Methods and apparatus for co-viewing adjustment
Methods and apparatus disclosed herein can be used to perform co-viewer adjustment. An example apparatus or viewership adjustment includes at least one memory, machine readable instructions, and processor circuitry to execute the machine readable instructions to determine compliant and non-compliant household panel meter data based on household metrics for past household viewing behavior, adjust undercounted viewership data based on an active media session interval associated with the household metrics, adjust overcounted viewership data based on a viewership model, the viewership model trained using the compliant household panel meter data, and output adjusted viewership data based on the adjusted undercounted viewership data and adjusted overcounted viewership data.
1 . A method comprising:
obtaining, from a meter, a first set of media data, wherein the first set of media data is indicative of one or more users in a household viewing one or more media sessions on a media device;
obtaining a second set of media data, wherein the second set of media data is indicative of the same one or more media sessions;
determining at least a portion of the first set of media data is non-compliant data using the second set of media data, wherein the non-compliant data represents undercounted viewership data;
modifying, using a viewership model trained using compliant data, the non-compliant data to generate corrected viewership data;
and
outputting the corrected viewership data.
2 . The method of claim 1 , wherein the determining the at least the portion of the first set of media data is the non-compliant data comprises comparing the first set of media data to the second set of media data, and wherein the second set of media data is obtained from a portable meter of a user of the one or more users in the household viewing the one or more media sessions on the media device.
3 . The method of claim 1 , wherein the second set of media data comprises one or more features of the one or more media sessions, and wherein the one or more features are at least one of: a number of audience changes, a household size of the household, session length of a media session of the one or more media sessions, or a time of day associated with a media session of the one or more media sessions.
4 . The method of claim 1 , further comprising:
identifying the household as a non-compliant household, and
wherein the determining the at least the portion of the first set of media data is the non-compliant data occurs after the identifying.
5 . The method of claim 4 , wherein the identifying the household as the non-compliant household is based on a measure of compliance for the household being below a threshold of compliance, and wherein the measure of compliance is based on the one or more users in the household indicating who is viewing the one or more media sessions.
6 . The method of claim 1 , wherein the modifying comprises:
generating a probability of co-viewership associated with the non-compliant data.
7 . The method of claim 6 , wherein the modifyng further comprises:
adjusting the undercounted viewership data based on the probability of co-viewership to generate the corrected viewership data.
8 . A computing system comprising:
a processor; and
a non-transitory computer-readable storage medium, having stored thereon program instructions that, upon execution by the processor, cause performance of a set of operations comprising:
obtaining, from a meter, a first set of media data, wherein the first set of media data is indicative of one or more users in a household viewing one or more media sessions on a media device;
obtaining a second set of media data, wherein the second set of media data is indicative of the same one or more media sessions;
determining at least a portion of the first set of media data is non-compliant data using the second set of media data, wherein the non-compliant data represents undercounted viewership data;
modifying, using a viewership model trained using compliant data, the non-compliant data to generate corrected viewership data;
and
outputting the corrected viewership data.
9 . The computing system of claim 8 , wherein the determining the at least the portion of the first set of media data is the non-compliant data comprises comparing the first set of media data to the second set of media data, and wherein the second set of media data is obtained from a portable meter of a user of the one or more users in the household viewing the one or more media sessions on the media device.
10 . The computing system of claim 8 , wherein the second set of media data comprises one or more features of the one or more media sessions, and wherein the one or more features are at least one of: a number of audience changes, a household size of the household, session length of a media session of the one or more media sessions, or a time of day associated with a media session of the one or more media sessions.
11 . The computing system of claim 8 , the set of operations further comprising:
identifying the household as a non-compliant household, and
wherein the determining the at least the portion of the first set of media data is the non-compliant data occurs after the identifying.
12 . The computing system of claim 11 , wherein the identifying the household as the non-compliant household is based on a measure of compliance for the household being below a threshold of compliance, and wherein the measure of compliance is based on the one or more users in the household indicating who is viewing the one or more media sessions.
13 . The computing system of claim 8 , wherein the modifying comprises:
generating a probability of co-viewership associated with the non-compliant data.
14 . The computing system of claim 13 , wherein the modifying further comprises:
adjusting the undercounted viewership data based on the probility of co-viewership to generate the corrected viewership data.
15 . A non-transitory computer-readable storage medium, having stored thereon program instructions that, upon execution by a processor, cause performance of a set of operations comprising:
obtaining, from a meter, a first set of media data, wherein the first set of media data is indicative of one or more users in a household viewing one or more media sessions on a media device;
obtaining a second set of media data, wherein the second set of media data is indicative of the same one or more media sessions;
determining at least a portion of the first set of media data is non-compliant data using the second set of media data, wherein the non-compliant data represents undercounted viewership data;
modifying, using a viewership model trained using compliant data, the non-compliant data to generate corrected viewership data;
and
outputting the corrected viewership data.
16 . The non-transitory computer-readable storage medium of claim 15 , wherein the determining the at least the portion of the first set of media data is the non-compliant data comprises comparing the first set of media data to the second set of media data, and wherein the second set of media data is obtained from a portable meter of a user of the one or more users in the household viewing the one or more media sessions on the media device.
17 . The non-transitory computer-readable storage medium of claim 15 , wherein the second set of media data comprises one or more features of the one or more media sessions, and wherein the one or more features are at least one of: a number of audience changes, a household size of the household, session length of a media session of the one or more media sessions, or a time of day associated with a media session of the one or more media sessions.
18 . The non-transitory computer-readable storage medium of claim 15 , wherein the modifying comprises:
generating a probability of co-viewership associated with the non-compliant data; and
adjusting the undercounted viewership data based on the probability of co-viewership to generate the corrected viewership data.
19 . The non-transitory computer-readable storage medium of claim 15 , the set of operations further comprising:
identifying the household as a non-compliant household, and
wherein the determining the at least the portion of the first set of media data is the non-compliant data occurs after the identifying.
20 . The non-transitory computer-readable storage medium of claim 19 , wherein the identifying the household as the non-compliant household is based on a measure of compliance for the household being below a threshold of compliance, and wherein the measure of compliance is based on the one or more users in the household indicating who is viewing the one or more media sessions.