Methods and apparatus to determine audience engagement
Methods, apparatus, systems, and articles of manufacture are disclosed. An example system includes: interface circuitry; programmable circuitry; and instructions to program the programmable circuitry to: obtain audio of a media presentation; obtain ambient noise in an area associated with the media presentation; determine an intensity of a difference between the audio and the ambient noise; and determine an engagement level of an audience of the media presentation based on a duration the intensity satisfies a threshold value.
1 . A system comprising:
a processor; and
a memory storing instructions that, when executed by the processor, cause the system to perform operations comprising:
obtaining an audio of a media presentation;
obtaining ambient noise in an area associated with the media presentation; and
determining an engagement level of an audience of the media presentation based on an intensity of a difference between the audio and the ambient noise, wherein the engagement level of the audience is inversely proportional to the intensity of the difference between the audio and the ambient noise e between the audio and the ambient noise is determined as a continuous value over the duration of the media presentation.
2 . The system of claim 1 , wherein determining the engagement level of the audience of the media presentation based on the intensity of the difference between the audio and the ambient noise comprises:
determining the engagement level based on a duration of the intensity of the difference between the audio and the ambient noise.
3 . The system of claim 1 , wherein the operations further comprise:
transmitting the engagement level of the audience of the media presentation to a remote server.
4 . The system of claim 1 , wherein the media presentation is a television program displayed on a television, the audio is a speaker audio of the television program played through a speaker, and wherein the operations further comprise:
obtaining the audio from a first microphone directed at the speaker; and
obtaining the ambient noise from a second microphone directed at the area associated with the media presentation.
5 . The system of claim 1 , wherein determining the engagement level of the audience of the media presentation comprises:
determining the engagement level of the audience of the media presentation based on an output of a neural network classifier.
6 . The system of claim 1 , wherein the operations further comprise:
determining if an audience member is present based on activity of a meter device.
7 . The system of claim 1 , wherein the engagement level of the audience of the media presentation is based further on an audio volume change, or a channel change.
8 . The system of claim 1 , wherein the audio of the media presentation is a first audio, the ambient noise is a first ambient noise, and wherein the operations further comprise:
obtaining a second audio of the media presentation;
obtaining a second ambient noise in the area associated with the media presentation; and
adjusting the engagement level of the audience of the media presentation based on an intensity of a difference between the second audio and the second ambient noise.
9 . The system of claim 1 , wherein the operations further comprise:
obtaining media identifying information for the media presentation;
obtaining one or more audience member identifiers for the audience of the media presentation; and
associating the media identifying information and the one or more audience member identifiers with the engagement level of the audience of the media presentation.
10 . The system of claim 1 , wherein determining the engagement level of the audience of the media presentation comprises:
determining the engagement level based on a type of the media presentation.
11 . The system of claim 10 , wherein the type of the media presentation is a genre of the media presentation.
12 . A method comprising:
obtaining an audio of a media presentation;
obtaining ambient noise in an area associated with the media presentation; and
determining an engagement level of an audience of the media presentation based on an intensity of a difference between the audio and the ambient noise, wherein the engagement level of the audience is inversely proportional to the intensity of the difference between the audio and the ambient noise and wherein the intensity of the difference between the audio and the ambient noise is determined as a continuous value over a duration of the media presentation.
13 . The method of claim 12 , wherein determining the engagement level of the audience of the media presentation based on the intensity of the difference between the audio and the ambient noise comprises:
determining the engagement level based on a duration of the intensity of the difference between the audio and the ambient noise.
14 . The method of claim 12 , further comprising:
transmitting the engagement level of the audience of the media presentation to a remote server.
15 . The method of claim 12 , wherein the media presentation is a television program displayed on a television, the audio is a speaker audio of the television program played through a speaker, and wherein the method further comprises:
obtaining the audio from a first microphone directed at the speaker; and
obtaining the ambient noise from a second microphone directed at the area associated with the media presentation.
16 . The method of claim 12 , wherein determining the engagement level of the audience of the media presentation comprises:
determining the engagement level of the audience of the media presentation based on an output of a neural network classifier.
17 . The method of claim 12 , further comprising:
determining if an audience member is present based on activity of a meter device.
18 . The method of claim 12 , wherein the engagement level of the audience of the media presentation is based further on an audio volume change, or a channel change.
19 . The method of claim 12 , wherein the audio of the media presentation is a first audio, the ambient noise is a first ambient noise, and wherein the method further comprises:
obtaining a second audio of the media presentation;
obtaining a second ambient noise in the area associated with the media presentation; and
adjusting the engagement level of the audience of the media presentation based on an intensity of a difference between the second audio and the second ambient noise.
20 . A non-transitory computer readable storage medium having stored thereon program instructions that, upon execution by a processor, cause performance of operations comprising:
obtaining an audio of a media presentation;
obtaining ambient noise in an area associated with the media presentation; and
determining an engagement level of an audience of the media presentation based on an intensity of a difference between the audio and the ambient noise, wherein the engagement level of the audience is inversely proportional to the intensity of the difference between the audio and the ambient noise, and wherein the intensity of the difference between the audio and the ambient noise is determined as a continuous value over a duration of the media presentation.