PROVISION OF USER INPUT IN SYSTEMS FOR JOINTLY DISCOVERING TOPICS AND SENTIMENTS

• US 20130018651A1
• Filed: 07/10/2012
• Published: 01/17/2013
• Est. Priority Date: 07/11/2011
• Status: Active Grant

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture Global Services Limited (Accenture PLC)
• Inventors: Djordjevic, Divna, Ghani, Rayid, Krema, Marko
• Granted Patent: US 9,015,035 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06Q 10/00 Administration; Management

Abstract

A generative model is used to develop at least one topic model and at least one sentiment model for a body of text. The at least one topic model is displayed such that, in response, a user may provide user input indicating modifications to the at least one topic model. Based on the received user input, the generative model is used to provide at least one updated topic model and at least one updated sentiment model based on the user input. Thereafter, the at least one updated topic model may again be displayed in order to solicit further user input, which further input is then used to once again update the models. The at least one updated topic model and the at least one updated sentiment model may be employed to analyze target text in order to identify topics and associated sentiments therein.

Claims

1. A method, in a system for jointly discovering topics and sentiments in a body of text, for providing user input to the system, the method comprising:

providing, by a processing device implementing a generative model for determining the topics and sentiments within the body of text, at least one topic model and at least one sentiment model;

displaying, by the processing device via a display operatively connected to the processing device, at least a portion of the at least one topic model;

receiving, by the processing device via a user input device operatively connected to the processing device, user input data indicating modification of the at least one topic model; and

providing, by the processing device via the generative model, at least one updated topic model and at least one updated sentiment model based at least in part upon the user input data.

2. The method of claim 1, further comprising:

displaying, by the processing device via the display, at least a portion of the at least one sentiment model.

3. The method of claim 1, further comprising receiving the user input data, wherein the user input data indicates a merger of at least two topics modeled by the at least one topic model.

4. The method of claim 1, further comprising receiving the user input data, wherein the user input data indicates division of a single topic modeled by the at least one topic model into two or more topics.

5. The method of claim 1, further comprising receiving the user input data, wherein the user input data indicates modification of a feature probability within a topic modeled by the at least one topic model.

6. The method of claim 1, further comprising receiving the user input data, wherein the user input data indicates deletion of a feature probability within a topic modeled by the at least one topic model.

7. The method of claim 1, further comprising receiving the user input data, wherein the user input data indicates moving a feature probability from a first topic to a second topic modeled by the at least one topic model.

8. The method of claim 1, further comprising receiving the user input data, wherein the user input data indicates a new feature and associated feature probability corresponding to a topic.

9. The method of claim 1, further comprising receiving the user input data, wherein the user input data indicates deletion of a topic from the at least one topic model.

10. The method of claim 1, further comprising:

analyzing, by the processing device, target text constituting at least a portion of the body of text according to the at least one updated topic model and the at least one updated sentiment model.

11. The method of claim 1, further comprising:

receiving, by the processing device prior to providing the at least one topic model and the at least one sentiment model, user input data indicating a new feature and associated feature probability corresponding to an initial topic.

12. An apparatus for providing user input to a system for jointly discovering topics and sentiments in a body of text, comprising:

a processor;

a display operatively connected to the processor;

a user input device operatively connected to the processor; and

a storage device operatively connected to the processor, having stored thereon instructions that, when executed by the processor cause the processor to;

provide at least one topic model and at least one sentiment model based on a generative model for determining the topics and sentiments within the body of text;

display, via the display, at least a portion of the at least one topic model;

receive, via the user input device, user input data indicating modification of the at least one topic model; and

provide, via the generative model, at least one updated topic model and at least one updated sentiment model based at least in part upon the user input data.

13. The apparatus of claim 12, the storage device further comprising instructions that, when executed by the processor cause the processor to:

display, via the display, at least a portion of the at least one sentiment model.

14. The apparatus of claim 12, wherein that portion of the instructions that cause the processor to receive the user input data are further operative to cause the processor to receive data indicative of a merger of at least two topics modeled by the at least one topic model.

15. The apparatus of claim 12, wherein that portion of the instructions that cause the processor to receive the user input data are further operative to cause the processor to receive data indicative of division of a single topic modeled by the at least one topic model into two or more topics.

16. The apparatus of claim 12, wherein that portion of the instructions that cause the processor to receive the user input data are further operative to cause the processor to receive data indicative of modification of a feature probability within a topic modeled by the at least one topic model.

17. The apparatus of claim 12, wherein that portion of the instructions that cause the processor to receive the user input data are further operative to cause the processor to receive data indicative of deletion of a feature probability within a topic modeled by the at least one topic model.

18. The apparatus of claim 12, wherein that portion of the instructions that cause the processor to receive the user input data are further operative to cause the processor to receive data indicative of moving a feature probability from a first topic to a second topic modeled by the at least one topic model.

19. The apparatus of claim 12, wherein that portion of the instructions that cause the processor to receive the user input data are further operative to cause the processor to receive data indicative of a new feature and associated feature probability corresponding to a topic.

20. The apparatus of claim 12, wherein that portion of the instructions that cause the processor to receive the user input data are further operative to cause the processor to receive data indicative of deletion of a topic from the at least one topic model.

21. The apparatus of claim 12, the storage device further comprising instructions that, when executed by the processor cause the processor to:

analyze target text constituting at least a portion of the body of text according to the at least one updated topic model and the at least one updated sentiment model.

22. The apparatus of claim 12, wherein that portion of the instructions that cause the processor to receive user input data are further operative to cause the processor to receive, prior to providing the at least one topic model and the at least one sentiment model, user input data indicative of a new feature and associated feature probability corresponding to an initial topic.