Predicting sharing on a social network

1. A non-transitory computer-readable storage device comprising instructions that, when executed, cause one or more processors to:

calculate a score for an article, from a source, using an average number of times other articles belonging to the source were shared on a social network (“t-density”);

predict, using the score, a number of times the article will be shared on the social network.

2. The device of claim 1 , wherein calculating the score further causes the one or more processors to multiply the t-density by a percentage of times the t-density is above the average t-density of multiple sources.

3. The device of claim 1 , wherein using the average number of times comprises using the average number of times other articles belonging to the source were shared on the social network within a particular number of previous days.

4. The device of claim 3 , wherein the particular number is 54.

5. The device of claim 1 , wherein predicting the number of times comprises assigning the article to a class out of a plurality of classes using the score, each class representing a numerical range, the range of the assigned class including the number of times predicted.

6. The device of claim 1 , wherein calculating the score comprises using a number of how many named entities are in the article, a named entity comprising a well-known place, person, or organization.

7. The device of claim 1 , wherein calculating the score comprises using a number of how many named entities appear in the article, a named entity comprising a well-known place, person, or organization.

8. The device of claim 1 , wherein calculating the score comprises using a popularity score associated with a named entity in the article, a named entity comprising a well-known place, person, or organization, each named entity associated with a popularity score.

9. The device of claim 8 , wherein the popularity score associated with a named entity is calculated using the average number of times an article in which the named entity appears is shared on the social network within a particular number of previous days.

10. The device of claim 1 , wherein calculating the score comprises using a number of how many named entities appear in the article, a named entity comprising a well-known place, person, or organization.

11. The device of claim 1 , wherein calculating the score comprises using an average popularity score of named entities in the article, a named entity comprising a well-known place, person, or organization, each named entity associated with a popularity score.

12. A method, comprising:

calculating, by a processor, a score for an article, from a source, using an average number of times other articles belonging to the source were shared on a social network (“t-density”);

predicting, by the processor, using the score, a number of times the article will be shared on the social network.

13. The method of claim 12 , wherein calculating the score comprises multiplying the t-density by a percentage of times the t-density is above the average t-density of multiple sources.

14. The method of claim 12 , wherein using the average number of times comprises using the average number of times other articles belonging to the source were shared on the social network within a particular number of previous days.

15. The method of claim 12 , wherein predicting the number of times comprises assigning the article to a class out of a plurality of classes using the score, each class representing a numerical range, the range of the assigned class including the number of times predicted.

16. The method of claim 12 , wherein calculating the score comprises using a number of how many named entities are in the article, a named entity comprising a well-known place, person, or organization.

17. A system, comprising:

a parser engine; and

a prediction engine coupled to the parser engine, the prediction engine to:

calculate a score for an article, from a source, using an average number of times other articles belonging to the source were shared on a social network (“t-density”);

predict, using the score, a number of times the article will be shared on the social network.

18. The system of claim 17 , wherein the parser engine supplies the prediction engine with metadata parsed from the article.

19. The system of claim 17 , wherein using the average number of times comprises using the average number of times other articles belonging to the source were shared on the social network within a particular number of previous days.

20. The system of claim 17 , wherein calculating the score comprises using a number of how many named entities are in the article, a named entity comprising a well-known place, person, or organization.