System and method for analyzing text using emotional intelligence factors

• US 8,463,594 B2
• Filed: 03/23/2009
• Issued: 06/11/2013
• Est. Priority Date: 03/21/2008
• Status: Expired due to Fees

• Current Assignee: Synapsify, Inc.
• Original Assignee: Sauriel, LLC
• Inventors: Au, Lawrence
• Primary Examiner(s): Shah, Paras D
• Application Number:
  US12/382,754
• Publication Number:
  US 20090248399A1
• Time in Patent Office: 1,541 Days
• Field of Search: None
• US Class Current: 704/9
• CPC Class Codes: G06F 40/237 Lexical tools

Abstract

A system, method and computer program products for facilitating the automated reading, disambiguation, analysis, indexing, retrieval and scoring of text by utilizing emotional intelligence-based factors. Text quality is scored based upon character development, rhythm, per-page quality, gaps, and climaxes, among other factors. The scores may be standardized by subtracting the population mean from an individual raw score and then dividing the difference by the population standard deviation.

Claims

1. A computer implemented method for automatically generating a computer analysis of a text comprising a plurality of words, the computer comprising a processor and a user interface, the method comprising:

receiving the text;

performing, via the processor, token-by-token analysis by tagging tokens of the text, based on mappings of literary DNA, with one of a contextual sentiment and a contextual emotion, wherein each of the tokens comprises letters or phonemes mapped to numbers, used to map literary DNA;

performing, via the processor, a segmentation analysis of the text using one of a dimension of sentiment and an emotional analysis and a rhetorical structure analysis; and

outputting, via the user interface, the computer analysis of the text;

wherein the computer analysis includes a classification, a categorization or a sorting of the text according to one of a sentiment, an emotion, a rhetorical structure and an ontological similarity.

2. The computer implemented method according to claim 1, wherein the dimension of sentiment is one of single-dimensional and multi-dimensional.

3. The computer implemented method according to claim 1, the text comprising a character, the method further comprising:

performing, via the processor, character-arc development; and

performing, via the processor, character resolution;

wherein the character-arc development and the character resolution are tracked along co-occurrences of the character with single- or multi-dimensional shifts in a sentiment or emotions in the text.

4. The computer implemented method according to claim 1, the text comprising a character, the method further comprising:

performing, via the processor, thematic development, tracked independently or along co-occurrences of the character, with single- or multi-dimensional shifts in a sentiment or emotion in the text.

5. The computer implemented method according to claim 3, the text having a text story, the method further comprising:

determining, via the processor, a quality of the text story, using a scoring system calibrated to actual sales of a sold text having a sold text story.

6. The computer implemented method according to claim 1, the text having an associated individual, the method further comprising:

generating, via the processor, a tool to improve the text for use by the individual.

7. The computer implemented method according to claim 1, the text comprising content, the content having a class, the method further comprising:

matching the class of the content of the text, the content being selected from the group consisting of advertising content, non-advertising content, peer-reviewed content, non-peer-reviewed content, controversial court decisions, and non-controversial court decisions.

8. The computer implemented method according to claim 1, the computer analysis including a classification, a categorization or a sorting of the text according to a sentiment, the outputting being performed via a primary-color display module that indicates a dimension of the sentiment.

9. The computer implemented method according to claim 1, the computer analysis including a classification of the text into classes, the outputting being performed via a primary-color display module that indicates the classes.

10. The computer implemented method according to claim 1, further comprising:

generating a quality measure of the text for informing potential readers of the quality of text.

11. The computer implemented method according to claim 1, further comprising:

performing, via the processor, anaphor resolution of the text.

12. The computer implemented method according to claim 1, wherein the user interface is a conversation interface.

13. The computer implemented method according to claim 1, further comprising:

performing an analysis of sentiment or emotion based on a measure of contextual sentiment and a contextual emotion similarity between rhetorically or ontologically similar texts.

14. A system for automatically generating a computer analysis of a text comprising a plurality of words, the system comprising a computer processor and a user interface, the system further comprising:

a receiving module for receiving the text;

a first performing module for performing, via the processor, token-by-token analysis by tagging tokens of the text, based on mappings of literary DNA, with one of a contextual sentiment and a contextual emotion, wherein each of the tokens comprises letters or phonemes mapped to numbers, used to map literary DNA;

a second performing module for performing, via the processor, a segmentation analysis of the text using one of a dimension of sentiment and an emotional analysis; and

an output module for outputting, via the user interface, the computer analysis of the text;

wherein the computer analysis includes a classification, a categorization, a disambiguation of the text or a sorting of the text according to one of a sentiment, an emotion and an ontological similarity.

15. The system according to claim 14, further comprising:

an analysis module for analyzing sentiment or emotion based on a measure of contextual sentiment and a contextual emotion similarity between rhetorically or ontologically similar texts.

16. The system according to claim 14, the text comprising a character, the system further comprising:

a first performing module for performing, via the processor, character-arc development; and

a second performing module for performing, via the processor, character resolution;

wherein the character-arc development and the character resolution are tracked along co-occurrences of the character with single- or multi-dimensional shifts in a sentiment or an emotions in the text.

17. A system for automatically generating a computer analysis of a text comprising a plurality of words, the system comprising:

a processor;

a user interface functioning via the processor; and

a repository accessible by the processor;

wherein a text including a plurality of words is received;

wherein token-by-token analysis is performed via the processor by tagging tokens of the text, based on mappings of literary DNA, with one of a contextual sentiment and a contextual emotion, wherein each of the tokens comprises letters or phonemes mapped to numbers, used to map literary DNA;

wherein a segmentation analysis of the text is performed via the processor using one of a dimension of sentiment and an emotional analysis; and

wherein the computer analysis of the text is outputted via the user interface, the computer analysis including a classification, a categorization, a disambiguation of the text or a sorting of the text according to one of a sentiment, an emotion and an ontological similarity.

18. The system according to claim 17, wherein an analysis of sentiment or emotion is performed based on a measure of contextual sentiment and a contextual emotion similarity between rhetorically or ontologically similar texts.

19. A computer program product comprising a non-transitory computer usable medium having control logic stored therein for causing a computer to automatically generate a computer analysis of a text comprising a plurality of words, the computer comprising a processor and a user interface, the control logic comprising:

first computer readable program code means for receiving the text;

second computer readable program code means for performing, via the processor, token-by-token analysis by tagging tokens of the text, based on mappings of literary DNA, with one of a contextual sentiment and a contextual emotion, wherein each of the tokens comprises letters or phonemes mapped to numbers, used to map literary DNA;

third computer readable program code means for performing, via the processor, a segmentation analysis of the text using one of a dimension of sentiment and an emotional analysis and a rhetorical structure analysis; and

fourth computer readable program code means for outputting, via the user interface, the computer analysis of the text;

wherein the computer analysis includes a classification, a categorization or a sorting of the text according to one of a sentiment, an emotion, a rhetorical structure and an ontological similarity.