Device and method of determining emotive index corresponding to a message

• US 6,999,914 B1
• Filed: 09/28/2000
• Issued: 02/14/2006
• Est. Priority Date: 09/28/2000
• Status: Expired due to Fees

• Current Assignee: Manning & Napier Information Services LLC
• Original Assignee: Manning & Napier Information Services LLC
• Inventors: Frey, James, Boerner, Peer
• Primary Examiner(s): Ometz, David L.
• Assistant Examiner(s): Sked, Matthew J
• Application Number:
  US09/676,296
• Time in Patent Office: 1,965 Days
• Field of Search: 704/1, 704 2- 6, 704/9, 395/708, 395/751, 707/5, 715530-532
• US Class Current: 704/1
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

The invention includes a method and a device for determining an emotive index for a message. In the method, a message is received and words in the message are identified for analysis. An emotive index corresponding to the identified words is then determined. The emotive index is preferably a function of a word count index corresponding to the number of identified words, an affinity index and an antagonism index. A device according to the present invention includes a computer readable storage medium having encoded thereon computer readable instructions capable of instructing a computer to carry out the method.

Claims

1. A method of determining an emotive index for a message, comprising:

receiving a message;

identifying words to be analyzed in the message to provide identified words;

incrementing a word count value each time an identified word is encountered until an ending point is reached;

determining whether the word count value is greater than a threshold value;

setting a word count index equal to a first value if the word count value is greater than a threshold value, and setting the word count index equal to a second value if the word count value is not greater than the threshold value;

changing an emotive index by the word count index;

providing a list of intensifiers;

analyzing the identified words to find an intensifier;

providing a list of affinity indicators;

analyzing the identified words to find affinity indicators;

locating an affinity indicator nearest to the intensifier;

changing an affinity index by an affinity amount corresponding to the intensifier and the affinity indicator nearest to the intensifier; and

changing the emotive index by the affinity index.

2. The method of claim 1, wherein identifying words to be analyzed in the message includes:

identifying noise text in the message; and

excluding the noise text from the identified words.

3. The method of claim 2, wherein the noise text is an earlier message.

4. The method of claim 2, wherein the noise text is a footer.

5. The method of claim 2, wherein the noise text is primarily comprised of words that have been cut from a document and pasted into the message.

6. The method of claim 1, further comprising;

identifying noise text in the message;

counting the number of words in the noise text; and

decrementing the word count value by a noise text amount corresponding to the number of words in the noise text.

7. The method of claim 6, wherein the noise text is an earlier message.

8. The method of claim 6, wherein the noise text is a footer.

9. The method of claim 6, wherein the noise text is primarily comprised of words that have been cut from a document and pasted into the message.

10. The method of claim 1, wherein the ending point is reached once the word count value is equal to the threshold value.

11. The method of claim 1, wherein the ending point is reached once the last word in the message has been counted.

12. The method of claim 1, further comprising:

determining whether the word count index is less than a threshold value; and

providing an indication that the emotive index can not be determined.

13. The method of claim 1, wherein the affinity amount is determined by counting the number of times the affinity indicator is identified in the identified words.

14. The method of claim 1, wherein the affinity amount is a first value if the affinity indicator is found at least once in the identified words.

15. The method of claim 1, wherein the affinity indicator is identified if a first word and a second word are found in the identified words.

16. The method of claim 1, wherein the affinity indicator is a phrase.

17. The method of claim 1, wherein the affinity indicator is a group of words.

18. The method of claim 1, further comprising:

providing a list of intensifiers;

analyzing the identified words to find an intensifier;

changing an intensifier index by an intensifier amount, if the intensifier is found in the identified words; and

changing the emotive index by an additional amount corresponding to the intensifier index and the affinity index.

19. The method of claim 18, wherein the intensifier is an adjective.

20. The method of claim 18, wherein the intensifier is an adverb.

21. The method of claim 1, further comprising:

grouping the affinity indicators into at least two classes;

determining which classes were found in the identified words; and

sending a signal if a predetermined group of classes is among the classes found in the identified words.

22. The method of claim 21, further comprising:

determining a class value corresponding to those affinity indicators of a sampling class found in the identified words; and

changing the emotive index by the class value.

23. The method of claim 1, further comprising:

providing a list of antagonism indicators;

analyzing the identified words to find an antagonism indicator;

changing an antagonism index by an antagonism amount, if the antagonism indicator is found; and

changing the emotive index by the antagonism index.

24. The method of claim 23, wherein the antagonism amount is determined by counting the number of times the antagonism indicator is found in the identified words.

25. The method of claim 23, wherein the antagonism amount is a first value if the antagonism indicator is found at least once in the identified words.

26. The method of claim 23, wherein the antagonism indicator is found if a first word and a second word are found in the identified words.

27. The method of claim 23, wherein the antagonism indicator is a phrase.

28. The method of claim 23, wherein the antagonism indicator is a group of words.

29. The method of claim 23, further comprising:

changing an intensifier index by an intensifier amount, if the intensifier is found in the identified words; and

changing the emotive index by an additional amount corresponding to the intensifier index and the antagonism index.

30. The method of claim 29, wherein the intensifier is an adjective.

31. The method of claim 29, wherein the intensifier is an adverb.

32. The method of claim 23, further comprising:

grouping the antagonism indicators into at least two classes;

determining which classes were found in the identified words; and

sending a signal if a predetermined group of classes is among the classes found in the identified words.

33. The method of claim 1, further comprising:

providing a list of antagonism indicators in a sampling class;

analyzing the identified words to find the antagonism indicators;

determining a class value corresponding to the antagonism indicators of the sampling class found in the identified words;

determining an antagonism amount corresponding to the class value;

changing an antagonism index by the antagonism amount; and

changing the emotive index by the antagonism index.

34. The method of claim 1, further comprising:

providing a list of antagonism indicators;

analyzing the identified words to find antagonism indicators;

locating an antagonism indicator nearest to the intensifier;

changing an antagonism index by an antagonism amount corresponding to the intensifier and the antagonism indicator nearest to the intensifier; and

changing the emotive index by the antagonism index.

35. A method of determining an emotive index for a message, comprising:

receiving a message;

identifying words to be analyzed in the message to provide identified words;

providing a list of affinity indicators;

analyzing the identified words to find an affinity indicator in the message;

changing an affinity index by an affinity amount corresponding to the affinity indicator found in the message;

providing a list of antagonism indicators;

analyzing the identified words to find an antagonism indicator in the message;

changing an antagonism index by an antagonism amount corresponding to the antagonism indicator found in the message;

changing an emotive index by a difference amount equal to the difference between the absolute value of the affinity index and the absolute value of the antagonism index;

providing a list of intensifiers;

analyzing the identified words to find intensifiers in the message;

changing an intensifier index by an intensifier amount;

comparing the absolute value of the affinity index to the absolute value of the antagonism index to determine which absolute value is greater;

selecting the affinity index if the absolute value of the affinity index is greater than the absolute value of the antagonism index, and selecting the antagonism index if the absolute value of the antagonism index is greater than the absolute value of the affinity index; and

changing the emotive index by a modified index corresponding to the intensifier index multiplied by the selected one of the affinity index and the antagonism index.

36. The method of claim 35, further comprising changing the emotive index by an additional amount equal to the affinity index if the antagonism index was selected, and equal to the antagonism index if the affinity index was selected.

37. The method of claim 35, wherein the intensifier amount corresponds to the intensifiers found in the identified words.

38. The method of claim 35, further comprising:

grouping the affinity indicators into at least two classes;

grouping the antagonism indicators into at least two additional classes;

determining which classes were found in the identified words; and

sending a signal if a predetermined group of classes is among the classes found in the identified words.

39. The method of claim 35, further comprising:

grouping the affinity indicators into at least a first class and a second class;

grouping the antagonism indicators into at least a third class and a fourth class;

determining which classes were found in the identified words; and

sending a signal if at least one of the classes was found in the identified words and if at least one of the classes was not found in the identified words.

40. The method of claim 35, further comprising:

incrementing a word count value each time an identified word is found until an ending point is reached;

determining whether the word count value is greater than a threshold value;

setting a word count index equal to a first value if the word count value is greater than the threshold value, and setting the word count index equal to a second value if the word count value is not greater than the threshold value; and

changing the emotive index by the word count index.

41. A computer readable storage medium having encoded thereon computer readable instructions capable of instructing a computer to:

receive a message;

identify words to be analyzed in the message to provide identified words;

increment a word count value each time one of the identified words is found until an ending point is reached;

determine whether the word count value is greater than a threshold value;

set a word count index equal to a first value if the word count value is greater than the threshold value, and set the word count index equal to a second value if the word count value is not greater than the threshold value;

change an emotive index by the word count index;

provide a list of intensifiers;

analyze the identified words to find an intensifier;

provide a list of affinity indicators;

analyze the identified words to find affinity indicators;

locate an affinity indicator nearest to the intensifier;

change an affinity index by an affinity amount corresponding to the intensifier and the affinity indicator nearest to the intensifier; and

change the emotive index by the affinity index.

42. A computer readable storage medium having encoded thereon computer readable instructions capable of instructing a computer to:

receive a message;

identify words to be analyzed in the message to provide identified words;

receive a list of affinity indicators;

analyze the identified words to find an affinity indicator in the message;

change an affinity index by an affinity amount corresponding to the affinity indicator found in the message;

receive a list of antagonism indicators;

analyze the identified words to find an antagonism indicator in the message;

change an antagonism index by an antagonism amount corresponding to the antagonism indicator found in the message;

provide a list of intensifiers;

analyze the identified words to find intensifiers in the message;

change an intensifier index by an intensifier amount;

compare the absolute value of the affinity index to the absolute value of the antagonism index to determine which absolute value is greater;

select the affinity index if the absolute value of the affinity index is greater than the absolute value of the antagonism index, and selecting the antagonism index if the absolute value of the antagonism index is greater than the absolute value of the affinity index; and

change the emotive index by a modified index corresponding to the intensifier index multiplied by the selected one of the affinity index and the antagonism index.

43. A method of determining an emotive index for a message, comprising:

receiving a message;

identifying words to be analyzed in the message to provide identified words;

incrementing a word count value each time an identified word is encountered until an ending point is reached;

determining whether the word count value is greater than a threshold value;

setting a word count index equal to a first value if the word count value is greater than a threshold value, and setting the word count index equal to a second value if the word count value is not greater than the threshold value;

changing an emotive index by the word count index;

providing a list of intensifiers;

analyzing the identified words to find an intensifier;

providing a list of antagonism indicators;

analyzing the identified words to find antagonism indicators;

locating an antagonism indicator nearest to the intensifier;

changing an antagonism index by an antagonism amount corresponding to the intensifier and the antagonism indicator nearest to the intensifier; and

changing the emotive index by the antagonism index.

44. The method of claim 43, wherein identifying words to be analyzed in the message includes:

identifying noise text in the message; and

excluding the noise text from the identified words.

45. The method of claim 44, wherein the noise text is an earlier message.

46. The method of claim 44, wherein the noise text is a footer.

47. The method of claim 44, wherein the noise text is primarily comprised of words that have been cut from a document and pasted into the message.

48. The method of claim 43, further comprising;

identifying noise text in the message;

counting the number of words in the noise text; and

decrementing the word count value by a noise text amount corresponding to the number of words in the noise text.

49. The method of claim 48, wherein the noise text is an earlier message.

50. The method of claim 48, wherein the noise text is a footer.

51. The method of claim 48, wherein the noise text is primarily comprised of words that have been cut from a document and pasted into the message.

52. The method of claim 43, wherein the ending point is reached once the word count value is equal to the threshold value.

53. The method of claim 43, wherein the ending point is reached once the last word in the message has been counted.

54. The method of claim 43, further comprising:

determining whether the word count index is less than a threshold value; and

providing an indication that the emotive index can not be determined.

55. The method of claim 43, wherein the antagonism amount is determined by counting the number of times the antagonism indicator is identified in the identified words.

56. The method of claim 43, wherein the antagonism amount is a first value if the antagonism indicator is found at least once in the identified words.

57. The method of claim 43, wherein the antagonism indicator is identified if a first word and a second word are found in the identified words.

58. The method of claim 43, wherein the antagonism indicator is a phrase.

59. The method of claim 43, wherein the antagonism indicator is a group of words.

60. The method of claim 43, further comprising:

changing an intensifier index by an intensifier amount, if the intensifier is found in the identified words; and

changing the emotive index by an additional amount corresponding to the intensifier index and the antagonism index.

61. The method of claim 60, wherein the intensifier is an adjective.

62. The method of claim 60, wherein the intensifier is an adverb.

63. The method of claim 43, further comprising:

grouping the antagonism indicators into at least two classes;

determining which classes were found in the identified words; and

sending a signal if a predetermined group of classes is among the classes found in the identified words.

64. The method of claim 63, further comprising:

determining a class value corresponding to those antagonism indicators of a sampling class found in the identified words; and

changing the emotive index by the class value.

65. The method of claim 43, further comprising:

providing a list of affinity indicators;

analyzing the identified words to find an affinity indicator;

changing an affinity index by an affinity amount, if the affinity indicator is found; and

changing the emotive index by the affinity index.

66. The method of claim 65, wherein the affinity amount is determined by counting the number of times the affinity indicator is found in the identified words.

67. The method of claim 65, wherein the affinity amount is a first value if the affinity indicator is found at least once in the identified words.

68. The method of claim 65, wherein the affinity indicator is found if a first word and a second word are found in the identified words.

69. The method of claim 65, wherein the affinity indicator is a phrase.

70. The method of claim 65, wherein the affinity indicator is a group of words.

71. The method of claim 65, further comprising:

changing an intensifier index by an intensifier amount, if the intensifier is found in the identified words; and

changing the emotive index by an additional amount corresponding to the intensifier index and the affinity index.

72. The method of claim 71, wherein the intensifier is an adjective.

73. The method of claim 71, wherein the intensifier is an adverb.

74. The method of claim 65, further comprising:

grouping the affinity indicators into at least two classes;

determining which classes were found in the identified words; and

sending a signal if a predetermined group of classes is among the classes found in the identified words.

75. The method of claim 43, further comprising:

providing a list of affinity indicators in a sampling class;

analyzing the identified words to find the affinity indicators;

determining a class value corresponding to the affinity indicators of the sampling class found in the identified words;

determining an affinity amount corresponding to the class value;

changing an affinity index by the affinity amount; and

changing the emotive index by the affinity index.

76. The method of claim 43, further comprising:

providing a list of affinity indicators;

analyzing the identified words to find affinity indicators;

locating an affinity indicator nearest to the intensifier;

changing an affinity index by an affinity amount corresponding to the intensifier and the affinity indicator nearest to the intensifier; and

changing the emotive index by the affinity index.