Lookalike expansion of source-based custom audience by an online system

1. A method comprising:

receiving a request from a third party system to present a content item to users of an online system, the content item associated with a category;

receiving messages from client devices associated with a plurality of users who have visited webpages associated with the third party system, each message including identification information associated with a user and descriptive information associated with the webpage visited by the user;

extracting tags for the webpages based on the descriptive information associated with the webpages;

classifying the webpages into one or more categories based on the extracted tags, the one or more categories including the category associated with the content item;

generating a seed group of users for the category associated with the content item by including the users who visited one or more of the webpages that are classified in the category associated with the content item into the seed group for the category;

for each candidate user of a plurality of users of the online system who are not included in the seed group for the category, performing a cluster expansion process by:

applying a cluster model to one or more characteristics of the candidate user maintained by the online system, the cluster model outputting a cluster score for the candidate user, the cluster score indicating a similarity of the candidate user to the users of the seed group,

determining whether to include the candidate user in a cluster group for the category associated with the content item based on the candidate user's cluster score, and

including the candidate user in the cluster group based on the determination; and

using membership in the cluster group as an eligibility criteria in a content selection process for the content item for presentation to one or more of the users of the online system.

2. The method of claim 1 , wherein extracting tags for the webpages based on the descriptive information associated with the webpages comprises:

for each webpage:

identifying a product associated with the webpage based on the descriptive information associated with the webpage, and

determining a tag for the webpage based on the identified product.

3. The method of claim 1 , wherein classifying the webpages into one or more categories based on the extracted tags comprises:

obtaining a taxonomy indicating hierarchy between a plurality of tags, the hierarchy including multiple levels of tags; and

determining a category for each extracted tag based on the taxonomy.

4. The method of claim 1 , wherein determining whether to include the candidate user in the cluster group for the category associated with the content item based on the candidate user's cluster score comprises:

comparing the candidate user's cluster score with a cluster group cutoff score; and

determining to include the candidate user in the cluster group based on the candidate user's cluster score at least equal to the cluster group cutoff score.

5. The method of claim 1 , wherein the identification information associated with a user includes at least one of the following: a name associated with the user, an email address associated with the user, a physical address associated with the user, a number associated with the user, an image associated with the user, or any combination thereof.

6. The method of claim 1 , wherein the descriptive information associated with a webpage visited by the user includes at least one of the following: a domain name associated with the webpage, a uniform source locator (URL) associated with the webpage, a product or service associated with the webpage, or any combination thereof.

7. The method of claim 1 , wherein the one or more characteristics of a user include at least one of the following: hobbies or preferences, location, age, gender, educational background, work experience, historical actions of the user, connections associated with the user on the online system, or any combination thereof.

8. A non-transitory computer readable medium storing executable computer program instructions, the computer program instructions comprising instructions that when executed cause a computer processor to:

receive a request from a third party system to present a content item to users of an online system, the content item associated with a category;

receive messages from client devices associated with a plurality of users who have visited webpages associated with the third party system, each message including identification information associated with a user and descriptive information associated with the webpage visited by the user;

extract tags for the webpages based on the descriptive information associated with the webpages;

classify the webpages into one or more categories based on the extracted tags, the one or more categories including the category associated with the content item;

a seed group of users for the category associated with the content item, the seed group comprising the users who visited one or more of the webpages that are classified in the category associated with the content item;

for each candidate user of a plurality of users of the online system who are not included in the seed group for the category, perform a cluster expansion process by:

applying a cluster model to one or more characteristics of the candidate user maintained by the online system, the cluster model outputting a cluster score for the candidate user, the cluster score indicating a similarity of the candidate user to the users of the seed group,

determining whether to include the candidate user in a cluster group for the category associated with the content item based on the candidate user's cluster score, and

including the candidate user in the cluster group based on the determination; and

use membership in the cluster group as an eligibility criteria in a content selection process for the content item for presentation to one or more of the users of the online system.

9. The computer readable medium of claim 8 , wherein the computer program instructions for extracting tags for the webpages based on the descriptive information associated with the webpages comprise instructions that when executed cause the computer processor to:

for each webpage:

identify a product associated with the webpage based on the descriptive information associated with the webpage, and

determine a tag for the webpage based on the identified product.

10. The computer readable medium of claim 8 , wherein the computer program instructions for classifying the webpages into one or more categories based on the extracted tags comprise instructions that when executed cause the computer processor to:

obtain a taxonomy indicating hierarchy between a plurality of tags, the hierarchy including multiple levels of tags; and

determine a category for each extracted tag based on the taxonomy.

11. The computer readable medium of claim 8 , wherein the computer program instructions for determining whether to include the candidate user in the cluster group for the category associated with the content item based on the candidate user's cluster score further comprise instructions that when executed cause the computer processor to:

compare the candidate user's cluster score with a cluster group cutoff score; and

determine to include the candidate user in the cluster group based on the candidate user's cluster score at least equal to the cluster group cutoff score.

12. The computer readable medium of claim 8 , wherein the identification information associated with a user includes at least one of the following: a name associated with the user, an email address associated with the user, a physical address associated with the user, a number associated with the user, an image associated with the user, or any combination thereof.

13. The computer readable medium of claim 8 , wherein the descriptive information associated with a webpage visited by the user includes at least one of the following: a domain name associated with the webpage, a uniform source locator (URL) associated with the webpage, a product or service associated with the webpage, or any combination thereof.

14. The computer readable medium of claim 8 , wherein the one or more characteristics of a user include at least one of the following: hobbies or preferences, location, age, gender, educational background, work experience, historical actions of the user, connections associated with the user on the online system, or any combination thereof.

15. A computer system comprising:

a non-transitory computer-readable storage medium storing executable computer program instructions, the computer program instructions comprising instructions that when executed cause a computer processor to perform steps, comprising:

receiving a request from a third party system to present a content item to users of an online system, the content item associated with a category;

receiving messages from client devices associated with a plurality of users who have visited webpages associated with the third party system, each message including identification information associated with a user and descriptive information associated with the webpage visited by the user;

extracting tags for the webpages based on the descriptive information associated with the webpages;

classifying the webpages into one or more categories based on the extracted tags, the one or more categories including the category associated with the content item;

generating a seed group of users for the category associated with the content item, the seed group comprising the users who visited one or more of the webpages that are classified in the category associated with the content item;

for each candidate user of a plurality of users of the online system who are not included in the seed group for the category, performing a cluster expansion process by:

applying a cluster model to one or more characteristics of the candidate user maintained by the online system, the cluster model outputting a cluster score for the candidate user, the cluster score indicating a similarity of the candidate user to the users of the seed group,

determining whether to include the candidate user in a cluster group for the category associated with the content item based on the candidate user's cluster score, and

including the candidate user in the cluster group based on the determination; and

using membership in the cluster group as an eligibility criteria in a content selection process for the content item for presentation to one or more of the users of the online system.

16. The system of claim 15 , wherein extracting tags for the webpages based on the descriptive information associated with the webpages comprises:

for each webpage:

identifying a product associated with the webpage based on the descriptive information associated with the webpage, and

determining a tag for the webpage based on the identified product.

17. The system of claim 15 , wherein classifying the webpages into one or more categories based on the extracted tags comprises:

obtaining a taxonomy indicating hierarchy between a plurality of tags, the hierarchy including multiple levels of tags; and

determining a category for each extracted tag based on the taxonomy.

18. The system of claim 15 , wherein determining whether to include the candidate user in the cluster group for the category associated with the content item based on the candidate user's cluster score comprises:

comparing the candidate user's cluster score with a cluster group cutoff score; and

determining to include the candidate user in the cluster group based on the candidate user's cluster score at least equal to the cluster group cutoff score.

19. The system of claim 15 , wherein the identification information associated with a user includes at least one of the following: a name associated with the user, an email address associated with the user, a physical address associated with the user, a number associated with the user, an image associated with the user, or any combination thereof.

20. The system of claim 15 , wherein the descriptive information associated with a webpage visited by the user includes at least one of the following: a domain name associated with the webpage, a uniform source locator (URL) associated with the webpage, a product or service associated with the webpage, or any combination thereof.