Sentiment-scoring application score unification

• US 9,563,622 B1
• Filed: 12/29/2012
• Issued: 02/07/2017
• Est. Priority Date: 12/30/2011
• Status: Active Grant

• Current Assignee: Teradata Corporation
• Original Assignee: Teradata US, Inc. (Teradata Corporation)
• Inventors: Anderson, Joshua David
• Primary Examiner(s): Bowen, Richard
• Application Number:
  US13/730,964
• Time in Patent Office: 1,501 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A sentiment score unification system includes a storage device configured to store a plurality of sentiment scoring applications and a sentiment unification module. The sentiment score unification system further includes a processor in communication with the memory device. The processor may be configured to receive a plurality of sentiment expressions and execute each of the plurality of sentiment scoring applications. Each of the plurality of sentiment scoring applications is executable to generate a respective sentiment score based on the plurality of sentiment expressions. Each respective sentiment score is indicative of a level of sentiment. The processor is further configured to execute the sentiment unification module. The sentiment unification module is executable to generate a single unified sentiment score based on the respective sentiment scores. A method and computer-readable medium are also disclosed.

Claims

1. A sentiment score unification system comprising:

a storage device configured to store a sentiment unification module;

a processor in communication with the memory device, the processor configured to;

receive a plurality of single sentiment scores, wherein each single sentiment score is from a respective scoring sentiment application, wherein each single sentiment score is indicative of a respective overall sentiment of a plurality of sentiment expressions, wherein each sentiment expression from the plurality of sentiment expressions is from a different, independent sentiment source; and

execute the sentiment unification module, wherein the sentiment unification module is executable to generate a single unified sentiment score based on the plurality of single sentiment scores, wherein the single unified sentiment score is indicative of an overall sentiment of the plurality of sentiment expressions.

2. The sentiment score unification system of claim 1, wherein the sentiment unification module is further executable to:

normalize the single sentiment scores; and

generate the single unified sentiment score based on the normalized single sentiment scores.

3. The sentiment score unification system of claim 1, wherein the sentiment unification module is further configured to apply a respective weighting factor to each of the single sentiment scores, wherein a higher relative weighting factor is indicative of a sentiment scoring application being older than a different sentiment scoring application having a lower relative weighting factor.

4. The sentiment score unification system of claim 1, wherein the sentiment unification module is further configured to:

select a subset of the plurality of sentiment scoring applications;

receive a subset of the plurality of single sentiment scores from the subset of sentiment scoring applications, wherein each single sentiment score from the subset of the plurality of single sentiment scores is from a respective sentiment scoring application of the plurality of sentiment scoring applications; and

execute the sentiment unification module, wherein the sentiment unification module is executable to generate a single unified sentiment score based on the subset of single sentiment scores from the subset of sentiment scoring applications.

5. The sentiment score unification system of claim 4, wherein the sentiment unification module is further configured to select the subset of sentiment scoring applications based on a respective relative age of each sentiment scoring application, wherein the sentiment scoring applications of the subset are relatively older than unselected sentiment scoring applications.

6. The sentiment score unification system of claim 4, wherein the sentiment unification module is further configured to select the subset of sentiment scoring applications based on a frequency of prior use of the sentiment scoring applications, wherein the sentiment scoring applications of the subset are used more frequently than unselected sentiment scoring applications.

7. The sentiment score unification system of claim 1, wherein at least one of the received expressions of sentiment is delivered from a social network website.

8. A method comprising:

receiving, with a processor, a plurality of single sentiment scores, wherein each single sentiment score is from a respective scoring sentiment application, wherein each single sentiment score is indicative of a respective overall sentiment of a plurality of sentiment expressions, wherein each sentiment expression from the plurality of sentiment expressions is from a different, independent sentiment source; and

generating, with the processor, a single unified sentiment score based on the plurality of single sentiment scores, wherein the single unified sentiment score is indicative of an overall sentiment of the plurality of sentiment expressions.

9. The method of claim 8, further comprising normalizing, with the processor, the single sentiment scores, wherein, generating, with the processor, the single unified sentiment score comprises generating, with the processor, the single unified sentiment score based on the normalized single sentiment scores.

10. The method of claim 8, further comprising applying, with the processor, a respective weighting factor to each of the single sentiment scores, wherein a higher relative weighting factor is indicative of a sentiment scoring application being older than a different sentiment scoring application having a lower relative weighting factor.

11. The method of claim 8, further comprising:

selecting, with the processor, a subset of the plurality of sentiment scoring applications; and

receiving a subset of the plurality of single sentiment scores from the subset of sentiment scoring applications, and wherein each single sentiment score from the subset of the plurality of single sentiment scores is from a respective sentiment scoring application of the plurality of sentiment scoring applications, wherein generating, with the processor, a single unified sentiment score comprises generating, with the processor, the single unified sentiment score based on the single sentiment scores from the subset of sentiment scoring applications.

12. The method of claim 11, wherein selecting, with the processor, the subset of sentiment scoring applications comprises selecting, with the processor, the subset of sentiment scoring applications based on a respective relative age of each sentiment scoring application, wherein the sentiment scoring applications of the subset are relatively older than unselected sentiment scoring applications.

13. The method of claim 11, wherein selecting, with the processor, the subset of sentiment scoring applications comprises selecting, with the processor, the subset of sentiment scoring applications based on a frequency of prior use of the sentiment scoring applications, wherein the sentiment scoring applications of the subset are used more frequently than unselected sentiment scoring applications.

14. The method of claim 8 wherein at least one of the received expressions of sentiment is delivered from a social network website.

15. A non-transitory computer-readable medium encoded with a set of instructions executable by a processor, the set of instructions comprising:

instructions to receive a plurality of single sentiment scores, wherein each single sentiment score is from a respective scoring sentiment application, wherein each single sentiment score is indicative of a respective overall sentiment of a plurality of sentiment expressions, wherein each sentiment expression from the plurality of sentiment expressions is from a different, independent sentiment source; and

instructions to generate a single unified sentiment score based on the plurality of single sentiment scores, wherein the single unified sentiment score is indicative of an overall sentiment of the plurality of sentiment expressions.

16. The non-transitory computer-readable medium of claim 15, wherein the set of instructions further comprises instructions to normalize the single sentiment scores, wherein, the instructions to generate the single unified sentiment score comprise instructions to generate the single unified sentiment score based on the normalized single sentiment scores.

17. The non-transitory computer-readable medium of claim 15, wherein the set of instructions further comprises instructions to apply a respective weighting factor to each of the single sentiment scores, wherein a higher relative weighting factor is indicative of a sentiment scoring application being older than a different sentiment scoring application having a lower relative weighting factor.

18. The non-transitory computer-readable medium of claim 15, wherein the set of instructions further comprises:

instructions to select a subset of the plurality of sentiment scoring applications; and

instructions to receive a subset of the plurality of single sentiment scores from the subset of sentiment scoring applications, wherein each single sentiment score from the subset of the plurality of single sentiment scores is from a respective sentiment scoring application of the plurality of sentiment scoring applications, and wherein instructions to generate a single unified sentiment score comprise instructions to generate the single unified sentiment score based on the single sentiment scores from the subset of sentiment scoring applications.

19. The non-transitory computer-readable medium of claim 17, wherein the instructions to select a subset of sentiment scoring application comprise instructions to select the subset of sentiment scoring applications based on a respective relative age of each sentiment scoring application, wherein the sentiment scoring applications of the subset are relatively older than unselected sentiment scoring applications.

20. The non-transitory computer-readable medium of claim 18, wherein the instructions to select a subset of sentiment scoring application comprise instructions to select the subset of sentiment scoring applications based on a frequency of prior use of the sentiment scoring applications, wherein the sentiment scoring applications of the subset are used more frequently than unselected sentiment scoring applications.