Method and system for the automatic recognition of deceptive language

• US 20070010993A1
• Filed: 12/08/2005
• Published: 01/11/2007
• Est. Priority Date: 12/10/2004
• Status: Active Grant

• Current Assignee: Deception Discovery Technologies LLC
• Original Assignee: Deception Discovery Technologies LLC
• Inventors: Bachenko, Joan, Schonwetter, Michael
• Granted Patent: US 7,853,445 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

A system for identifying deception within a text includes a processor for receiving and processing a text file. The processor includes a deception indicator tag analyzer for inserting into the text file at least one deception indicator tag that identifies a potentially deceptive word or phrase within the text file, and an interpreter for interpreting the at least one deception indicator tag to determine a distribution of potentially deceptive word or phrases within the text file and generating deception likelihood data based upon the density or distribution of potentially deceptive word or phrases within the text file. A method for identifying deception within a text includes the steps of receiving a first text to be analyzed, normalizing the first text to produce a normalized text, inserting into the normalized text at least one part-of-speech tag that identifies a part of speech of a word associated with the part-of-speech tag, inserting into the normalized text at least one syntactic label that identifies a linguistic construction of one or more words associated with the syntactic label, inserting into the normalized text at least one deception indicator tag that identifies a potentially deceptive word or phrase within the normalized text, interpreting the at least one deception indicator tag to determine a distribution of potentially deceptive word or phrases within the normalized text, and generating deception likelihood data based upon the density or frequency of distribution of potentially deceptive word or phrases within the normalized text.

Claims

1. A system for identifying deception within a text, comprising:

a processor for receiving and processing a text file, said processor having

a deception indicator tag analyzer for inserting into the text file at least one deception indicator tag that identifies a potentially deceptive word or phrase within the text file, and

an interpreter for interpreting the at least one deception indicator tag to determine a distribution of potentially deceptive word or phrases within the text file and generating deception likelihood data based upon the distribution of potentially deceptive word or phrases within the text file.

2. A system according to claim 1, further comprising a display for displaying the deception likelihood data according to one or more levels of likely deception.

3. A system according to claim 1, wherein the processor further comprises

a receiver for receiving a first text file to be analyzed;

a component for normalizing the first text file to produce a normalized text;

a component for inserting into the normalized text file at least one part-of-speech tag that identifies a part of speech of a word associated with the part-of-speech tag; and

a component for inserting into the normalized text file at least one syntactic label that identifies a linguistic construction of one or more words associated with the syntactic label,

wherein the normalized text file including the at least one part-of-speech tag and the at least one syntactic label is provided to the deception indicator tag analyzer.

4. A system according to claim 3, wherein the deception indicator tag analyzer inserts the deception indicator tag into the normalized text file based upon words or phrases in the normalized text, part-of-speech tags inserted into the normalized text file, and syntactic labels inserted in the normalized text file.

5. A system according to claim 4, wherein the deception indicator tags are associated with a defined word or phrase.

6. A system according to claim 4, wherein the deception indicator tags are associated with a defined word or phrase when used in a defined linguistic context.

7. A system according to claim 1, wherein the interpreter calculates a proximity metric for each word or phrase in the text file based upon the proximity of the word or phrase to a deception indicator tag, wherein the proximity metric comprises a portion of the deception likelihood data.

8. A system according to claim 7, wherein the interpreter calculates a moving average metric for each word or phrase in the text file based upon the proximity metric of the word or phrase, wherein the moving average metric comprises a portion of the deception likelihood data.

9. A system according to claim 8, wherein the calculation of the moving average metric for each word or phrase in the text file may be adjusted by a user of the system to focus the deception likelihood data within a text window length as specified in a configuration file.

10. A system according to claim 8, wherein the moving average metric associated with each word or phrase within the text file is used to determine a level of potential deception likelihood for the associated word or phrase.

11. A method for identifying deception within a text, comprising the steps of:

receiving a first text to be analyzed;

normalizing the first text to produce a normalized text;

inserting into the normalized text at least one part-of-speech tag that identifies a part of speech of a word associated with the part-of-speech tag;

inserting into the normalized text at least one syntactic label that identifies a linguistic construction of one or more words associated with the syntactic label;

inserting into the normalized text at least one deception indicator tag that identifies a potentially deceptive word or phrase within the normalized text, interpreting the at least one deception indicator tag to determine a distribution of potentially deceptive word or phrases within the normalized text; and

generating deception likelihood data based upon the distribution of potentially deceptive word or phrases within the normalized text.

12. A method according to claim 11, further comprising the step of displaying the deception likelihood data according to one or more levels of likely deception.

13. A method according to claim 11, wherein the deception indicator tag analyzer inserts the deception indicator tag into the normalized text based upon words or phrases in the normalized text, part-of-speech tags inserted into the normalized text, and syntactic labels inserted in the normalized text.

14. A method according to claim 13, wherein the deception indicator tags are associated with a defined word or phrase.

15. A method according to claim 13, wherein the deception indicator tags are associated with a defined word or phrase when used in a defined linguistic context.

16. A method according to claim 11, wherein the step of interpreting the at least one deception indicator tag comprises the step of:

calculating a proximity metric for each word or phrase in the text file based upon the proximity of the word or phrase to a deception indicator tag, wherein the proximity metric comprises a portion of the deception likelihood data.

17. A method according to claim 16, wherein the step of interpreting the at least one deception indicator tag further comprises the step of:

calculating a moving average metric for each word or phrase in the text file based upon the proximity metric of the word or phrase, wherein the moving average metric comprises a portion of the deception likelihood data.

18. A method according to claim 17, wherein the calculation of the moving average metric for each word or phrase in the text file may be adjusted by a user of the system to focus the deception likelihood data within a text window length as specified in a configuration file.

19. A method according to claim 18, wherein the moving average metric associated with each word or phrase within the text file is used to determine a level of potential deception likelihood for the associated word or phrase.

20. A method according to claim 11, wherein the step of receiving a first text to be analyzed comprises receiving a live feed from a real-time transcription of a person'"'"'s utterances and the deception likelihood data is generated in real time.

21. An article of manufacture comprising:

a computer readable medium; and

program code on the computer readable medium for identifying deception within a text, wherein the program code directs a computer to perform a method comprising the steps of;

controlling a deception indicator tag analyzer for inserting into the text file at least one deception indicator tag that identifies a potentially deceptive word or phrase within the text file, and

controlling an interpreter for interpreting the at least one deception indicator tag to determine a distribution of potentially deceptive word or phrases within the text file and generating deception likelihood data based upon the distribution of potentially deceptive words or phrases within the text file.

22. An article of manufacture according to claim 21, further comprising program code for:

receiving a first text to be analyzed;

normalizing the first text to produce a normalized text;

inserting into the normalized text at least one part-of-speech tag that identifies a part of speech of a word associated with the part-of-speech tag; and

inserting into the normalized text at least one syntactic label that identifies a linguistic construction of one or more words associated with the syntactic label; and

wherein the program code for the deception indicator tag analyzer inserts into the normalized text at least one deception indicator tag that identifies a potentially deceptive word or phrase within the normalized text, and the program code for the interpreter interprets the at least one deception indicator tag to determine a distribution of potentially deceptive words or phrases within the normalized text and generates deception likelihood data based upon the distribution of potentially deceptive word or phrases within the normalized text.