×

Method and system for the automatic recognition of deceptive language

  • US 7,853,445 B2
  • Filed: 12/08/2005
  • Issued: 12/14/2010
  • Est. Priority Date: 12/10/2004
  • Status: Expired due to Fees
First Claim
Patent Images

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

  • a processor for storing and processing a text file containing statements from a particular person whose credibility is being weighed as to verifiable propositions included in the text; and

    a memory;

    a deception indicator tag analyzer stored in memory and executing on the processor for inserting into the stored text file at least one deception indicator tag that identifies a potentially deceptive word or phrase at its location within the text file, andan interpreter stored in memory and executing on the processor for(a) interpreting the at least one deception indicator tag to determine a distribution of potentially deceptive words or phrases within the text file and for computing and storing for user review deception likelihood data based upon the distribution of potentially deceptive words or phrases within the text file, said deception likelihood data including a calculated distribution proximity metric for a plurality of words or phrases in the text file based upon the proximity of a word or phrase to the at least one deception indicator tag; and

    (b) marking words in the text file with differentiating indicia showing the proximity level calculated, to identify areas of the text file more likely to involve deception.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×