Method and System for Predicting Audience Viewing Behavior

• US 20100211439A1
• Filed: 03/29/2010
• Published: 08/19/2010
• Est. Priority Date: 09/05/2006
• Status: Active Grant

• Current Assignee: Nielsen Consumer LLC (Nielsen Holdings plc)
• Original Assignee: Innerscope Research, Inc. (Nielsen Holdings plc)
• Inventors: Levine, Brian, Siefert, Caleb J., Marci, Carl D., Kothuri, Ravi Kanth V
• Granted Patent: US 9,514,436 B2
• Time in Patent Office: Days
• US Class Current: 705/10
• CPC Class Codes: A61B 5/0002 Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network A61B5/07 takes precedence; transmission systems for measured values G08C; transmission H04B; transmission of digital information H04L; wireless communication networks H04W
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/0533 Measuring galvanic skin response
• CPC Class Codes: A61B 5/08 Detecting, measuring or recording devices for evaluating the respiratory organs A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/11 Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb for measuring pulse A61B5/02 ;A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721
• CPC Class Codes: A61B 5/16 Devices for psychotechnics using teaching or educational appliances G09B1/00 - G09B7/00; Testing reaction times ; Devices for evaluating the psychological state
• CPC Class Codes: A61B 5/163 by tracking eye movement, gaze, or pupil change
• CPC Class Codes: A61B 5/225 of the fingers, e.g. by monitoring hand-grip force
• CPC Class Codes: A61B 5/6897 Computer input devices, e.g. mice or keyboards
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: H04H 60/33 Arrangements for monitoring the users' behaviour or opinions
• CPC Class Codes: H04N 21/252 Processing of multiple end-users' preferences to derive collaborative data
• CPC Class Codes: H04N 21/25883 being end-user demographical data, e.g. age, family status or address arrangements for identifying locations of users in broadcast systems H04H60/52
• CPC Class Codes: H04N 21/42201 biosensors, e.g. heat sensor for presence detection, EEG sensors or any limb activity sensors worn by the user input arrangements for interaction with the human body based on nervous system activity detection G06F3/015
• CPC Class Codes: H04N 21/44218 Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program methods or arrangements for recognising human body or animal bodies or body parts G06V40/10; methods or arrangements for acquiring or recognising human faces, facial parts, facial sketches, facial expressions G06V40/16; methods or arrangements for recognising movements or behaviour G06V40/20; arrangements for identifying users in broadcast systems H04H60/45
• CPC Class Codes: H04N 21/4532 involving end-user characteristics, e.g. viewer profile, preferences monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/4662 characterized by learning algorithms
• CPC Class Codes: H04N 21/84 Generation or processing of descriptive data, e.g. content descriptors systems specially adapted for using meta-information in broadcast systems H04H60/73

Abstract

The present invention is directed to a method and system for predicting the behavior of an audience based on the biologically based responses of the audience to a presentation that provides a sensory stimulating experience and determining a measure of the level and pattern of engagement of that audience to the presentation. In particular, the invention is directed to a method and system for predicting whether an audience is likely to view a presentation in its entirety. In addition, the present invention may be used to determine the point at which an audience is likely to change their attention to an alternative sensory stimulating experience including fast forwarding through recorded content, changing the channel or leaving the room when viewing live content, or otherwise redirecting their engagement from the sensory stimulating experience.

Claims

1. A method for predicting viewership of a content stimulus comprising:

dividing the content stimulus into a preset number of intervals;

obtaining an engagement score for each interval of the presentation based on the biometrics of an audience;

using the engagement score to determine at least one metric selected from the group consisting of negative buildup, positive buildup, average engagement score, maximum engagement score, and combinations thereof; and

predicting viewership based on the at least one metric.

2. The method of claim 1 wherein the step of obtaining an engagement score comprises:

exposing the audience to the content stimulus over a period of time, wherein the period of time is divided into at least two intervals;

measuring at least one biologically based response to the content stimulus for each member of the sample population;

determining at least one intensity value as a function of at least one of the measured biologically based responses for each interval;

determining at least one synchrony value as a function of a rate of change of at least one of the measured biologically based responses for each interval; and

determining at least one engagement score for each interval as a function of at least one of the intensity values and at least one synchrony value.

3. The method of claim 2, wherein the step of measuring at least one biologically based response comprises:

measuring at least one of heart rate, skin conductance, respiration state, motion, and eye tracking.

4. The method of claim 1, wherein the step of using the engagement score to determine at least one metric comprises determining the positive buildup by:

setting at least one threshold value;

dividing the engagement curve into ascending segments defined by intervals that the engagement value remains relatively constant or increases;

computing the area above the threshold value for each such ascending segment;

summing the areas; and

dividing the sum by the duration of the content.

5. The method of claim 1, wherein the step of using the engagement score to determine at least one metric comprises determining the negative buildup by:

setting at least one threshold value;

dividing the engagement curve into descending segments defined by intervals that the engagement value remains relatively constant or decreases;

computing the area below the threshold value for each such descending segment;

summing the areas; and

dividing the sum by the duration of the content.

6. The method of claim 1, wherein the step of predicting viewership based on the at least one metric further comprises:

predicting viewership of the content stimulus based on predetermined correlations between the metric and actual viewership data previously collected.

7. The method of claim 1, wherein the step of predicting viewership based on the at least one metric further comprises:

determining whether a viewer will watch the entirety of the content stimulus when the content stimulus is previously recorded.

8. The method of claim 1, wherein the step of predicting viewership based on the at least one metric further comprises:

determining whether a viewer will watch the entirety of the content stimulus when the content stimulus is presented live.

9. The method of claim 1, wherein content stimulus comprises show segments, presentations, commercials, and combinations thereof.

10. The method of claim 1, wherein the step of predicting viewership comprises evaluating at least two metrics selected from the group consisting of negative buildup, positive buildup, average engagement score, maximum engagement score, and combinations thereof.

11. A computerized system for predicting viewership of a content stimulus comprising:

a plurality of sensors, each adapted for measuring a biologically based response to the presentation over a period;

the time period being divided into two or more time intervals;

a computer processing system adapted for receiving data relating to the presentation and data from the plurality of sensors providing a measure of at least one biologically based response to the content stimulus;

an intensity processing module adapted for determining, for each time interval, at least one intensity value as a function of at least one of the measured biologically based responses;

a synchrony processing module adapted for determining, for each time interval, at least one synchrony value as a function of at least one of the measured biologically based responses; and

an engagement processing module adapted for determining, for each time interval, at least one engagement value as a function of the at least one intensity value and the at least one synchrony value, and at least one metric selected from the groups consisting of negative buildup, positive buildup, average engagement score, and maximum engagement score.

12. The system of claim 11, further comprising:

a comparison module adapted for comparing said at least one engagement value to an engagement value stored in a database corresponding to a second content stimulus; and

an indicator adapted for indicating that the content stimulus is similar to the second content stimulus based on the comparison.

13. The system of claim 11, wherein the biologically based responses are chosen from the group consisting of heart rate, skin conductance, respiration state, motion, and eye tracking.

14. The system of claim 11, wherein the intensity processing module is adapted for determining the intensity value as a function of a standardized score and the standardized score is determined as a function of at least one of a peak value, a trough value, a median value, an average value and a rate of change value of at least one of the biologically based responses.

15. The system of claim 11, wherein said synchrony processing module is adapted for determining the synchrony value as a function of a variance of a rate of change value of at least one of the biologically based responses over at least a portion of the audience.

16. A method of validating metrics associated with viewership of a content stimulus comprising:

exposing the audience to the content stimulus over a period of time, wherein the period of time is divided into at least two intervals;

measuring at least one biologically based response to the content stimulus for each member of the sample population;

determining at least one intensity value as a function of at least one of the measured biologically based responses for each interval;

determining at least one synchrony value as a function of a rate of change of at least one of the measured biologically based responses for each interval; and

determining at least one engagement score for each interval as a function of at least one of the intensity values and at least one synchrony value;

using the engagement score to determine engagement metrics comprising negative buildup, positive buildup, average engagement score, and maximum engagement score;

normalizing the data; and

determining correlations between the engagement metrics and commercially available viewership retention numbers.

17. The method of claim 16, wherein the step of measuring at least one biologically based response comprises:

measuring at least one of heart rate, skin conductance, respiration rate, respiration state, motion, and eye tracking.

18. The method of claim 16, wherein the step of using the engagement score to determine engagement metrics comprises determining the negative buildup by:

setting at least one threshold value;

dividing the curve into descending segments defined by intervals that the engagement value remains relatively constant or decreases;

computing the area below the threshold value for each such ascending segment;

summing the areas; and

dividing the sum by the duration of the content.

19. The method of claim 16, wherein the step of using the engagement score to determine engagement metrics comprises determining the positive buildup by:

setting at least one threshold value;

dividing the curve into ascending segments defined by intervals that the engagement value remains relatively constant or increases;

computing the area above the threshold value for each such ascending segment;

summing the areas; and

dividing the sum by the duration of the content.