Method to increase content relevance using insights obtained from user activity updates
Embodiments are directed towards ranking candidate pieces of content for publication based on a weighted combination of an “activity score” and a “trending score”. In one embodiment, the activity score measures social activity related to the content, such as how much the content has been shared, viewed, or commented on. In one embodiment, the trending score indicates a measure of trending topics contained in the content. In one embodiment, trending topics are keywords derived from an analysis of social activities across the internet, such as blog posts, wall posts, tweets, comments, ratings, tags, videos, pictures, and the like. In one embodiment, a topic is trending if it surpasses a minimum absolute threshold of social activity as well as a percentage increase in social activity.
1. A network device, comprising:
a processor; and
a memory storing instructions that, when executed by the processor, cause the network device to perform actions including:
receiving a plurality of candidate pieces of content;
receiving a plurality of aggregated user activity streams, each aggregated user activity stream containing a record of at least one social activity performed by a user on a web page;
extracting a plurality of topics from the plurality of aggregated user activity streams;
calculating a velocity of each extracted topic based on a difference between a metric of the topic over a first period of time and a metric of the topic over a second period of time, wherein the second period of time came before the first period of time;
calculating a trending score for each of the plurality of candidate pieces of content based on a measure of the velocities of one or more extracted topics contained in the candidate piece of content;
ranking the plurality of candidate pieces of content based on the trending score; and
publishing one or more of the plurality of candidate pieces of content based on the ranking.
2. The network device of claim 1 , wherein the trending score is also based on a popularity score, wherein the popularity score includes a measure of social activity associated with one or more pieces of content each of which reference the topic.
3. The network device of claim 1 , wherein the ranking is also based on an activity score calculated for each of the plurality of candidate pieces of content, wherein the activity score is calculated based on a measure of social activity associated with the plurality of candidate pieces of content.
4. The network device of claim 1 , wherein the velocity of each topic is calculated based on an average of historical metrics taken over a plurality of related periods of time including particular hours of the day over one or more days, particular days of the week over one or more weeks, particular weeks of the year over one or more years, particular months of the year over one or more years, particular seasons of the year over one or more years, or particular holidays over one or more years.
5. The network device of claim 2 , wherein calculating the trending score further includes ranking topics based on the velocity of each topic and the popularity score of each topic and calculating the relevance of each of the plurality of candidate pieces of content based on the ranked topics.
6. The network device of claim 1 , wherein the metric of the topic over the first period of time includes a number of times a topic is contained within the aggregated user activity streams during the first period of time.
7. The network device of claim 1 , wherein a social activity includes any type of free text expressing thoughts or feelings of a user, a quantification of how much a user likes something, a means by which a link to a piece of content may be shared, or a word or phrase associated with a piece of content.
8. A method implemented on a computing machine, comprising:
receiving a plurality of candidate pieces of content;
receiving a plurality of aggregated user activity streams, each aggregated user activity stream containing a record of at least one social activity performed by a user on a web page;
extracting a plurality of topics from the plurality of aggregated user activity streams;
calculating a velocity of each extracted topic based on a difference between a metric of the topic over a first period of time and a metric of the topic over a second period of time, wherein the second period of time came before the first period of time;
calculating a trending score for each of the plurality of candidate pieces of content based on a measure of the velocities of one or more extracted topics contained in the candidate piece of content;
ranking the plurality of candidate pieces of content based on the trending score; and
publishing one or more of the plurality of candidate pieces of content based on the ranking.
9. The method of claim 8 , wherein the trending score is also based on a popularity score, wherein the popularity score includes a measure of social activity associated with one or more pieces of content each of which reference the topic.
10. The method of claim 8 , wherein the ranking is also based on an activity score calculated for each of the plurality of candidate pieces of content, wherein the activity score is calculated based on a measure of social activity associated with the plurality of candidate pieces of content.
11. The method of claim 8 , wherein the velocity of each topic is calculated based on an average of historical metrics taken over a plurality of related periods of time including particular hours of the day over one or more days, particular days of the week over one or more weeks, particular weeks of the year over one or more years, particular months of the year over one or more years, particular seasons of the year over one or more years, or particular holidays over one or more years.
12. The method of claim 9 , wherein calculating the trending score further includes ranking topics based on the velocity of each topic and the popularity score of each topic and calculating the relevance of each of the plurality of candidate pieces of content based on the ranked topics.
13. The method of claim 8 , wherein the metric of the topic over the first period of time includes a number of times a topic is contained within the aggregated user activity streams during the first period of time.
14. The method of claim 8 , wherein a social activity includes any type of free text expressing thoughts or feelings of a user, a quantification of how much a user likes something, a means by which a link to a piece of content may be shared, or a word or phrase associated with a piece of content.
15. A non-transitory computer-readable storage medium storing instructions that when executed by a processor cause actions to be performed, comprising:
receiving a plurality of candidate pieces of content;
receiving a plurality of aggregated user activity streams, each aggregated user activity stream containing a record of at least one social activity performed by a user on a web page;
extracting a plurality of topics from the plurality of aggregated user activity streams;
calculating a velocity of each extracted topic based on a difference between a metric of the topic over a first period of time and a metric of the topic over a second period of time, wherein the second period of time came before the first period of time;
calculating a trending score for each of the plurality of candidate pieces of content based on a measure of the velocities of one or more extracted topics contained in the candidate piece of content;
ranking the plurality of candidate pieces of content based on the trending score; and
publishing one or more of the plurality of candidate pieces of content based on the ranking.
16. The computer-readable storage medium of claim 15 , wherein the trending score is also based on a popularity score, wherein the popularity score includes a measure of social activity associated with one or more pieces of content each of which reference the topic.
17. The computer-readable storage medium of claim 15 , wherein the ranking is also based on an activity score calculated for each of the plurality of candidate pieces of content, wherein the activity score is calculated based on a measure of social activity associated with the plurality of candidate pieces of content.
18. The computer-readable storage medium of claim 15 , wherein the velocity of each topic is calculated based on an average of historical metrics taken over a plurality of related periods of time including particular hours of the day over one or more days, particular days of the week over one or more weeks, particular weeks of the year over one or more years, particular months of the year over one or more years, particular seasons of the year over one or more years, or particular holidays over one or more years.
19. The computer-readable storage medium of claim 16 , wherein calculating the trending score further includes ranking topics based on the velocity of each topic and the popularity score of each topic and calculating the relevance of each of the plurality of candidate pieces of content based on the ranked topics.
20. The computer-readable storage medium of claim 15 , wherein the metric of the topic over the first period of time includes a number of times a topic is contained within the aggregated user activity streams during the first period of time.