Content attribute impact invalidation method
View Patent ↗The invention concerns a method of determining the effect of content attributes on content ratings. The method may include obtaining content attributes, recording set-top box events as content is experienced without knowing individual-specific demographic information, correlating set-top box events to content attributes, and analyzing the correlations of set-top box events to content attributes over time to estimate the effect of content attributes on content ratings.
1. A method of determining the effect of content attributes on content ratings, comprising:
obtaining content attributes;
recording set-top box events as content is experienced without knowing individual-specific demographic information;
correlating set-top box events to content attributes; and
analyzing the correlations of set-top box events to content attributes over time to estimate the effect of content attributes on content ratings.
2. The method of claim 1 , wherein the content attributes include times at which various content attributes are presented to a set-top box.
3. The method of claim 1 , further comprising:
correlating set-top box events and content attributes to demographic characteristics for each set-top box; and
analyzing such correlations over time to estimate the effect of content attributes on content ratings for specific demographic groups.
4. The method of claim 3 , wherein the content attributes include times at which various content attributes are presented to a set-top box.
5. The method of claim 3 , wherein the content attributes are obtained from embedded content information.
6. The method of claim 5 , wherein the content attributes are correlated with the set-top box events at the set-top box.
7. The method of claim 3 , wherein the content attributes are obtained from external sources.
8. The method of claim 7 , wherein the content attributes are correlated with the set-top box events at a sorting system.
9. The method of claim 3 , further comprising:
applying with a computer inverse demographic matrix calculation techniques to estimate probabilities for demographic characteristic and set-top box event dataset correlations; and
ascribing the demographic characteristic probabilities to each set-top box over time based on observed set-top box events and their relationship to the estimated inverse demographic matrix probabilities.
10. The method of claim 9 , further comprising:
evaluating the ascribed demographic characteristic probabilities over time through statistical analysis;
fitting the ascribed demographic characteristics probabilities to statistically estimate a set of probable demographic identities for each set-top box; and,
fitting the set of probable demographic identities to inverse demographic matrix probability sets for a set-top box event.
11. The method of claim 10 , further comprising:
storing the set of probable demographic identities in an array over time; and
applying statistical analysis to the stored array to estimate predominant demographic identities for a given set-top box.
12. The method of claim 1 , wherein the content attributes are obtained from embedded content information.
13. The method of claim 12 , wherein the content attributes are correlated with the set-top box events at the set-top box.
14. The method of claim 1 , wherein the content attributes are obtained from external sources.
15. The method of claim 14 , wherein the content attributes are correlated with the set-top box events at a sorting system.