of claim 7, wherein the individual analysis result comprises a set of the snippets having vector values that are clustered together.

11. The method of claim 1, in which the volatility index is displayable in an interface.

12. The method of claim 1, wherein the individual analysis result corresponds to a central or pertinent idea of some or all of a content item.

13. A computer readable medium having stored thereon a sequence of instructions which, when executed by a processor causes the processor to execute a method comprising:

generating a user interface that displays analysis results identified from within one or more social media data sources, the user interface comprising;

(a) a first interface portion of the user interface comprising a list of one or more analysis results identified from within one or more social media data sources, an individual analysis result from among the one or more analysis results being selectable to display a set of terms associated with a selected individual analysis result in a second interface portion,

(b) the second interface portion of the user interface comprising the set of terms, a first interface control, and a second interface control, the set of terms associated with the selected individual analysis result, the first interface control constraining a search to include themes that correspond to the selected individual analysis result, the second interface control constraining the search to exclude the themes that correspond to the selected individual analysis result, and

(c) a third interface portion of the user interface comprising a set of one or more semantic filters selected according to the second interface portion;

receiving a search criteria to perform a search of content from the one or more social media data sources;

performing the search of the content from the one or more social media data sources to generate the list of the one or more analysis results, a volatility index corresponding to a level of commonality between two or more themes being generated for the one or more analysis results, the volatility index usable to automatically control creation of a new topic based at least in part upon a threshold value established for the volatility index, the level of commonality between the two or more themes is calculated by computing centroids for the two or more themes and determining distances between the centroids;

displaying the list of one or more analysis results identified from within one or more social media data sources pertaining to the search criteria in the first interface portion of the user interface;

receiving a selection of the first or second interface control in the second interface portion of the user interface corresponding to an application of a semantic filter, the semantic filter constraining the search of the content from the one or more social media data sources by;

(a) adding the semantic filter to definition parameters for a new topic if the first interface control is selected;

(b) adding the semantic filter to the set of one or more semantic filters in the third interface portion of the user interface if the second interface control is selected; and

(c) performing a modified search of the content with application of the semantic filter, the modified search updating the list of one or more analysis results identified from within one or more social media data sources in the first interface portion of the user interface to either remove or add results in the first interface portion that pertain to the semantic filter; and

creating the new topic based at least in part on the definition parameters, wherein the new topic corresponds to the search criteria and the semantic filter.

14. The computer readable medium of claim 13, wherein the search criteria comprises a search term.

15. The computer readable medium of claim 13, wherein the semantic filter comprises a filter to include themes more like selected theme.

16. The computer readable medium of claim 13, wherein the semantic filter comprises a filter to exclude themes less like selected theme.

17. The computer readable medium of claim 13, wherein the one or more sources comprise social media sources.

18. The computer readable medium of claim 13, wherein the new topic is stored as a vector value corresponding to the search criteria and the semantic filter.

19. The computer readable medium of claim 13, wherein snippets are obtained from the content, and the snippets are analyzed to generate search results.

20. The computer readable medium of claim 19, wherein the snippets comprise a set of terms on either side of an occurrence of a word of interest within the content.

21. The computer readable medium of claim 19, wherein at least some of the snippets comprise a sentence or paragraph boundary.

22. The computer readable medium of claim 19, wherein the individual analysis result comprises a set of the snippets having vector values that are clustered together.

23. The computer readable medium of claim 13, in which the volatility index is displayable in an interface.

24. The computer readable medium of claim 13, wherein the individual analysis result corresponds to a central or pertinent idea of some or all of a content item.

25. A system, comprising:

a processor;

a storage device to hold content from one or more sources;

a memory comprising computer code executed using the processor, in which the computer code implements;

generating a user interface that displays analysis results identified from within one or more social media data sources, the user interface comprising;

(a) a first interface portion of the user interface comprising a list of one or more analysis results identified from within one or more social media data sources, an individual analysis result from among the one or more analysis results being selectable to display a set of terms associated with a selected individual analysis result in a second interface portion,

(b) the second interface portion of the user interface comprising the set of terms, a first interface control, and a second interface control, the set of terms associated with the selected individual analysis result, the first interface control constraining a search to include themes that correspond to the selected individual analysis result, the second interface control constraining the search to exclude the themes that correspond to the selected individual analysis result, and

(c) a third interface portion of the user interface comprising a set of one or more semantic filters selected according to the second interface portion;

receiving a search criteria to perform a search of content from the one or more social media data sources;

performing the search of the content from the one or more social media data sources to generate the list of the one or more analysis results, a volatility index corresponding to a level of commonality between two or more themes being generated for the one or more analysis results, the volatility index usable to automatically control creation of a new topic based at least in part upon a threshold value established for the volatility index, the level of commonality between the two or more themes is calculated by computing centroids for the two or more themes and determining distances between the centroids;

displaying the list of one or more analysis results identified from within one or more social media data sources pertaining to the search criteria in the first interface portion of the user interface;

receiving a selection of the first or second interface control in the second interface portion of the user interface corresponding to an application of a semantic filter, the semantic filter constraining the search of the content from the one or more social media data sources by;

(a) adding the semantic filter to definition parameters for a new topic if the first interface control is selected;

(b) adding the semantic filter to the set of one or more semantic filters in the third interface portion of the user interface if the second interface control is selected; and

(c) performing a modified search of the content with application of the semantic filter, the modified search updating the list of one or more analysis results identified from within one or more social media data sources in the first interface portion of the user interface to either remove or add results in the first interface portion that pertain to the semantic filter; and

creating the new topic based at least in part on the definition parameters, wherein the new topic corresponds to the search criteria and the semantic filter.

26. The system of claim 25, wherein the search criteria comprises a search term.

27. The system of claim 25, wherein the semantic filter comprises a filter to include themes more like selected theme.

28. The system of claim 25, wherein the semantic filter comprises a filter to exclude themes less like selected theme.

29. The system of claim 25, wherein the one or more sources comprise social media sources.

30. The system of claim 25, wherein the new topic is stored as a vector value corresponding to the search criteria and the semantic filter.

31. The system of claim 25, wherein snippets are obtained from the content, and the snippets are analyzed to generate search results.

32. The system of claim 31, wherein the snippets comprise a set of terms on either side of an occurrence of a word of interest within the content.

33. The system of claim 31, wherein at least some of the snippets comprise a sentence or paragraph boundary.

34. The system of claim 31, wherein the individual analysis result comprises a set of the snippets having vector values that are clustered together.

35. The system of claim 25, in which the volatility index is displayable in an interface.

36. The system of claim 25, wherein the individual analysis result corresponds to a central or pertinent idea of some or all of a content item.