SYSTEM FOR MANAGEMENT OF SENTIMENTS AND METHODS THEREOF

• US 20140289253A1
• Filed: 03/06/2014
• Published: 09/25/2014
• Est. Priority Date: 03/20/2013
• Status: Active Grant

• Current Assignee: Infosys Limited
• Original Assignee: Infosys Limited
• Inventors: Natarajan, Swaminathan, Deepak, Krishnamurthy Sai, Subbarao, Venugopal, Pisipati, Radha Krishna, Teli, Prasanna Nagesh
• Granted Patent: US 9,514,496 B2
• Time in Patent Office: Days
• US Class Current: 707/740
• CPC Class Codes: G06Q 10/101 Collaborative creation, e.g. joint development of products or services
• CPC Class Codes: G06Q 10/103 Workflow collaboration or project management
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: G06Q 30/0278 Product appraisal
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Systems and methods for improved management of sentiments over conventional approaches are disclosed. Supervised approach is used to augment the rule-based approach for classification. Initially, sentiment evaluation is performed by the system using a rule based approach and an interface is provided to the user to give feedback on the correctness of evaluated sentiment. This feedback is used by the sentiment evaluation system to update the set of rule-based and also apply the supervised approach to train the classifier for evaluating complex posts.

Claims

1. A method for managing sentiments, the method comprising:

receiving, by a sentiment management computing device, one or more evaluated posts as an input item to be managed, wherein each of the one or more evaluated posts is categorized into a first classification type;

identifying, by the sentiment management computing device, each of the one or more evaluated posts in a multidimensional feature space, wherein each dimension represents a unique feature corresponding to the one or more evaluated posts;

receiving, by the sentiment management computing device, an indication from at least one user on each of the one or more identified evaluated posts, as an output item to be managed, wherein the indication from the user represents a second classification type; and

performing, by the sentiment management computing device, a neighborhood operation for each of the one or more identified evaluated posts, based on the second classification type.

2. The method as set forth in claim 1, further comprising:

selecting, by the sentiment management computing device, a preconfigured subset of features in the multidimensional feature space.

3. The method as set forth in claim 1, wherein performing the neighborhood operation further comprises:

adjusting, by the sentiment management computing device, a preconfigured pattern space around each of the one or more evaluated posts identified in the multidimensional feature space.

4. The method as set forth in claim 3, wherein performing the neighborhood operation further comprises:

re-classifying, by the sentiment management computing device, the first classification type for each of the one or more posts in the pattern space.

5. The method as set forth in claim 4 further comprising:

subjecting, by the sentiment management computing device, each of the one or more re-classified posts as training data sets for subsequent classification, wherein the subsequent classification corresponds to the first classification type.

6. The method as set forth in claim 1, wherein performing the neighborhood operation further comprises:

re-classifying, by the sentiment management computing device, the first classification type for each of the one or more posts in a pattern space.

7. The method as set forth in claim 1, wherein performing the neighborhood operation further comprises:

adapting, by the sentiment management computing device, at least one pre-configured pattern space.

8. A sentiment management computing device, comprising:

a processor coupled to a memory and configured to execute programmed instructions stored in the memory, comprising;

receiving one or more evaluated posts as an input item to be managed, wherein each of the one or more evaluated posts is categorized into a first classification type;

identifying each of the one or more evaluated posts in a multidimensional feature space, wherein each dimension represents a unique feature corresponding to the one or more evaluated posts;

receiving an indication from at least one user on each of the one or more identified evaluated posts, as an output item to be managed, wherein the indication from the user represents a second classification type; and

performing a neighborhood operation for each of the one or more evaluated based on the second classification type.

9. The device as set forth in claim 8, wherein the processor is further configured to execute programmed instructions stored in the memory further comprising selecting a preconfigured subset of features in the multidimensional feature space.

10. The device as set forth in claim 8, wherein the processor is further configured to execute programmed instructions stored in the memory further comprising adjusting a preconfigured pattern space around each of the one or more evaluated posts identified in the multidimensional feature space.

11. The device as set forth in claim 10, wherein the processor is further configured to execute programmed instructions stored in the memory further comprising re-classifying the first classification type for each of the one or more posts in the pattern space.

12. The device as set forth in claim 11, wherein the processor is further configured to execute programmed instructions stored in the memory further comprising subjecting each of the one or more re-classified posts as training data sets for subsequent classification, wherein the subsequent classification corresponds to the first classification type.

13. The device as set forth in claim 8, wherein the processor is further configured to execute programmed instructions stored in the memory further comprising re-classifying the first classification type for each of the one or more posts in the pattern space.

14. The device as set forth in claim 8, wherein the processor is further configured to execute programmed instructions stored in the memory further comprising adapting at least one pre-configured pattern space.

20. The medium as set forth in claim 8, wherein the medium further comprises machine executable code which, when executed by the processor causes the processor to perform steps further comprising re-classifying the first classification type for each of the one or more posts in the pattern space.

21. The medium as set forth in claim 8, wherein the medium further comprises machine executable code which, when executed by the processor causes the processor to perform steps further comprising adapting at least one pre-configured pattern space.

15. A non-transitory computer readable medium having stored thereon instructions for managing sentiments comprising machine executable code which when executed by a processor, causes the processor to perform steps comprising:

receiving one or more evaluated posts as an input item to be managed, wherein each of the one or more evaluated posts is categorized into a first classification type;

identifying each of the one or more evaluated posts in a multidimensional feature space, wherein each dimension represents a unique feature corresponding to the one or more evaluated posts;

receiving an indication from at least one user on each of the one or more identified evaluated posts, as an output item to be managed, wherein the indication from the user represents a second classification type; and

performing a neighborhood operation for each of the one or more evaluated based on the second classification type.

16. The medium as set forth in claim 15, wherein the medium further comprises machine executable code which, when executed by the processor causes the processor to perform steps further comprising:

selecting a preconfigured subset of features in the multidimensional feature space.

17. The medium as set forth in claim 15 wherein the medium further comprises machine executable code which, when executed by the processor causes the processor to perform steps further comprising:

adjusting a preconfigured pattern space around each of the one or more evaluated posts identified in the multidimensional feature space.

18. The medium as set forth in claim 17, wherein the medium further comprises machine executable code which, when executed by the processor causes the processor to perform steps further comprising:

re-classifying the first classification type for each of the one or more posts in the pattern space.

19. The medium as set forth in claim 18, wherein the medium further comprises machine executable code which, when executed by the processor causes the processor to perform steps further comprising:

subjecting each of the one or more re-classified posts as training data sets for subsequent classification, wherein the subsequent classification corresponds to the first classification type.