User interaction based related digital content items

1. A computer-implemented method for identifying related digital content items in a plurality of digital content items V comprising digital content item (V 1 , . . . V n ), the method comprising:

for a plurality of pairs of digital content items (V i , V j ) in the plurality of digital content items V, accessing a count C i,j of a number of positive user interactions of each of a plurality of users with digital content item V i which co-occurred within a locality of time with positive user interactions of the user with digital content item V j included in each pair of digital content items (V i , V j );

for at least one digital content item V i included in the plurality of pairs of digital content items (V i , V j ), ranking the digital content items V j according to the counts C i,j ; and

for the at least one digital content item V i , identifying a set R i of related digital content items from the ranked digital content items V j based on the ranked counts C i,j .

2. The computer-implemented method of claim 1 , wherein the positive user interactions of each of the plurality of users with the digital content item V i which co-occurred within the locality of time with the positive user interactions of the user with the digital content item V j indicates user interest in both the digital content item V i and the digital content item V j within the locality of time.

3. The computer-implemented method of claim 1 , further comprising:

storing for a plurality of users, user events indicating positive interactions of each user with the plurality of digital content items V;

wherein a user event indicating a positive interaction with a digital content item V i from the plurality of digital content items V indicates user interest in the digital content item V i .

4. The computer-implemented method of claim 3 , wherein the positive interaction with the digital content item V i comprises an indication of a user viewing the digital content item V i in its entirety.

5. The computer-implemented method of claim 3 , wherein the positive interaction with the digital content item V i comprises an indication of a user requesting playback of the digital content item V i .

6. The computer-implemented method of claim 3 , wherein the positive interaction with the digital content item V i comprises an indication of a user viewing the digital content item V i for a length of time above a threshold.

7. The computer-implemented method of claim 3 , wherein the positive interaction with the digital content item V i comprises an indication of a user rating the digital content item V i above a threshold.

8. The computer-implemented method of claim 3 , wherein the positive interaction with the digital content item V i comprises an indication of a user rewinding the digital content item V i by a threshold percentage.

9. The computer-implemented method of claim 3 , wherein the positive interaction with the digital content item V i comprises an indication that a user navigated to a web page comprising the digital content item V i through a link to the web page.

10. The computer-implemented method of claim 1 , further comprising:

storing for a plurality of users, user events indicating negative interactions of each user with the plurality of digital content items V;

wherein a user event indicating a negative interaction with a digital content item V i from the plurality of digital content items V indicates user disinterest in the digital content item V i .

11. The computer-implemented method of claim 10 , wherein the negative interaction with the digital content item V i comprises an indication of a user viewing the digital content item V i for a length of time less than a threshold.

12. The computer-implemented method of claim 10 , wherein the negative interaction with the digital content item V i comprises an indication of a user viewing less than a threshold percentage of the digital content item V i .

13. The computer-implemented method of claim 10 , wherein the negative interaction with the digital content item V i comprises an indication of a user rating the digital content item V i below a threshold.

14. The computer-implemented method of claim 3 , wherein the negative interaction with the digital content item V i comprises an indication of receiving a search query from a user for another digital content item V j while the digital content item V i is displayed to the user.

15. The computer-implemented method of claim 3 , wherein the negative interaction with the digital content item V i comprises an indication of a user opening a web page while the digital content item V i is displayed to the user.

16. The computer-implemented method of claim 3 , further comprising:

determining from the user events, the count C i,j of the number of positive interactions of each of the plurality of users with digital content item V i which co-occurred within the locality of time with the positive user interactions of the user with the digital content item V j included in each pair of digital content items (V i , V j ).

17. The computer-implemented method of claim 1 , further comprising:

generating a collection of related digital content items for the at least one digital content item V i based on the identified set R i of related digital content items.

18. A computer program product for identifying related digital content items in a plurality of digital content items V comprising digital content item (V 1 , . . . V n ), the computer program product comprising a non-transitory computer readable storage medium containing computer executable code for:

for a plurality of pairs of digital content items (V i , V j ) in the plurality of digital content items V, accessing a count C i,j of a number of positive user interactions of each of a plurality of users with digital content item V i which co-occurred within a locality of time with positive user interactions of the user with digital content item V j included in each pair of digital content items (V i , V j );

for at least one digital content item V i included in the plurality of pairs of digital content items (V i , V j ), ranking the digital content items V j according to the counts C i,j ; and

for the at least one digital content item V i , identifying a set R i of related digital content items from the ranked digital content items V j based on the ranked counts C i,j .

19. The computer program product of claim 18 , wherein the positive user interactions of each of the plurality of users with the digital content item V i which co-occurred within the locality of time with the positive user interactions of each user with the digital content item V j indicates user interest in both the digital content item V i and the digital content item V j within the locality of time.

20. The computer program product of claim 18 , wherein the computer executable code is further for:

storing for a plurality of users, user events indicating positive interactions of each user with the plurality of digital content items V;

wherein a user event indicating a positive interaction with a digital content item V i from the plurality of digital content items V indicates user interest in the digital content item V i ;

wherein the positive interaction with the digital content item V i comprises at least one of an indication of a user viewing the digital content item V i in its entirety, an indication of a user requesting playback of the digital content item V i , an indication of a user viewing the digital content item V i for a length of time above a threshold, an indication of a user rating the digital content item V i above a threshold, or an indication of a user rewinding the digital content item V i by a threshold percentage.

21. A computer system for identifying related digital content items in a plurality of digital content items V comprising digital content item (V 1 , . . . V n ), the computer system comprising:

a computer processor; and

a computer-readable storage medium comprising executable code when executed by the computer processor causes the computer processor to:

for a plurality of pairs of digital content items (V i , V j ) in the plurality of digital content items V, access a count C i,j of a number of positive user interactions of each of a plurality of users with digital content item V i which co-occurred within a locality of time with positive user interactions of the user with digital content item V j included in each pair of digital content items (V i , V j );

for at least one digital content item V i included in the plurality of pairs of digital content items (V i , V j ), rank the digital content items V j according to the counts C i,j ; and

for the at least one digital content item V i , identify a set R i of related digital content items from the ranked digital content items V j based on the ranked counts C i,j .