UNSPOKEN SENTIMENT

• US 20150073775A1
• Filed: 09/11/2013
• Published: 03/12/2015
• Est. Priority Date: 09/11/2013
• Status: Active Grant

• Current Assignee: Arlington Technologies, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Avaya Incorporated
• Inventors: Skiba, David, Erhart, George, Becker, Lee, Matula, Valentine C.
• Granted Patent: US 9,715,492 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G05B 13/048 using a predictor
• CPC Class Codes: G06F 17/10 Complex mathematical operations function generation by table look-up G06F1/03; evaluation of elementary functions by calculation G06F7/544
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: H04N 21/251 Learning process for intelligent management, e.g. learning user preferences for recommending movies details of learning user preferences for the retrieval of video data in a video database G06F16/739; computer systems using learning methods G06N3/08

Abstract

The sentiment of a message may not be obtainable from the message itself. However, many messages have an associated context that provides information useful in determining the sentiment of a message. Messages may include links to other resources, such as graphics or videos, which in turn include titles, comments, viewer ratings or other attributes that may provide a sentiment of the message.

Claims

1. A method, determining a message sentiment, comprising:

selecting a message;

selecting a context associated with the selected message;

determining a sentiment of the context; and

assigning the determined sentiment to the selected message.

2. The method of claim 1, further comprising:

selecting a plurality of contexts, each associated with the message; and

setting the sentiment of the message in accord with the plurality of contexts.

3. The method of claim 2, wherein the context includes a rate of occurrence context associated with the plurality of contexts.

4. The method of claim 2, further comprising,

determining a sentiment score for ones of the plurality of contexts;

and

setting the sentiment of the message in accord with the aggregate sentiment score for the ones of the plurality of contexts.

5. The method of claim 1, wherein the determining the sentiment of the context further comprises, determining the sentiment in accord with an attribute of a context.

6. The method of claim 5, wherein the context is associated with a media file and the attribute is at least one of poster comments, title, and viewer comments associated with the media file.

7. The method of claim 6, wherein the viewer comments include an explicit rating indicator.

8. The method of claim 1, wherein the context is an implied endorsement by a viewer of the message.

9. A system for determining sentiment of a message, comprising:

a processor,

a storage,

a network interface, and

wherein the processor is operable to obtain a message from the storage, the messaging having an associated context;

wherein the processor is further operable to determine the sentiment of the context; and

set the sentiment of the message in accord with the sentiment of the context.

10. The system of claim 9, wherein the processor is further operable to utilize the network interface to access at least one of the message and the context of the message.

11. The system of claim 9, wherein the processor is further operable to:

select a plurality of contexts, each associated with the message; and

set the sentiment of the message in accord with the plurality of contexts.

12. The system of claim 11, wherein the context includes a rate of occurrence context associated with the plurality of contexts.

13. The system of claim 9, wherein the processor determines the sentiment of the context by determining the sentiment in accord with an attribute of a context.

14. The system of claim 13, wherein the context is associated with a media file and the attribute is at least one of poster comments, title, and viewer comments associated with the media file.

15. The system of claim 14, wherein the viewer comments include an explicit rating indicator.

16. The system of claim 9, wherein the context is an implied endorsement by a viewer of the message.

17. A non-transitory medium with instructions thereon that, when executed by a machine, cause the machine to perform:

selecting a message;

selecting a context associated with a message of the message;

determining the sentiment of the context; and

setting the sentiment of the message in accord with the sentiment of the context.

18. The instructions of claim 17, wherein the determining the sentiment of the context further comprises, determining the sentiment in accord with an attribute of a context.

19. The instructions of claim 18, wherein the context is associated with a media file and the attribute is at least one of poster comments, title, and viewer comments associated with the media file.

20. The instructions of claim 17, wherein the context is an implied endorsement by a viewer of the message.