Method for detecting deception and predicting interviewer accuracy in investigative interviewing using interviewer, interviewee and dyadic physiological and behavioral measurements

Patent metadata

Field	Value
Publication number	US-2016354024-A1
Application number	US-201514728527-A
Country	US
Kind code	A1
Filing date	Jun 2, 2015
Priority date	Jun 2, 2015
Publication date	Dec 8, 2016
Grant date	—

Abstract

Existing approaches for deception detection are primarily based on polygraph systems that measure specific channels of physiology in highly structured interviews and that are interpreted by trained polygraph examiners. Existing approaches for predicting interviewer accuracy involve interviewers' own estimates of their performances which inevitably are biased. The methods and systems described herein provides objective, quantitative and automated metrics to detect deception and predict interviewer accuracy. Physiological information of the interviewer during the interview is recorded by at least a first sensor. The physiological information includes a time series of physiological data. An interview assessment is calculated by a computer. By processing the recorded physiological information, the interview assessment indicates at least one of whether a statement made by the interviewee is likely to be deceitful and whether the interviewer is likely to be accurate in estimating truthfulness of the interviewee. The interview assessment is output by the computer.

First claim

What is claimed is:

1 . A method of detecting deception by an interviewee and predicting accuracy by an interviewer in an interview conducted by the interviewer, comprising:
recording, by at least a first sensor, physiological information of the interviewer during the interview, wherein the physiological information includes a time series of physiological data; calculating, by a computer, an interview assessment by processing the recorded physiological information, the interview assessment indicating at least one of whether a statement made by the interviewee is likely to be deceitful and whether the interviewer is likely to be accurate in estimating truthfulness of the interviewee; and outputting, by the computer, the interview assessment.

2 . The method according to claim 1 , wherein the physiological data comprises at least one of electrocardiogram data, skin conductance data, and pulse oximetry data.

3 . The method according to claim 1 , wherein the physiological data comprises a time series of electrocardiogram recordings of the interviewer, and processing the physiological information comprises at least one of calculating a level of entropy of the electrocardiogram recordings, a heart rate, and time intervals between consecutive normal sinus beats.

4 . The method according to claim 1 , further comprising recording by at least a second sensor, physiological information of the interviewee during the interview, wherein processing the physiological information comprises performing dyadic analysis of the recorded physiological information of the interviewer with the recorded physiological information of the interviewee.

5 . The method according to claim 4 , wherein the dyadic analysis comprises applying an auto-regressive integrated moving average analysis to the physiological information of the interviewer and the interviewee, and determining at least one of an influence relationship between changes in the physiological information of interviewer and the interviewee and a degree of coherence between the physiological information of interviewer and the interviewee.

6 . The method according to claim 1 , wherein calculating the interview assessment further comprises determining by the computer at least one of an influence relationship and a level of coherence between bodily motions of the interviewer and the interviewee.

7 . The method according to claim 6 , further comprising recording video of the interview and processing the recorded video to generate an interviewer bodily motion time series and an interviewee bodily motion time series, wherein the determining by the computer at least one of the influence relationship and the level of coherence between bodily motions of the interviewer and the interviewee comprises processing the interviewer bodily motion time series and the interviewee bodily motion time series.

8 . The method according to claim 6 , wherein the interviewer bodily motion time series and the interviewee bodily motion time series indicate times at which the interviewer and interviewee, respectively, moved their respective limbs or appendages.

9 . The method according to claim 6 , wherein the determining by the computer at least one of an influence relationship and a level of coherence between bodily motions of the interviewer and the interviewee comprises modelling the bodily motions of the interviewer and interviewee as a coupled Hidden Markov Model.

10 . A system of detecting deception by an interviewee and predicting accuracy by an interviewer in an interview conducted by the interviewer, comprising:
at least a first sensor configured to record physiological information of the interviewer during the interview, wherein the physiological information includes a time series of physiological data; a processor configured to calculate an interview assessment by processing the recorded physiological information, the interview assessment indicating at least one of whether a statement made by the interviewee is likely to be deceitful and whether the interviewer is likely to be accurate in estimating truthfulness of the interviewee; and an output device configured to output the interview assessment.

11 . The system according to claim 10 , wherein the physiological data comprises at least one of electrocardiogram data, skin conductance data, and pulse oximetry data.

12 . The system according to claim 10 , wherein the physiological data comprises a time series of electrocardiogram recordings of the interviewer, and processing the physiological information comprises at least one of calculating a level of entropy of the electrocardiogram recordings, a heart rate, and time intervals between consecutive normal sinus beats.

13 . The system according to claim 10 , further comprising at least a second sensor configured to record physiological information of the interviewee during the interview, wherein, when the processor processes the physiological information, the processor is configured to perform dyadic analysis of the recorded physiological information of the interviewer with the recorded physiological information of the interviewee.

14 . The system according to claim 13 , wherein, when the processor performs dyadic analysis, the processor is configured to apply an auto-regressive integrated moving average analysis to the physiological information of the interviewer and the interviewee, and determine at least one of an influence relationship between changes in the physiological information of interviewer and the interviewee and a degree of coherence between the physiological information of interviewer and the interviewee.

15 . The system according to claim 10 , wherein, when the processor calculates the interview assessment, the processor is configured to further determine at least one of an influence relationship and a level of coherence between bodily motions of the interviewer and the interviewee.

16 . The system according to claim 15 , further comprising a video recording device configured to record a video of the interview and process the recorded video to generate an interviewer bodily motion time series and an interviewee bodily motion time series, wherein, when the processor determines at least one of the influence relationship and the level of coherence between bodily motions of the interviewer and the interviewee, the processor is configured to process the interviewer bodily motion time series and the interviewee bodily motion time series.

17 . The system according to claim 16 , wherein the interviewer bodily motion time series and the interviewee bodily motion time series indicate times at which the interviewer and interviewee, respectively, moved their respective limbs or appendages.

18 . The system according to claim 16 , wherein, when the processor determines at least one of the influence relationship and the level of coherence between bodily motions of the interviewer and the interviewee, the processor is configured to model the bodily motions of the interviewer and interviewee as a coupled Hidden Markov Model.

19 . A non-transitory computer readable medium storing a computer-readable program of detecting deception by an interviewee and predicting accuracy by an interviewer in an interview conducted by the interviewer, comprising:
computer-readable instructions to record, from at least a first sensor, physiological information of the interviewer during the interview, wherein the physiological information includes a time series of physiological data; computer-readable instructions to calculate

Assignees

• Charles Stark Draper Laboratory Inc

Inventors

• Keshava Nirmal
• Webb Andrea K
• Mariano Laura J
• Parks Philip D
• Poore Joshua C

Classifications

• A61B5/04012

  Human Necessities · mapped topic

• A61B5/164 Primary

  Lie detection · CPC title

• A61B5/0205

  Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition · CPC title

• A61B5/0402

  Human Necessities · mapped topic

• A61B5/0531

  Measuring skin impedance · CPC title