Identification of user segments based on video viewership activity and analysis
The techniques disclosed herein facilitate online audience targeting based on brand and product interest/enthusiasm as determined by a measurement metric that is a function of one of more (and preferably all) of the following: recency data, frequency data, intensity data, consumption data, site data, meta data related to given videos, data, and other demographic data.
1. Apparatus, comprising:
a processor;
computer memory holding computer program instructions that are executed by the processor, comprising:
program code to receive video viewing data;
program code to use the received video viewing data to determine an enthusiasm metric for one of: a particular brand, a product, an activity, and an interest, the enthusiasm metric being based on recency data, frequency data, and engagement data, the recency data being a measure of how active a user has been in video viewing behavior over one or more given recent time periods, the frequency data being a measure of a number of video clips viewed by a user with a given category, and the engagement data being a measure of how long a user spent viewing video clips within a given category or what actions the user took while viewing video clips within a session, the enthusiasm metric being further based on an identification of what video sites have audiences that have a degree of content affinity as determined from at least one cross-video site data comparison; and
program code to use the enthusiasm metric to obtain, from a set of audience profiles, a particular audience profile representing an enthusiast for the particular brand, product, activity or interest, the set of audience profiles representing different enthusiasm levels;
program code to provide the obtained audience profile for ad targeting.
2. The apparatus as described in claim 1 wherein the enthusiasm metric is also a function of data concerning location of a target audience for one or more video clips.
3. The apparatus as described in claim 1 , wherein the video clips include user-generated video content.
4. The apparatus as described in claim 1 wherein the at least one cross-video site data comparison is one of: a probability of viewing particular content on a first site determined by dividing a number of views of the particular content on the first site by a total number of views of the particular content across one or more other sites that are distinct from the first site, and a probability of viewing the particular content on the first site, given that the particular content was also viewed on a second site distinct from the first site.
5. Apparatus, comprising:
a processor;
computer memory holding computer program instructions that are executed by the processor, comprising:
program code to receive video viewing data; and
program code to use the received video viewing data to generate an audience overlap metric, the audience overlap metric being one of: (i) with respect to a given video site, an identification of what audiences from other given video sites also come to the given video site to watch video clips; (ii) an identification of one or more pairs of video sites at which video clips are watched and that have generated a given conversion rate; and (iii) an identification of what video sites have audiences that have a degree of content affinity as determined from at least one cross-video site data comparison;
program code to use the audience overlap metric to generate an enthusiasm metric for one of: a particular brand, a product, an activity, and an interest;
program code to use the enthusiasm metric to obtain, from a set of audience profiles, a particular audience profile representing an enthusiast for the particular brand, product, activity or interest, the set of audience profiles representing different enthusiasm levels; and
program code to provide the obtained audience profile for ad targeting.
6. The apparatus as described in claim 5 wherein the audience overlap metric also includes an identification of one or more usage intensity segments.
7. The apparatus as described in claim 5 wherein the at least one cross-video site data comparison is one of: a probability of viewing particular content on a first site determined by dividing a number of views of the particular content on the first site by a total number of views of the particular content across one or more other sites that are distinct from the first site, and a probability of viewing the particular content on the first site, given that the particular content was also viewed on a second site distinct from the first site.