Method and system for predicting audience viewing behavior
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.
1. An apparatus comprising:
a biometric sensor to measure a biometric response of an audience member while exposed to media during a time period, the time period divided into time intervals; and
a processor to:
determine engagement scores for respective ones of the time intervals based on the biometric response;
generate an engagement curve based on the engagement scores and the time period;
identify a segment of the engagement curve having ascending engagement;
calculate an area above a threshold engagement score and below the engagement curve for the segment by:
determining a first engagement value at a start of the segment,
determining a second engagement value at an end of the segment,
calculating a first difference between the first engagement value and the second engagement value,
determining a first time value at the start of the segment,
determining a second time value at the end of the segment,
calculating a second difference between the first time value and the second time value, and
calculating the area as half of the product of the first difference and the second difference;
determine a positive buildup value for the media based on a ratio of the area to the time period; and
predict viewership based on the positive buildup value.
2. The apparatus of claim 1 , wherein the segment is a first segment, and the processor is to identify a second segment of the engagement curve having descending engagement.
3. The apparatus of claim 2 , wherein the processor is to:
perform a comparison of a decrease in engagement during the second segment with an increase in engagement during the first segment; and
determine whether the decrease in engagement is greater than a threshold percentage of the increase in engagement based on the comparison.
4. The apparatus of claim 3 , wherein the processor is to identify the second segment as having descending engagement if the decrease in engagement is greater than the threshold percentage of the increase in engagement.
5. The apparatus of claim 1 , wherein the processor is to rank the media based on a comparison of the positive buildup value to another positive buildup value of another media.
6. The apparatus of claim 1 , wherein the processor is to determine a likelihood that the audience member will watch the media again based on the positive buildup value.
7. The apparatus of claim 1 , wherein the processor is to determine a percentile rank for the positive buildup value based on a database of positive buildup values.
8. The apparatus of claim 1 , wherein the processor is to predict the viewership based on the positive buildup value by determining whether a viewer will watch the entirety of the media when the media is live.
9. The apparatus of claim 1 , wherein the processor is to:
determine intensity scores for respective ones of the time intervals based on the biometric response;
determine synchrony scores for respective ones of the time intervals based on the biometric response and another biometric response of another audience member; and
determine the engagement scores based on the intensity scores and the synchrony scores of the respective ones of the time intervals.
10. An apparatus comprising:
a biometric sensor to measure a biometric response of an audience member while exposed to media during a time period, the time period divided into time intervals; and
a processor to:
determine engagement scores for respective ones of the time intervals based on the biometric response;
generate an engagement curve based on the engagement scores and the time period;
identify a segment of the engagement curve having descending engagement;
calculate an area below a threshold engagement score and above the engagement curve for the segment by:
determining a first engagement value at a start of the segment,
determining a second engagement value at an end of the segment,
calculating a first difference between the first engagement value and the second engagement value,
determining a first time value at the start of the segment,
determining a second time value at the end of the segment,
calculating a second difference between the first time value and the second time value, and
calculating the area as half of the product of the first difference and the second difference;
determine a negative buildup value for the media based on a ratio of the area to the time period; and
predict viewership based on the negative buildup value.
11. The apparatus of claim 10 , wherein the segment is a first segment, and the processor is to identify a second segment of the engagement curve having ascending engagement.
12. The apparatus of claim 11 , wherein the processor is to:
perform a comparison of an increase in engagement during the second segment with a decrease in engagement during the first segment; and
determine whether the increase in engagement is greater than a threshold percentage of the decrease in engagement.
13. The apparatus of claim 12 , wherein the processor is to identify the second segment as having ascending engagement if the increase in engagement is greater than the threshold percentage of the decrease in engagement.
14. The apparatus of claim 10 , wherein the processor is to rank the media based on a comparison of the negative buildup value to another negative buildup value of another media.
15. The apparatus of claim 10 , wherein the processor is to predict whether a viewer will watch the entirety of the media when the media is previously recorded based on the negative buildup value.
16. The apparatus of claim 15 , wherein the processor is to predict whether the viewer will watch the entirety of the media by determining a likelihood that the viewer will fast-forward through the media.
17. The apparatus of claim 10 , wherein the processor is to determine an order to present the media in relation to other media based on the negative buildup value.
18. The apparatus of claim 10 , wherein the processor is to determine a percentile rank for the negative buildup value based on a database of negative buildup values.
19. The apparatus of claim 10 , wherein the processor is to:
determine intensity scores for respective ones of the time intervals based on the biometric response;
determine synchrony scores for respective ones of the time intervals based on the biometric response and another biometric response of another audience member; and
determine the engagement scores based on the intensity scores and the synchrony scores of the respective ones of the time intervals.