Methods and apparatus for measuring engagement during media exposure
Methods, apparatus, systems, and articles of manufacture are disclosed for measuring engagement during media exposure. An example apparatus includes at least one memory, machine readable instructions, and processor circuitry to at least one of instantiate or execute the machine readable instructions to identify media presented via a media device in a media presentation environment, identify ambient audio detected in the media presentation environment, determine whether the ambient audio is distractive to presentation of the media in the media presentation environment, and adjust a media exposure report based on a determination that the ambient audio is distractive.
1. An audience measurement system comprising:
at least one processor; and
memory having stored thereon machine readable instructions that, when executed by the at least one processor, cause the audience measurement system to:
identify media presented via a media device in a media presentation environment, the presentation of the media associated with a first timestamp;
identify an instance of distractive ambient audio detected in the media presentation environment, the detection of the instance of distractive ambient audio associated with a second timestamp;
determine that the first timestamp aligns with the second timestamp;
based on the determination that the first timestamp aligns with the second timestamp, generate an attention score indicating that the instance of distractive ambient audio is distractive to presentation of the media in the media presentation environment; and
output a media exposure report based on the generated attention score.
2. The audience measurement system of claim 1 , wherein the machine readable instructions further cause, when executed by the at least one processor, the audience measurement system to employ a neural network to classify a household activity associated with the identified instance of distractive ambient audio.
3. The audience measurement system of claim 1 , wherein the machine readable instructions further cause, when executed by the at least one processor, the audience measurement system to identify the instance of distractive ambient audio by:
employing a universal library including one or more reference audio identifiers corresponding to one or more known household activities; and
comparing the instance of distractive ambient audio to the one or more reference audio identifiers.
4. The audience measurement system of claim 3 , wherein the machine readable instructions further cause, when executed by the at least one processor, the audience measurement system to determine a household activity associated with the instance of distractive ambient audio based on comparing the instance of distractive ambient audio to the one or more reference audio identifiers.
5. The audience measurement system of claim 1 , wherein the machine readable instructions further cause, when executed by the at least one processor, the audience measurement system to identify the instance of distractive ambient audio by:
employing an adaptive reference system that is trained to classify ambient audio as either distractive or non-distractive based on a presence characteristic of previous and successive ambient audio detected in the media presentation environment; and
determining that the instance of distractive ambient audio is distractive based on the presence characteristic.
6. The audience measurement system of claim 5 , wherein the machine readable instructions further cause, when executed by the at least one processor, the audience measurement system to identify the instance of distractive ambient audio by comparing the presence characteristic to a threshold.
7. The audience measurement system of claim 1 , wherein the machine readable instructions further cause, when executed by the at least one processor, the audience measurement system to decrease a hit score associated with the presentation of the media in response to generating the attention score indicating that the instance of distractive ambient audio is distractive.
8. A non-transitory machine readable storage medium comprising instructions that, when executed by a processor, cause performance of at least:
identifying media presented via a media device in a media presentation environment, the presentation of the media associated with a first timestamp;
identifying an instance of distractive ambient audio detected in the media presentation environment, the detection of the instance of distractive ambient audio associated with a second timestamp;
determining that the first timestamp aligns with the second timestamp;
based on the determination that the first timestamp aligns with the second timestamp, generate an attention score indicating that the instance of distractive ambient audio is distractive to presentation of the media in the media presentation environment; and
outputting a media exposure report based on the generated attention score.
9. The non-transitory machine readable storage medium of claim 8 , wherein the instructions further cause, when executed by the processor, performance of employing a neural network to classify a household activity associated with the identified instance of distractive ambient audio.
10. The non-transitory machine readable storage medium of claim 8 , wherein the instructions further cause, when executed by the processor, performance of identifying the instance of distractive ambient audio by:
employing a universal library including one or more reference audio identifiers corresponding to one or more known household activities; and
comparing the instance of distractive ambient audio to the one or more reference audio identifiers.
11. The non-transitory machine readable storage medium of claim 10 , wherein the instructions further cause, when executed by the processor, performance of determining a household activity associated with the instance of distractive ambient audio based on comparing the instance of distractive ambient audio to the one or more reference audio identifiers.
12. The non-transitory machine readable storage medium of claim 8 , wherein the instructions further cause, when executed by the processor, performance of identifying the instance of distractive ambient audio by:
employing an adaptive reference system that is trained to classify ambient audio as either distractive or non-distractive based on a presence characteristic of previous and successive ambient audio detected in the media presentation environment; and
determining that the instance of distractive ambient audio is distractive based on the presence characteristic.
13. The non-transitory machine readable storage medium of claim 12 , wherein the machine readable instructions further cause, when executed by the processor, performance of identifying the instance of distractive ambient audio by comparing the presence characteristic to a threshold.
14. The non-transitory machine readable storage medium of claim 8 , wherein the instructions further cause, when executed by the processor, performance of decreasing a hit score associated with the presentation of the media in response to generating the attention score indicating that the instance of distractive ambient audio is distractive.
15. A method comprising:
identifying, via one or more processors, media presented via a media device in a media presentation environment, the presentation of the media associated with a first timestamp;
identifying, via one or more processors, an instance of distractive ambient audio detected in the media presentation environment, the detection of the instance of distractive ambient audio associated with a second timestamp;
determining that the first timestamp aligns with the second timestamp;
based on the determination that the first timestamp aligns with the second timestamp, generating, via one or more processors, an attention score indicating that the instance of distractive ambient audio is distractive to presentation of the media in the media presentation environment; and
outputting a media exposure report based on the generated attention score.
16. The method of claim 15 , wherein identifying the instance of distractive ambient audio includes:
employing a universal library including one or more reference audio identifiers corresponding to one or more known household activities; and
comparing the instance of distractive ambient audio to the one or more reference audio identifiers.
17. The method of claim 16 , further including determining a household activity associated with the instance of distractive ambient audio based on comparing the instance of distractive ambient audio to the one or more reference audio identifiers.
18. The method of claim 15 , wherein identifying the instance of distractive ambient audio includes:
employing an adaptive reference system that is trained to classify ambient audio as either distractive or non-distractive based on a presence characteristic of previous and successive ambient audio detected in the media presentation environment; and
determining that the instance of distractive ambient audio is distractive based on the presence characteristic.
19. The method of claim 18 , wherein identifying the instance of distractive ambient audio further includes comparing the presence characteristic to a threshold.
20. The method of claim 15 , further including decreasing a hit score associated with the presentation of the media in response to generating the attention score indicating that the instance of distractive ambient audio is distractive.