Generation of advertising targeting information based upon affinity information obtained from an online social network
Systems and methods for automatically generating targeting information for presentation of an offer via an online social network using affinity information collected concerning members of online social networks in accordance with embodiments of the invention are disclosed. One embodiment includes indexing member profiles within social networks for affinity to keywords using a targeting system that retrieves data concerning member profiles and activities from servers within an online social network, identifying member profiles that have affinity for at least one offer keyword using the targeting system and the index, identifying additional keywords for which the identified member profiles have affinity using the targeting system and the index, determining a set of keywords that target a desired audience based upon the identified additional keywords, and targeting presentation of advertisements for the specific offer to members of an online social network using the online social network and the targeting keywords.
1. An advertising targeting system configured to generate a set of targeting keywords that target a specific offer to a desired audience, the system comprising:
a targeting server system comprising a network interface and a database;
wherein the targeting server system is configured to:
obtain a set of offer keywords comprising the attributes of at least one specific offer within an advertising campaign
obtain a set of member profile data from at least one server that forms part of an online social network using the network interface, where a member profile in the obtained member profile data describes activities performed on the online social network associated with the member profiles;
determine member profile affinity metadata for a subset of the set of member profile data, where the member profile affinity metadata describes the affinity of a member profile with respect to a set of specific keywords;
generate a member affinity database stored using the database and containing the member profiles and the determined member profile affinity metadata; and
identify targeting keywords within the specific keywords based on the offer keywords and the member affinity database by:
clustering the member profiles within the member affinity database based on the member profile affinity metadata and the offer keywords;
selecting at least one member profile cluster based on the affinity of the member profiles within the member profile cluster to at least one of the offer keywords;
identifying at least one additional keyword within the specific keywords based on the affinity of the member profiles within the selected at least one member profile cluster to the at least one additional keyword; and
determining a set of targeting keywords based on the offer keywords and the additional keywords.
2. The advertising targeting system of claim 1 , wherein the targeting server system is further configured to provide the targeting keywords to a server that is part of the online social network using the network interface so that the online social network displays the specific offer to members of the online social network targeted using the targeting keywords.
3. The advertising targeting system of claim 1 , wherein the targeting server system is further configured to score the affinity between a member profile and the set of specific keywords within data describing an activity associated with the member profile.
4. The advertising targeting system of claim 3 , wherein the targeting server system is further configured to determine sentiment related to the set of specific keywords within data describing an activity associated with a member profile.
5. The advertising targeting system of claim 3 , wherein the targeting server system is further configured to determine intent related to the set of specific keywords within data describing an activity associated with a member profile.
6. The advertising targeting system of claim 1 , wherein the targeting server system is further configured to select the set of specific keywords by clustering the member profiles identified as having associations with an affinity to at least one offer keyword.
7. The advertising targeting system of claim 6 , wherein the targeting server system is further configured to:
assign a feature vector to each of the identified keywords; and
estimate the performance of the feature vector in targeting the specific offer to the desired audience.
8. The advertising targeting system of claim 7 , wherein the feature vector of a keyword includes at least one value indicative of a relationship between the keyword and at least one of the offer keywords.
9. The advertising targeting system of claim 7 , wherein the feature vector of a keyword includes at least one value indicative of a relationship between the keyword and at least one cluster of member profiles.
10. The advertising targeting system of claim 6 , wherein the targeting server system is further configured to estimate the performance of the feature vector in targeting the specific offer to the desired audience using a classifier.
11. The advertising targeting system of claim 6 , wherein the targeting server system is further configured to estimate performance by estimating the click-through rate of advertising targeted using the keyword.
12. The advertising targeting system of claim 1 , wherein the targeting server system is further configured to select a set of targeting keyword and demographic information combinations.
13. The advertising targeting system of claim 1 , wherein the targeting server system is further configured to select a set of targeting keywords using set completion.
14. A method of generating a set of targeting keywords for targeting a specific offer to members of an online social network, comprising:
obtaining a set of offer keywords using a targeting server system, where an offer keyword in the set of offer keywords comprises the attributes of at least one specific offer within an advertising campaign;
obtaining member profiles within one or more online social networks for affinity to a set of specific keywords using a targeting server system that retrieves data concerning member profiles and activities from servers within an online social network;
determining member profile affinity metadata for a subset of the member profiles describing the affinity for at least one specific keyword using the targeting server system; and
identifying a set of targeting keywords within the specific keywords that target a desired audience based on the offer keywords and the member profile affinity metadata using the targeting server system by:
clustering the member profiles within the member affinity database based on the member profile affinity metadata and the offer keywords using the targeting server system;
selecting at least one member profile cluster based on the affinity of the member profiles within the member profile cluster to at least one of the offer keywords using the targeting server system;
identifying at least one additional keyword within the specific keywords based on the affinity of the member profiles within the selected at least one member profile cluster to the at least one additional keyword using the targeting server system; and
determining a set of targeting keywords based on the offer keywords and the additional keywords using the targeting server system.
15. The method of claim 14 , further comprising targeting presentation of advertisements for the specific offer to members of an online social network based on the set of targeting keywords using the targeting server system.
16. The method of claim 15 , further comprising transmitting the targeted presentation of advertisements to an online social network using the targeting server system.