Systems and methods for targeted advertising
Methods of generating recommendations may include obtaining social network data from one or more network resources. Word relationships may be created between selected words in the social network data to produce relationship data. Advertisement or other asset recommendations may be generated for a target user by analyzing browse information of the target user to identify one or more words. Other words in the relationship data may be identified that are related to the words in the target user's browse information. One or more advertisements may be identified having at least one keyword that corresponds to the other words. At least a portion of these advertisements may be selected from a data repository to provide to the target user.
1. A method comprising:
obtaining, at a computing system, word data from data related to social networking activity of one or more users, the word data indicating words in content associated with the social networking activity, the social networking activity including one or more posts on one or more social networking sites;
generating, at the computing system, relationship data indicating one or more word relationships between multiple words indicated by the word data, each word relationship indicating an association between two or more of the multiple words and based on a degree of the association, wherein the degree of the association corresponds to a ranking based on a recency of the content, wherein a first ranking of a first degree of association is greater than a second ranking of a second degree of association based on the multiple words related to the first degree of association having a more recent content relationship than the multiple words related to the second degree of association;
analyzing, at the computing system, browse information of a target user device to identify one or more first words in the browse information;
identifying, at the computing system and based on the relationship data, second words that are related to the first words in the browse information;
identifying, at the computing system, one or more content items having at least one associated keyword that corresponds to the second words; and
providing at least a portion of the one or more content items retrieved from a data repository to the target user device.
2. The method of claim 1 , wherein the computer system comprises a server supporting multiple users and not dedicated to one individual user, and wherein the recency of the content is based on a date the content is published to the one or more social networking sites.
3. The method of claim 1 , further comprising retrieving the word data from one or more social network resources, wherein providing the at least a portion of the one or more content items to the target user device comprises providing the at least a portion of the one or more content items to a third party server that hosts a webpage.
4. The method of claim 1 , further comprising weighting the one or more first words based at least in part on a frequency of which the one or more first words appear in the browse information.
5. The method of claim 1 , further comprising inferring one or more category relationships from the one or more word relationships and inferring one or more asset relationships from the one or more category relationships.
6. The method of claim 5 , further comprising creating additional asset relationships by relating assets based at least in part on one or more browse behavior relationships of the one or more users.
7. The method of claim 1 , wherein further comprising:
detecting a proximity of first and second words of the multiple words in the content;
determining a particular degree for the first and second words based on a particular recency of a portion of the content that contains the first and second words; and
creating the one or more word relationships based on the proximity and based on the particular degree.
8. The method of claim 1 , wherein the degree of the association between the two or more of the multiple words is further based on an authority associated with the content.
9. The method of claim 8 , wherein the authority associated with the content is based on an authority of a user that posted the content or an authority of the social networking site on which the content is posted.
10. The method of claim 1 , wherein the content is selected based on a level of social media activity of the one or more users.
11. The method of claim 1 , wherein the degree of the association between the two or more of the multiple words is further based on an amount of social momentum associated with the two or more of the multiple words.
12. The method of claim 11 , wherein the social momentum corresponds to an amount of other social networking activity associated with the content and a recency of the other social networking activity.
13. The method of claim 1 , further comprising extracting, at the computing system, signal words from the word data, the signal words including nouns and verbs, wherein the relationships between the multiple words are indicated by the signal words.
14. A computing system comprising:
a processor; and
a memory coupled to the processor, the memory storing instructions that, when executed by the processor, cause the processor to perform operations comprising:
obtaining word data from data related to social networking activity of one or more users, the word data comprising words in content associated with the social networking activity, wherein the social networking activity includes one or more posts on one or more social networking sites;
generating relationship data indicating one or more word relationships between multiple words indicated by the word data, each word relationship indicating an association between two or more of the multiple words and based on a degree of the association, wherein the degree of the association corresponds to a ranking based on a recency of the content, wherein a first ranking of a first degree of association is greater than a second ranking of a second degree of association based on the multiple words related to the first degree of association having a more recent content relationship than the multiple words related to the second degree of association;
analyzing browse information of a target user device to identify one or more first words in the browse information;
identifying, at the computing system and based on the relationship data, second words that are related to the first words in the browse information;
identifying, at the computing system, one or more content items having at least one associated keyword that corresponds to the second words; and
initiating transmission of at least a portion of the one or more content items retrieved from a data repository to the target user device.
15. The computing system of claim 14 , wherein the data repository comprises a database configured to store a plurality of content items.
16. The computing system of claim 14 , wherein the operations further comprise retrieving the data related to social networking activity from one or more social network resources.
17. The computing system of claim 14 , wherein the operations further comprise inferring one or more category relationships from the one or more word relationships and inferring one or more asset relationships from the one or more category relationships.
18. The computing system of claim 17 , wherein the operations further comprise:
creating additional asset relationships by relating assets based at least in part on one or more browse behavior relationships of the one or more users; and
inferring additional word relationships from the additional asset relationships.
19. The computing system of claim 14 , wherein creating the one or more word relationships further comprises detecting a proximity of the multiple words in the content.
20. The computing system of claim 14 , further comprising a server that includes the processor and the memory, wherein the operations include detecting, at the server, signal words in the content using one or more natural language processing techniques.
21. The computing system of claim 20 , wherein detecting the signal words comprises generating graphs of the words indicated by the word data, the graphs comprising overlapping categories or related words of the words indicated by the word data.
22. A non-transitory, computer readable medium storing instructions that, when executed by a processor, cause the processor to perform operations comprising:
obtaining, at a computing system, word data from data related to social networking activity of one or more users, the word data indicating words in content associated with the social networking activity, wherein the social networking activity includes one or more posts on one or more social networking sites;
generating, at the computing system, relationship data indicating one or more word relationships between multiple words indicated by the word data, each word relationship indicating an association between two or more of the multiple words and based on a degree of the association, wherein the degree of the association corresponds to a ranking based on a recency of the content, wherein a first ranking of a first degree of association is greater than a second ranking of a second degree of association based on the multiple words related to the first degree of association having a more recent content relationship than the multiple words related to the second degree of association;
analyzing, at the computing system, browse information of a target user device to identify one or more first words in the browse information;
identifying, at the computing system and based on the relationship data, second words that are related to the first words in the browse information;
identifying, at the computing system, one or more content items having at least one associated keyword that corresponds to the second words; and
providing at least a portion of the one or more content items retrieved from a data repository to the target user device.
23. The non-transitory, computer readable medium of claim 22 , wherein providing the at least a portion of the one or more content items to the target user device comprises providing the at least a portion of the one or more content items to a third party server that hosts a webpage.
24. The non-transitory, computer readable medium of claim 22 , wherein the operations further comprise retrieving the data related to social networking activity from one or more social network resources.
25. The non-transitory, computer readable medium of claim 22 , wherein the operations further comprise weighting the one or more first words based at least in part on a frequency of which the one or more first words appear in the browse information.
26. The non-transitory, computer readable medium of claim 22 , wherein the operations further comprise inferring one or more category relationships from the one or more word relationships and inferring one or more asset relationships from the one or more category relationships.
27. The non-transitory, computer readable medium of claim 26 , wherein the operations further comprise:
creating additional asset relationships by relating assets based at least in part on one or more browse behavior relationships of the one or more users; and
inferring additional word relationships from the additional asset relationships.
28. A method comprising:
obtaining first data indicating words in content associated with social networking activity that includes a user post on a social networking site;
generating second data indicating an association between first words of the indicated words and indicating a degree of the association, the degree of the association corresponds to a ranking based on a recency of the content, wherein a first ranking of a first degree of association is greater than a second ranking of a second degree of association based on the multiple words related to the first degree of association having a more recent content relationship than the multiple words related to the second degree of association;
identifying, at a computing system, a word in browse information of a target user device, a second word determined based on the second data to be related to the word, and a content item having an associated keyword that corresponds to the second word; and
providing a portion of the content item retrieved from a data repository to the target user device.
29. The method of claim 28 , wherein:
the association is detected or created at the computing system,
the first words are selected from a plurality of the indicated words in the content,
the second data indicates a word relationship between the first words, and
the word relationship indicates the association.