Weighting sentiment information

• US 10,430,420 B2
• Filed: 08/16/2013
• Issued: 10/01/2019
• Est. Priority Date: 08/16/2013
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Galvin, Jr., James P., Travis, Amy D., Weber, Sara B.
• Primary Examiner(s): Trujillo, James
• Assistant Examiner(s): Khoshnoodi, Fariborz
• Application Number:
  US13/969,254
• Publication Number:
  US 20150051946A1
• Time in Patent Office: 2,237 Days
• Field of Search: 707723, 707731
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data

Abstract

Weighting sentiment information includes capturing sentiment information of a post from an electronic source, categorizing the post into categories based on the sentiment information, and assigning a weight to the post based on an interest attribute.

Claims

1. A computer program product for weighting sentiment information, comprising:

a tangible, non-transitory computer readable storage medium, said tangible computer readable storage medium comprising computer readable program code embodied therewith, said computer readable program code comprising program instructions that, when executed, causes a processor to;

capture sentiment information from a post about a topic of the post, wherein said post is from an electronic source that comprises an internet website configured for receiving and displaying user-generated content, and wherein said post addresses said topic;

categorize said post into one of a number of categories based on said sentiment information;

assign a weight to said post based on an interest attribute of said post, wherein said interest attribute denotes a degree of relevance of said post to said topic; and

providing intelligence to a user interested in said topic based on combining said weight and which of said categories applies to said post.

2. The computer program product of claim 1, wherein assigning said weight to said post based on said interest attribute further comprising computer readable program code comprising program instructions that, when executed, cause said processor to reference an interest attribute database.

3. The computer program product of claim 2, wherein said interest attribute database comprises a social network identification attribute, a network size attribute, a company name attribute, a job title attribute, a social network weight attribute, or combinations thereof.

4. The computer program product of claim 1, wherein said categories for said post based on said sentiment information includes a positive sentiment category, a neutral sentiment category, a negative sentiment category, or combinations thereof.

5. The computer program product of claim 1, further comprising computer readable program code comprising program instructions that, when executed, cause said processor to parse said sentiment information of said post based on said interest attribute to create parsed sentiment information.

6. The computer program product of claim 5, further comprising computer readable program code comprising program instructions that, when executed, cause said processor to display said parsed sentiment information to a user via a display.

7. The computer program product of claim 6, wherein displaying said parsed sentiment information to a user via a display includes displaying said parsed sentiment information as a graph, a table, a histogram, plots, or combinations thereof.

8. A system for weighting sentiment information, said system comprising a processor and associated memory resources to implement:

a capturing engine to capture sentiment information of a post to an electronic source that comprises an internet website configured for receiving and displaying user-generated content, wherein content of the post comments on a topic of interest to a user;

a categorization engine to categorize said post into one of a plurality of categories based on said sentiment information;

an assigning engine to assign a weight to said post based on an interest attribute of said post, wherein said assigning engine recognizes a set of different interest attributes and receives user input specifying which of said interest attributes should be used to assign said weight to said post, wherein for each user-specified interest attribute that said post possess, weight is assigned to said post; and

an interest attribute parsing engine to parse said sentiment information of said post and said weight of said post based on said interest attribute to create intelligence that combines said sentiment information and said weight based on selected interest attributes.

9. The system of claim 8, further comprising a reference engine to reference an interest attribute database.

10. The system of claim 9, wherein said interest attribute database comprises a social network identification attribute, a network size attribute, a company name attribute, a job title attribute, a social network weight attribute, or combinations thereof.

11. The system of claim 8, wherein said categories for said post based on said sentiment information includes a positive sentiment category, a neutral sentiment category, a negative sentiment category, or combinations thereof.

12. The system of claim 8, further comprising a display engine to display said intelligence to a user via a display.

13. The system of claim 12, wherein said display engine further displays said parsed sentiment information as a graph, a table, a histogram, plots, or combinations thereof.

14. A system for weighting sentiment information, said system comprising a processor and associated memory resources to implement:

a categorization engine to categorize said post into categories based on said sentiment information; and

an assigning engine to assign a weight to said post based on an interest attribute of said post, said interest attribute identifying some aspect of a source from which said post comes;

said assigning engine implementing rules comprising;

when said post is made by a specific user, said post is assigned a weight,

when said post is made by a user from a network of a specific size, said post is assigned a weight,

when said post is made by a user at a specific company, said post is assigned a weight,

when said post is made by a user having a specific job title, said post is assigned a weight,

when said post is made on a specific social network, said post is assigned a weight.

15. The system of claim 14, further comprising a capturing engine to capture said sentiment information of said post from an electronic source.

16. The system of claim 14, wherein assigning said weight to said post based on said interest attribute comprises a reference engine to reference an interest attribute database.

17. The system of claim 16, wherein said interest attribute database comprises a social network identification attribute, a network size attribute, a company name attribute, a job title attribute, a social network weight attribute, or combinations thereof.

18. The system of claim 14, wherein said categories for said post based on said sentiment information includes a positive sentiment category, a neutral sentiment category, a negative sentiment category, or combinations thereof.

19. The system of claim 16, further comprising an interest attribute parsing engine to parse said sentiment information of said post based on said interest attribute to create parsed sentiment information.

20. The system of claim 14, further comprising a user interface with which a user specifies which of the rules will be applied in assigning weight to said post, wherein rules not selected by the user are ignored in assigning weight to said post.