Systems and methods for assessing viewer engagement
A system for quantifying viewer engagement with a video playing on a display includes at least one camera to acquire image data of a viewing area in front of the display. A microphone acquires audio data emitted by a speaker coupled to the display. The system also includes a memory to store processor-executable instructions and a processor. Upon execution of the processor-executable instructions, the processor receives the image data and the audio data and determines an identity of the video displayed on the display based on the audio data. The processor also estimates a first number of people present in the viewing area and a second number of people engaged with the video. The processor further quantifies the viewer engagement of the video based on the first number of people and the second number of people.
1. A method of quantifying viewer engagement with content shown on a display, the method comprising:
acquiring image date, viewer data, and audio data while people are viewing content on a plurality of devices in non-public viewing areas in which participant viewers consent to participate in data collection, and wherein content comprises multiple videos;
quantifying viewer engagement with the content based at least in part on the viewer data;
quantifying the viewer engagement of the content based at least in part on a number of people present in each of the non-public viewing areas while a video of the multiple videos is being shown and a number of people engaged with the video in each non-public viewing area, wherein quantifying the viewer engagement comprises estimating an attention rate for the content, the attention rate for the content representing a ratio of the total number of people attentive to the plurality of devices over the total number of people in the non-public viewing areas, and for each unique video in a plurality of videos, determining an attention index based on the attention rates of the videos in the plurality of videos; and
quantifying the viewer engagement of the content based at least in part on a number of people present in each of the non-public viewing areas while a video of the multiple videos is being shown and a number of people engaged with the video in each non-public viewing area, wherein quantifying the viewer engagement comprises estimating an attention rate for the content, the attention rate for the content representing a ratio of the total number of people attentive to the plurality of devices over the total number of people in the non-public viewing areas, and for each unique video in a plurality of videos, determining an attention index based on the attention rates of the videos in the plurality of videos, and wherein no changes are made to content presented to viewers based on viewer engagement quantification, and no inducement to make purchases is presented to viewers.
2. The method of claim 1 , wherein the non-public viewing areas comprise households, the method further comprising:
estimating a viewer count and a positive duration ratio based on the image data and on demographic information about each household, the viewer count representing the number of people engaged with each unique video and the positive duration ratio representing a ratio of total time spent by people in the households watching the unique video to a duration of the unique video.
3. The method of claim 2 , wherein quantifying viewer engagement comprises one or more of:
facial tracking;
eyeball tracking;
facial recognition; and
sentiment analysis.
4. The method of claim 3 , wherein performing sentiment analysis comprises facial landmark detection and emotion analysis.
5. The method of claim 3 , wherein performing sentiment analysis comprises acquiring skeletal frame data.
6. A system for quantifying viewer engagement with content playing on a display, the system comprising:
at least one camera, disposed to image a viewing area in front of the display, to acquire image data of the viewing area, wherein the viewing area is a viewer's residence wherein the viewer's residence comprises one household of a plurality of households;
a microphone, disposed in proximity to the display, to acquire audio data representing a soundtrack of the video emitted by a speaker coupled to the display;
a memory, operably coupled to the at least one camera and the microphone, to store processor-executable instructions, the memory comprising a buffer to store the image data and the audio data; and
at least one processor, operably coupled to the at least one camera, the microphone, and the memory, wherein upon execution of the processor-executable instructions, the at least one processor performs a method comprising:
acquiring, with at least one camera, image data of a viewing area in front of the display while the video is being shown on the display;
estimating, with at least one processor and based at least in part on the image data, viewer data comprising a number of people present in the viewing area while the video is being shown on the display and a number of people engaged with the video in the viewing area;
acquiring, with a microphone, audio data representing a soundtrack of the video emitted by a speaker coupled to the display;
quantifying the viewer engagement with the video based at least in part on the viewer data wherein quantifying the viewer engagement of the video based at least in part on a number of people present in the viewing area while the video is being shown on the display and a number of people engaged with the video in the viewing area at each household in a plurality of households, wherein quantifying the viewer engagement comprises estimating an attention rate for the video, the attention rate representing a ratio of the total number of people attentive to a display over a total number of people in the households and determining an attention index based on the attention rate; and
estimating a viewer count and a positive duration ratio based on the image data and on demographic information about each household in the plurality of households, the viewer count representing the number of people engaged with each unique video and the positive duration ratio representing a ratio of total time spent by people in the plurality of households watching the unique video to a duration of the unique video, and wherein no changes are made to content presented to viewers based on viewer engagement quantification, and no inducement to make purchases is presented to viewers.
7. The system of claim 6 , wherein the method further comprises estimating a viewer count and a positive duration ratio based on the image data and on demographic information about each household in the plurality of households, the viewer count representing the number of people engaged with each unique video and the positive duration ratio representing a ratio of total time spent by people in the plurality of households watching the unique video to a duration of the unique video.
8. The system of claim 7 , wherein the method further comprises:
quantifying viewer engagement, comprising performing with the at least one processor one or more of:
facial tracking;
eyeball tracking;
facial recognition; and
sentiment analysis.
9. The system of claim 8 , wherein performing sentiment analysis comprises facial landmark detection and emotion analysis.
10. The system of claim 8 , wherein performing sentiment analysis comprises acquiring skeletal frame data.
11. The system of claim 10 , wherein the method further comprises quantifying the viewer engagement of the video based at least in part on a number of people present in the viewing area while the video is being shown on the display and a number of people engaged with the video in the viewing area at each house household in a plurality of households.
12. The system of claim 6 , wherein quantifying the viewer engagement comprises:
estimating an attention rate for the video, the attention rate representing a ratio of number of people present in the viewing area while the video is being shown on the display and a number of people engaged with the video in the viewing area; and
for each unique video in a plurality of videos, determining an attention index based on the attention rates of the videos in the plurality of videos.