REAL-TIME MESSAGE SENTIMENT AWARENESS

• US 20130346067A1
• Filed: 06/26/2012
• Published: 12/26/2013
• Est. Priority Date: 06/26/2012
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bhatt, Dhruv A.
• Granted Patent: US 9,678,948 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

Provided are techniques for determining a sentiment of an electronic message. The electronic message is parsed to identify one or more sub-constructs. For at least one of the sub-constructs that is not false-positive, a sentiment indicator is assigned from a set of types of sentiment indicators, and a score is assigned for the sentiment indicator. A final score is obtained for at least one type of sentiment indicator in the electronic message by summing scores for that type of sentiment indicator. Based on the final score for the at least one type of sentiment indicator, a sentiment of the electronic message is identified.

Claims

1. A method for determining a sentiment of an electronic message, comprising:

parsing, using a processor of a computer, the electronic message to identify one or more sub-constructs;

for at least one of the sub-constructs that is not false-positive,

assigning a sentiment indicator from a set of types of sentiment indicators; and

assigning a score for the sentiment indicator;

obtaining a final score for at least one type of sentiment indicator in the electronic message by summing scores for that type of sentiment indicator; and

based on the final score for the at least one type of sentiment indicator, identifying a sentiment of the electronic message.

2. The method of claim 1, wherein software is provided as a service in a cloud environment.

3. The method of claim 1, wherein one or more parsing rules are used to parse the electronic message, assign the sentiment indicator, and assign the score.

4. The method of claim 1, further comprising:

notifying the user of the sentiment by providing an emoticon representing the sentiment.

5. The method of claim 1, further comprising:

notifying the user of the sentiment by providing text describing the sentiment.

6. The method of claim 1, further comprising:

providing suggestions of alternate language using one or more suggestion thesauri.

7. The method of claim 1, further comprising:

storing one or more sentiment dictionaries, wherein each of the one or more sentiment dictionaries is associated with a type of sentiment and includes terms classified as that sentiment.

8. The method of claim 1, further comprising:

storing one or more false-positive dictionaries, wherein each of the one or more false-positive dictionaries is associated with a type of sentiment and includes terms that are incorrectly classified as that sentiment; and

identifying sub-constructs that are not false-positive using the one or more false-positive dictionaries.

9. The method of claim 1, further comprising:

storing the one or more parsing rules that are created using one or more sentiment dictionaries and one or more false-positive dictionaries.

10. A computer system for determining a sentiment of an electronic message, comprising:

a processor; and

a storage device connected to the processor, wherein the storage device has stored thereon a program, and wherein the processor is configured to execute instructions of the program to perform operations, wherein the operations comprise;

parsing, using a processor of a computer, the electronic message to identify one or more sub-constructs;

for at least one of the sub-constructs that is not false-positive,

assigning a sentiment indicator from a set of types of sentiment indicators; and

assigning a score for the sentiment indicator;

obtaining a final score for at least one type of sentiment indicator in the electronic message by summing scores for that type of sentiment indicator; and

based on the final score for the at least one type of sentiment indicator, identifying a sentiment of the electronic message.

11. The computer system of claim 10, wherein one or more parsing rules are used to parse the electronic message, assign the sentiment indicator, and assign the score.

12. The computer system of claim 10, wherein the operations further comprise:

notifying the user of the sentiment by providing an emoticon representing the sentiment.

13. The computer system of claim 10, wherein the operations further comprise:

notifying the user of the sentiment by providing text describing the sentiment.

14. The computer system of claim 10, wherein the operations further comprise:

providing suggestions of alternate language using one or more suggestion thesauri.

15. The computer system of claim 10, wherein the operations further comprise:

storing one or more sentiment dictionaries, wherein each of the one or more sentiment dictionaries is associated with a type of sentiment and includes terms classified as that sentiment.

16. The computer system of claim 10, wherein the operations further comprise:

storing one or more false-positive dictionaries, wherein each of the one or more false-positive dictionaries is associated with a type of sentiment and includes terms that are incorrectly classified as that sentiment; and

identifying sub-constructs that are not false-positive using the one or more false-positive dictionaries.

17. The computer system of claim 10, wherein the operations further comprise:

storing the one or more parsing rules that are created using one or more sentiment dictionaries and one or more false-positive dictionaries.

18. A computer program product for determining a sentiment of an electronic message, the computer program product comprising:

a computer readable storage medium having computer readable program code embodied therewith, wherein the computer readable program code, when executed by a processor of a computer, is configured to perform;

parsing, using a processor of a computer, the electronic message to identify one or more sub-constructs;

for at least one of the sub-constructs that is not false-positive,

assigning a sentiment indicator from a set of types of sentiment indicators; and

assigning a score for the sentiment indicator;

obtaining a final score for at least one type of sentiment indicator in the electronic message by summing scores for that type of sentiment indicator; and

based on the final score for the at least one type of sentiment indicator, identifying a sentiment of the electronic message.

19. The computer program product of claim 18, wherein one or more parsing rules are used to parse the electronic message, assign the sentiment indicator, and assign the score.

20. The computer program product of claim 18, wherein the computer readable program code, when executed by the processor of the computer, is configured to perform:

notifying the user of the sentiment by providing an emoticon representing the sentiment.

21. The computer program product of claim 18, wherein the computer readable program code, when executed by the processor of the computer, is configured to perform:

notifying the user of the sentiment by providing text describing the sentiment.

22. The computer program product of claim 18, wherein the computer readable program code, when executed by the processor of the computer, is configured to perform:

providing suggestions of alternate language using one or more suggestion thesauri.

23. The computer program product of claim 18, wherein the computer readable program code, when executed by the processor of the computer, is configured to perform:

storing one or more sentiment dictionaries, wherein each of the one or more sentiment dictionaries is associated with a type of sentiment and includes terms classified as that sentiment.

24. The computer program product of claim 18, wherein the computer readable program code, when executed by the processor of the computer, is configured to perform:

storing one or more false-positive dictionaries, wherein each of the one or more false-positive dictionaries is associated with a type of sentiment and includes terms that are incorrectly classified as that sentiment; and

identifying sub-constructs that are not false-positive using the one or more false-positive dictionaries.

25. The computer program product of claim 18, wherein the computer readable program code, when executed by the processor of the computer, is configured to perform:

storing the one or more parsing rules that are created using one or more sentiment dictionaries and one or more false-positive dictionaries.