Collaborative filtering of content recommendations
View Patent ↗Identifying collaboratively filtered content recommendations based on user activity data collected from users in an electronic environment is disclosed. The user activity data includes information relating to user-engagement indications of the users. Multiple connection pairs are identified based on the user activity data, with each connection pair including a potential target document and a candidate recommendation document. A connection strength is determined for each of the identified connection pairs. An overall grade is generated for a set of candidate connection pairs of the plurality of connection pairs, wherein the overall grade is based on the respective connection strength associated with each of the set of candidate connection pairs. One or more filtered recommendations for provisioning in connection with the target document based on a comparison of the overall grade associated with each of the set of candidate connection pairs.
1. A method comprising:
collecting user activity data associated with a plurality of users, wherein the user activity data comprises information relating to user-engagement indications of the plurality of users;
identifying a plurality of connection pairs based on the user activity data, wherein each connection pair comprises a target document and a candidate recommendation document;
determining a connection strength for each of the plurality of connection pairs;
generating an overall grade for each of a set of candidate connection pairs of the plurality of connection pairs, wherein the overall grade is based on the respective connection strength associated with each of the set of candidate connection pairs, and wherein the overall grade is decreased in view of a causality component representing a high global user-engagement indication value for a respective candidate recommendation document; and
identifying, by a processing device, one or more filtered recommendations for the target document based on a comparison of the overall grade associated with the candidate connection pairs.
2. The method of claim 1 , wherein the user-engagement indication comprises information indicating a user visited the target document and a first candidate recommendation document within a selected time period.
3. The method of claim 1 , further comprising facilitating provisioning of at least one of the one or more identified filtered recommendations associated with the target document.
4. The method of claim 1 , wherein the overall grade is based at least in part on a common user component, an aging component, and the causality component.
5. The method of claim 4 , wherein the common user component represents a measure of unique user-engagement indications associated with a respective connection pair.
6. The method of claim 4 , wherein the aging component represents a measure of an age of a respective candidate recommendation document.
7. The method of claim 4 , wherein the aging component represents a measure of an age of a respective connection pair of the plurality of connection pairs.
8. A system comprising:
a memory to store instructions; and
a processing device operatively coupled with the memory, the processing device to execute the instructions to:
collect user activity data associated with a plurality of users, wherein the user activity data comprises information relating to user-engagement indications of the plurality of users,
identify a plurality of connection pairs based on the user activity data, wherein each connection pair comprises a target document and a candidate recommendation document,
determine a connection strength for each of the plurality of connection pairs,
generate an overall grade for each of a set of candidate connection pairs of the plurality of connection pairs, wherein the overall grade is based on the respective connection strength associated with each of the set of candidate connection pairs, and wherein the overall grade is decreased in view of a causality component representing a high global user-engagement indication value for a respective candidate recommendation document, and
identify, by the processing device, one or more filtered recommendations for the target document based on a comparison of the overall grade associated with the candidate connection pairs.
9. The system of claim 8 , the processing device further configured to facilitate provisioning of at least one of the one or more identified filtered recommendations associated with the target document.
10. The system of claim 8 , wherein the overall grade is based at least in part on a common user component, an aging component, and the causality component.
11. The system of claim 10 , wherein the common user component represents a measure of unique user-engagement indications associated with a respective connection pair.
12. The system of claim 10 , wherein the aging component represents at least one of a measure of an age of a respective candidate recommendation document or an age of a respective connection pair of the plurality of connection pairs.
13. A non-transitory computer readable storage medium comprising instructions thereon that, in response to execution by a processing device, cause the processing device to perform operations comprising:
collecting user activity data associated with a plurality of users, wherein the user activity data comprises information relating to user-engagement indications of the plurality of users;
identifying a plurality of connection pairs based on the user activity data, wherein each connection pair comprises a target document and a candidate recommendation document;
determining a connection strength for each of the identified connection pairs;
generating an overall grade for each of a set of candidate connection pairs of the plurality of connection pairs, wherein the overall grade is based on the respective connection strength associated with each of the set of candidate connection pairs, and wherein the overall grade is decreased in view of a causality component representing a high global user-engagement indication value for a respective candidate recommendation document; and
identifying, by the processing device, one or more filtered recommendations for the target document based on a comparison of the overall grade associated with the candidate connection pairs.
14. The non-transitory computer readable storage medium of claim 13 , the operations further comprising facilitating provisioning of at least one of the one or more identified filtered recommendations associated with the target document.
15. The non-transitory computer readable storage medium of claim 13 , wherein the overall grade is based at least in part on a common user component, an aging component, and the causality component.
16. The non-transitory computer readable storage medium of claim 15 , wherein the common user component represents a measure of unique user-engagement indications associated with a respective connection pair.
17. The non-transitory computer readable storage medium of claim 16 , wherein the aging component represents at least one of a measure of an age of a respective candidate recommendation document or a measure of an age of a respective connection pair of the plurality of connection pairs.