Identifying deceptive answers to online questions through human-computer interaction data

Patent metadata

Field	Value
Publication number	US-10524713-B2
Application number	US-201414899865-A
Country	US
Kind code	B2
Filing date	Jun 18, 2014
Priority date	Jun 19, 2013
Publication date	Jan 7, 2020
Grant date	Jan 7, 2020

Abstract

The present invention provides a system and a method for eliciting information to sensitive questions and reliably detecting whether one is being deceptive, concealing information, or experiencing a heightened emotional response to the question. In particular, the system and the method of the invention are based on analyzing the user behavioral biometric of using one or more input device(s).

First claim

What is claimed is:

1. A real-time behavioral biometric-based deception analysis system for determining whether a subject is truthful or deceptive to a question of interest that is presented on a display screen, said system comprising:
a data interception unit configured to intercept input in real-time from a subject that is directed to a question presented on a display screen, wherein the data interception unit is configured to passively collect a pointing device usage characteristic in real-time;
a behavior analysis unit operatively coupled to said data interception unit to receive the passively collected pointing device usage characteristic; and
a behavior comparison unit operatively coupled to said behavior analysis unit, wherein said system dynamically monitors and passively collects behavioral biometric information in real-time, and translates said behavioral biometric information into representative data comprised of cursor trajectory data, wherein the representative data is normalized against population data and the cursor trajectory data is rescaled to account for screen resolution, stores and compares results, and outputs a result associated with truthfulness or deception of the subject to the question of interest presented on the display screen.

2. The behavioral biometric-based deception analysis system of claim 1 , wherein said behavior comparison unit is operatively connected to an application for presenting a question on the display screen such that said behavior comparison unit influences the next question presented on the display screen using a decision tree structure based on the result.

3. The behavioral biometric-based deception analysis system of claim 1 , wherein said pointing device usage characteristic comprises movement of said pointing device between the starting position of said pointing device and the answer selected by the subject on the display screen, the elapsed time between presentation of the question on the display screen and the selection of the answer by the subject, or a combination thereof.

4. The behavioral biometric-based deception analysis system of claim 3 , wherein said pointing device usage characteristic comprises speed, total distance travelled, initial direction of movement, total response time, change in direction on the x-axis, change in direction on the y-axis, acceleration, idle time, area under the curve, amount of deviation, reaction time, changes in angle, or a combination of two or more thereof.

5. The behavioral biometric-based deception analysis system of claim 1 , wherein the behavior comparison unit compares the result of the subject's behavioral biometric to a reference behavioral biometric.

6. The behavioral biometric-based deception analysis system of claim 5 , wherein said reference behavioral biometric comprises the subject's behavioral biometric to a non-sensitive question.

7. The behavioral biometric-based deception analysis system of claim 5 , wherein said reference behavioral biometric comprises an average behavioral biometric to the same question presented on the display screen of a plurality of subjects.

8. The behavioral biometric-based deception analysis system of claim 1 , wherein said system is suitably configured for real-time deception analysis.

9. The behavioral biometric-based deception analysis system of claim 1 , wherein said data interception unit is further configured to passively collect keyboard usage characteristic of the subject.

10. A method for determining whether a subject is truthful or deceptive to a question of interest in real-time, said method comprising:
(a) presenting a first key question and a plurality of answers on a display screen;
(b) allowing a subject to select an answer using a pointing device;
(c) passively collecting the subject's pointing device usage characteristic in real-time, wherein the pointing device usage characteristic is normalized against population data and rescaled to account for screen resolution;
(d) comparing subject's pointing device characteristic with a reference pointing device usage characteristic to determine whether the subject is truthful or deceptive to the question of interest; and
(e) displaying a result associated with truthfulness or deception of the subject to the question of interest.

11. The method of claim 10 further comprising the steps of:
(a) presenting a first control question and a plurality of answers on a display screen;
(b) allowing the subject to select an answer using the pointing device;
(c) passively collecting pointing device usage characteristic of the subject in real-time; and
(d) storing passively collected pointing device usage characteristic of the subject as the reference pointing device usage characteristic.

12. The method of claim 10 , wherein said reference pointing device usage characteristic is an average pointing device usage characteristic of a plurality of subjects for the same question of interest.

13. The method of claim 10 , wherein said pointing device usage characteristic comprises pointing device movement between the starting position of pointing device and the answer selected by the subject on the display screen.

14. The method of claim 13 , wherein said pointing device usage characteristic comprises at least one of speed, total distance travelled, initial direction of movement, total response time, change in direction on the x-axis, change in direction on the y-axis, idle time, area under the curve, amount of deviation, reaction time, applied pressure, changes in angle, the pattern of a users' acceleration or deceleration during a movement, the precision of movements, the click latency, or click pressure.

15. The method of claim 10 , further comprising repeating all of steps (a)-(d) with a second key question prior to step (e).

16. The method of claim 15 , wherein the reference pointing device usage characteristic for the second key question is an average pointing device usage characteristic of a plurality of subjects for the same question of interest.

17. The method of claim 15 , wherein the pointing device usage characteristic for the second key question comprises pointing device movement between the starting position of pointing device and the answer selected by the subject on the display screen.

18. The method of claim 17 , wherein the pointing device usage characteristic for the second key question comprises at least one of speed, total distance travelled, initial direction of movement, total response time, change in direction on the x-axis, change in direction on the y-axis, idle time, area under the curve, amount of deviation, reaction time, applied pressure, changes in angle, the pattern of a users' acceleration or deceleration during a movement, the precision of movements, the click latency, or click pressure.

Assignees

• Arizona Board Of Regents For The Univ Of Arizona
• Univ Arizona

Inventors

• Valacich Joseph S
• Jenkins Jeffrey L

Classifications

• G06F21/40

  by quorum, i.e. whereby two or more security principals are required · CPC title

• G06F21/316 Primary

  by observing the pattern of computer usage, e.g. typical user behaviour · CPC title

• G06F21/32

  using biometric data, e.g. fingerprints, iris scans or voiceprints · CPC title

• A61B5/164 Primary

  Lie detection · CPC title