Using status of sign-on to online services for content item recommendations
An SSO provider—i.e., a provider of user accounts that a number of other online services accept as a sign-on technique—identifies the online services to which its users sign on, as well as the digital content items that those users access. The SSO provider uses this information to associate particular content items with particular online services, or combinations of online services. The SSO provider can then use the associations to make recommendations of content items to users based on the services to which the users have signed on.
1. A computer-implemented method comprising:
identifying, using a hardware processor, a plurality of online services to which users sign on using a social sign-on account;
identifying, using the hardware processor, for each user of a plurality of the users, a plurality of content items that the user accesses;
grouping, using the hardware processor, the users into a plurality of groups according to the online services to which the users sign on using the social sign-on account;
associating, using the hardware processor, with each group of a plurality of the groups, a set of the identified content items that were accessed by the users within the group by (i) receiving a request for a first content item, the request originating from a web page of a first online service of the plurality of online services, (ii) determining, based on a referrer specified in the request, that the request originates from the first online service; and (iii) associating the first content item with groups of the plurality of groups that include the first online service;
identifying, using the hardware processor, for a first user, a first one of the groups into which the first user was grouped;
determining, using the hardware processor, from the first group, a first portion of the set of the identified content items that have not been previously accessed by the first user and a second portion of the set of the identified content items that have been previously accessed by the first user;
generating, using the hardware processor, a user interface associated with the first user, wherein the user interface presents the first portion of the set of the identified content items that have not been previously accessed by the first user and suppresses presentation of the second portion of the set of the identified content items that have been previously accessed by the first user based on the determination; and
causing, using the hardware processor, the user interface to be presented on a computing device associated with the first user.
2. The computer-implemented method of claim 1 , wherein identifying the first one of the groups comprises identifying, for each of the online services, whether the first user has signed on to the online service.
3. The computer-implemented method of claim 1 , further comprising:
identifying, from the content items, a first set of content items accessed by the users of a first group of the plurality of groups; and
selecting, as the associated content items for the first group, ones of the identified first set of content items that are popular with the users of the first group.
4. The computer-implemented method of claim 1 , further comprising:
training a classifier for a first group of the groups using features of the videos associated with the first group;
ranking a plurality of content items based on scores obtained by applying the trained classifier to the plurality of content items;
selecting a plurality of highest ranking content items from the ranked content items; and
selecting, as the associated content items for the first group, the selected plurality of highest-ranking content items.
5. The computer-implemented method of claim 1 , wherein each of the groups corresponds to a distinct set of the online services, at least one of the distinct sets corresponding to a plurality of the online services.
6. The computer-implemented method of claim 1 , wherein the content items comprise digital videos.
7. A non-transitory computer-readable storage medium comprising computer program instructions executable by a processor, the instructions comprising:
instructions for identifying a plurality of online services to which users sign on using a social sign-on account;
instructions for identifying, for each user of a plurality of the users, a plurality of content items that the user accesses;
instructions for grouping the users into a plurality of groups according to the online services to which the users sign on using the social sign-on account;
instructions for associating, with each group of a plurality of the groups, a set of the identified content items that were accessed by the users within the group by (i) receiving a request for a first content item, the request originating from a web page of a first online service of the plurality of online services, (ii) determining, based on a referrer specified in the request, that the request originates from the first online service; and (iii) associating the first content item with groups of the plurality of groups that include the first online service;
instructions for identifying, for a first user, a first one of the groups into which the first user was grouped;
instructions for determining, from the first group, a first portion of the set of the identified content items that have not been previously accessed by the first user and a second portion of the set of the identified content items that have been previously accessed by the first user;
instructions for generating a user interface associated with the first user, wherein the user interface presents the first portion of the set of the identified content items that have not been previously accessed by the first user and suppresses presentation of the second portion of the set of the identified content items that have been previously accessed by the first user based on the determination; and
instructions for causing the user interface to be presented on a computing device associated with the first user.
8. The non-transitory computer-readable storage medium of claim 7 , wherein identifying the first one of the groups comprises identifying, for each of the online services, whether the first user has signed on to the online service.
9. The non-transitory computer-readable storage medium of claim 7 , the instructions further comprising:
instructions for identifying, from the content items, a first set of content items accessed by the users of a first group of the plurality of groups; and
instructions for selecting, as the associated content items for the first group, ones of the identified first set of content items that are popular with the users of the first group.
10. The non-transitory computer-readable storage medium of claim 7 , the instructions further comprising:
training a classifier for a first group of the groups using features of the videos associated with the first group;
ranking a plurality of content items based on scores obtained by applying the trained classifier to the plurality of content items;
selecting a plurality of highest ranking content items from the ranked content items; and
selecting, as the associated content items for the first group, the selected plurality of highest-ranking content items.
11. The non-transitory computer-readable storage medium of claim 7 , wherein each of the groups corresponds to a distinct set of the online services, at least one of the distinct sets corresponding to a plurality of the online services.
12. The non-transitory computer-readable storage medium of claim 7 , wherein the content items comprise digital videos.
13. A computer system comprising:
a processor; and
computer program instructions executable by the processor, the instructions comprising:
instructions for identifying a plurality of online services to which users sign on using a social sign-on account;
instructions for identifying a plurality of content items that the users access;
instructions for grouping the users into a plurality of groups according to the online services to which the users sign on using the social sign-on account; and
instructions for associating, with each of a plurality of the groups, a set of the identified content items by (i) receiving a request for a first content item, the request originating from a web page of a first online service of the plurality of online services, (ii) determining, based on a referrer specified in the request, that the request originates from the first online service; and (iii) associating the first content item with groups of the plurality of groups that include the first online service;
instructions for identifying, for a first user, a first one of the groups into which the first user was grouped;
instructions for determining, from the first group, a first portion of the set of the identified content items that have not been previously accessed by the first user and a second portion of the set of the identified content items that have been previously accessed by the first user;
instructions for generating a user interface associated with the first user, wherein the user interface presents the first portion of the set of the identified content items that have not been previously accessed by the first user and suppresses presentation of the second portion of the set of the identified content items that have been previously accessed by the first user based on the determination; and
instructions for causing the user interface to be presented on a computing device associated with the first user.
14. The computer system of claim 13 , the instructions further comprising:
instructions for identifying, for a first user, a first one of the groups into which the first user was grouped; and
instructions for recommending, to the first user, ones of the content items that are associated with the first group and that the user has not already viewed.
15. The computer system of claim 13 , wherein identifying the first one of the groups comprises identifying, for each of the online services, whether the first user has signed on to the online service.
16. The computer system of claim 13 , the instructions further comprising:
instructions for identifying, from the content items, a first set of content items accessed by the users of a first group of the plurality of groups; and
instructions for selecting, as the associated content items for the first group, ones of the identified first set of content items that are popular with the users of the first group.
17. The computer system of claim 13 , the instructions further comprising:
instructions for training a classifier for a first group of the groups using features of the videos associated with the first group;
instructions for ranking a plurality of content items based on scores obtained by applying the trained classifier to the plurality of content items;
instructions for selecting a plurality of highest ranking content items from the ranked content items; and
instructions for selecting, as the associated content items for the first group, the selected plurality of highest-ranking content items.
18. The computer system of claim 13 , wherein each of the groups corresponds to a distinct set of the online services, at least one of the distinct sets corresponding to a plurality of the online services.