METHODS AND APPARATUS TO PREDICT TIME-SHIFTED EXPOSURE TO MEDIA
Methods, apparatus, systems and articles of manufacture are disclosed to predict time-shifted exposure to media. An example method includes normalizing, with a processor, audience measurement data corresponding to media exposure data and social media activity data. The example method also includes building an estimation model based on a relationship between a first subset of the normalized audience measurement data associated with a characteristic of the media asset and historical rating lift measurements associated with the media asset. The example method also includes estimating, with the processor, current ratings for the media asset based on time-period based ratings and broadcast time-periods. The example method also includes applying data related to the media asset and the estimated current ratings to the estimation model to estimate, with the processor, the ratings lift for the media asset.
1 . A method to estimate ratings lift for a media asset, the method comprising:
normalizing, with a processor, audience measurement data corresponding to media exposure data and social media activity data;
building an estimation model based on a relationship between a first subset of the normalized audience measurement data associated with a characteristic of the media asset and historical rating lift measurements associated with the media asset;
estimating, with the processor, current ratings for the media asset based on time-period based ratings and broadcast time-periods; and
applying data related to the media asset and the estimated current ratings to the estimation model to estimate, with the processor, the ratings lift for the media asset.
2 . The method as defined in claim 1 , wherein the normalizing of the audience measurement data includes:
transforming ratings-related information included in the audience measurement data to a first common scale;
transforming program attributes-related information included in the audience measurement data to a second common scale; and
transforming social media-related information included in the audience measurement data to a third common scale.
3 . The method as defined in claim 1 , wherein the normalizing of the audience measurement data includes transforming the audience measurement data from a first data type to a second data type.
4 . The method as defined in claim 1 , wherein the characteristic of the media asset corresponds to a season-episode grouping.
5 . The method as defined in claim 1 , wherein the estimation model corresponds to an equation including coefficients to be applied to the data related to the media asset and the estimated current ratings, and the building of the estimation model includes determining values of the coefficients based on the first subset of the normalized audience measurement data.
7 . The method as defined in claim 1 , wherein the determining of the estimated current ratings for the media asset includes:
determining a telecast time of the media asset based on the broadcast time-periods; and
mapping the time-period based ratings to the telecast time.
8 . An apparatus to estimate ratings lift for a media asset, the apparatus comprising:
a data translator to normalize audience measurement data corresponding to media exposure data and social media activity data;
a model builder to build an estimation model based on a relationship between a first subset of the normalized audience measurement data associated with a characteristic of the media asset and historical rating lift measurements associated with the media asset; and
a ratings estimator to:
estimate current ratings for the media asset based on time-period based ratings and broadcast time-periods; and
apply data related to the media asset and the estimated current ratings to the estimation model to estimate the rating lift for the media asset.
9 . The apparatus as defined in claim 8 , wherein the data translator includes:
a ratings handler to normalize ratings-related information included in the audience measurement data to a first common scale;
an attributes handler to normalize program attributes-related information included in the audience measurement data to a second common scale; and
a social media handler to normalize social media-related information included in the audience measurement data to a third common scale.
10 . The apparatus as defined in claim 8 , wherein the data translator transforms the audience measurement data from a first data type to a second data type.
11 . The apparatus as defined in claim 8 , wherein the characteristic of the media asset corresponds to a season-episode grouping.
12 . The apparatus as defined in claim 8 , wherein the estimation model is represented by an equation including coefficients to be applied to the data related to the media asset and the estimated current ratings.
13 . The apparatus as defined in claim 12 , wherein the model builder is to build the estimation model by determining values of the coefficients based on the first subset of the normalized audience measurement data.
14 . The apparatus as defined in claim 8 , wherein the ratings estimator is to:
determine a telecast time of the media asset based on the broadcast time-periods; and
map the time-period based ratings to the telecast time to determine the estimated current ratings for the media asset.
15 . A tangible machine-readable storage medium comprising instructions that, when executed, cause a processor to at least:
normalize audience measurement data corresponding to media exposure data and social media activity data;
build an estimation model based on a relationship between a first subset of the normalized audience measurement data associated with a characteristic of the media asset and historical rating lift measurements associated with the media asset;
estimate current ratings for the media asset based on time-period based ratings and broadcast time-periods; and
apply data related to the media asset and the estimated current ratings to the estimation model to estimate ratings lift for the media asset.
16 . The tangible machine-readable storage medium as defined in claim 15 , wherein the instructions further cause the processor to normalize the audience measurement data by:
transforming ratings-related information included in the audience measurement data to a first common scale;
transforming program attributes-related information included in the audience measurement data to a second common scale; and
transforming social media-related information included in the audience measurement data to a third common scale.
17 . The tangible machine-readable storage medium as defined in claim 15 , wherein the instructions further cause the processor to normalize the audience measurement data by transforming the audience measurement data from a first data type to a second data type.
18 . The tangible machine-readable storage medium as defined in claim 15 , wherein the characteristic of the media asset corresponds to a season-episode grouping.
19 . The tangible machine-readable storage medium as defined in claim 15 , wherein the estimation model corresponds to an equation including coefficients to be applied to the data related to the media asset and the estimated current ratings, and wherein the instructions further cause the processor to build the estimation model by determining values of the coefficients based on the first subset of the normalized audience measurement data.
20 . The tangible machine-readable storage medium as defined in claim 15 , wherein the instructions further cause the processor to determine the estimated current ratings for the media asset by:
determining a telecast time of the media asset based on the broadcast time-periods; and
mapping the time-period based ratings to the telecast time.