Ranking algorithms using unique bucketing identifiers

1. A method comprising:

identifying, by a processing device, a set of content items for inclusion in a feed displayed to a user of a social network platform in a user interface of the social network platform, wherein the set of content items are identified as candidates for inclusion in the feed based on a ranking score of each content item from the set of content items, and wherein the ranking score of each content item is generated in addition to identifying one or more bucketing tokens for a respective content item from the set of content items;

for each content item from the set of content items, identifying, by the processing device, one or more bucketing tokens, wherein each bucketing token comprises an identifier that identifies a plurality of content items as being associated with a group of users that have similar interests;

adjusting, by the processing device, a ranking score of each content item from the set of content items that has at least one bucketing token matching a bucketing token associated with the user of the social network platform; and

causing the set of content items identified for inclusion in the feed displayed to the user in the user interface of the social network platform to be modified based on adjusting ranking scores of respective content items from the set of content items.

2. The method of claim 1 wherein ranking scores of the set of content items are based on at least one of (i) watch histories of a plurality of other users followed by the user on the social network platform, or (ii) content item approvals of the plurality of other users on the social network platform.

3. The method of claim 1 , wherein the bucketing token is embedded in a metadata of each of the plurality of associated content items or is associated with a corresponding content item of the plurality of associated content items via a mapping between the bucketing token and the corresponding content item, the mapping being stored in a data store.

4. The method of claim 1 , further comprising receiving the set of content items from a content sharing platform.

5. The method of claim 4 , further comprising:

for a first content item in the set of content items:

determining whether a bucketing token is embedded in metadata of the first content item;

responsive to determining that the bucketing token is embedded in the metadata of the first content item, extracting the bucketing token from the metadata of the first content item; and

for a second content item in the set of content items:

responsive to determining that the bucketing token is not embedded in metadata of the second content item, requesting the bucketing token for the second content item from the content sharing platform.

6. The method of claim 5 , further comprising:

providing the bucketing token for the first content item to a ranking service;

providing, to the ranking service, a set of bucketing tokens associated with the user of the social network platform; and

receiving a ranking score for the first content item based on the bucketing token for the first content item and the set of bucketing tokens associated with the user of the social network.

7. The method of claim 6 , wherein the first content item has a higher scoring weight if the bucketing token for the first content item matches any of the set of bucketing tokens associated with the user of the social network platform.

8. A non-transitory machine-readable storage medium storing instructions which, when executed, cause a processing device to perform operations comprising:

identifying a set of content items for inclusion in a feed displayed to a user of a social network platform in a user interface of the social network platform, wherein the set of content items are identified as candidates for inclusion in the feed based on a ranking score of each content item from the set of content items, and wherein the ranking score of each content item is generated in addition to identifying one or more bucketing tokens for a respective content item from the set of content items;

for each content item from the set of content items, identifying one or more bucketing tokens, wherein each bucketing token comprises an identifier that identifies a plurality of content items as being associated with a group of users that have similar interests;

adjusting a ranking score of each content item from the set of content items that has at least one bucketing token matching a bucketing token associated with the user of the social network platform; and

causing the set of content items identified for inclusion in the feed displayed to the user in the user interface of the social network platform to be modified based on adjusted ranking scores of respective content items from the set of content items.

9. The non-transitory machine-readable storage medium of claim 8 wherein ranking scores of the set of content items are based on at least one of (i) watch histories of a plurality of other users followed by the user on the social network platform, or (ii) content item approvals of the plurality of other users on the social network platform.

10. The non-transitory machine-readable storage medium of claim 8 , wherein the bucketing token is embedded in a metadata of each of the plurality of associated content items or is associated with a corresponding content item of the plurality of associated content items via a mapping between the bucketing token and the corresponding content item, the mapping being stored in a data store.

11. The non-transitory machine-readable storage medium of claim 8 , wherein the operations further comprise receiving the set of content items from a content sharing platform.

12. The non-transitory machine-readable storage medium of claim 11 , wherein the operations further comprise:

for a first content item in the set of content items:

determining whether a bucketing token is embedded in metadata of the first content item;

responsive to determining that the bucketing token is embedded in the metadata of the first content item, extracting the bucketing token from the metadata of the first content item; and

for a second content item in the set of content items:

responsive to determining that the bucketing token is not embedded in metadata of the second content item, requesting the bucketing token for the second content item from the content sharing platform.

13. The non-transitory machine-readable storage medium of claim 12 , wherein the operations further comprise:

providing the bucketing token for the first content item to a ranking service;

providing, to the ranking service, a set of bucketing tokens associated with the user of the social network; and

receiving a ranking score for the first content item based on the bucketing token for the first content item and the set of bucketing tokens associated with the user of the social network platform.

14. The non-transitory machine-readable storage medium of claim 13 , wherein the first content item has a higher scoring weight if the bucketing token for the first content item matches any of the set of bucketing tokens associated with the user of the social network platform.

15. A system comprising:

a memory; and

a processing device, coupled to the memory, to:

identify a set of content items for inclusion in a feed displayed to a user of a social network platform in a user interface of the social network platform, wherein the set of content items are identified as candidates for inclusion in the feed based on a ranking score of each content item from the set of content items, and wherein the ranking score of each content item is generated in addition to identifying one or more bucketing tokens for a respective content item from the set of content items;

for each content item from the set of content items, identify one or more bucketing tokens, wherein each bucketing token comprises an identifier that identifies a plurality of content items as being associated with a group of users that have similar interests;

adjust a ranking score of each content item from the set of content items that has at least one bucketing token matching a bucketing token associated with the user of the social network platform; and

cause the set of content items identified for inclusion in the feed displayed to the user in the user interface of the social network platform to be modified based on adjusted ranking scores of respective content items from the set of content items.

16. The system of claim 15 wherein ranking scores of the set of content items are based on at least one of (i) watch histories of a plurality of other users followed by the user on the social network platform, or (ii) content item approvals of the plurality of other users on the social network platform.

17. The system of claim 15 , wherein the bucketing token is embedded in a metadata of each of the plurality of associated content items or is associated with a corresponding content item of the plurality of associated content items via a mapping between the bucketing token and the corresponding content item, the mapping being stored in a data store.

18. The system of claim 15 , wherein the processing device is further to receive the set of content items from a content sharing platform.

19. The system of claim 18 , wherein the processing device is further to:

for a first content item in the set of content items:

determine whether a bucketing token is embedded in metadata of the first content item;

responsive to determining that the bucketing token is embedded in the metadata of the first content item, extract the bucketing token from the metadata of the first content item; and

for a second content item in the set of content items:

responsive to determining that the bucketing token is not embedded in metadata of the second content item, request the bucketing token for the second content item from the content sharing platform.

20. The system of claim 19 , wherein the processing device is further to:

provide the bucketing token for the first content item to a ranking service;

provide, to the ranking service, a set of bucketing tokens associated with the user of the social network; and

receive a ranking score for the first content item based on the bucketing token for the first content item and the set of bucketing tokens associated with the user of the social network platform.