Baseline interest profile for recommendations using a geographic location

1. A method, comprising:

generating a first representation of interests for a geographical location, wherein the first representation includes a plurality of entities that are derived from at least one corpus of documents and wherein each entity of the plurality of entities is associated with an expected value that is based at least in part on engagement signals received by a content-aggregation service from one or more users in the geographical location and that is weighted using a sparse-polarity approach to be discriminative with respect to other entities, wherein one or more entities of the plurality of entities are labels derived from the at least one corpus; and

using the first representation, a similarity measure, and a second representation to create rankings of a plurality of ingested articles, wherein each ingested article of the plurality of ingested articles is represented by the second representation that associates an about score from each entity of the plurality of entities.

2. The method of claim 1 , wherein the geographical location is a city.

3. The method of claim 1 , wherein the first representation and the second representation are vectors.

4. The method of claim 1 , comprising an operation of updating the plurality of entities with new signals in real-time or near-real-time, using stream processing.

5. The method of claim 1 , wherein the similarity measure is cosine similarity.

6. The method of claim 1 , wherein the labels are nodes in a taxonomy created at least in part from documents previously ingested by the content-aggregation service.

7. The method of claim 1 , wherein the expected value reflects a conditional probability of a positive user engagement with an entity, given the geographical location.

8. The method of claim 1 , wherein the geographical location is determined from an internet-protocol (IP) address.

9. The method of claim 1 , wherein the sparse-polarity approach involves application of a threshold to a z-statistic.

10. One or more computer-readable media that are non-transitory and that store a program, wherein the program, when executed, instructs a processor to perform the following operations:

generate a first representation of interests for a geographical location, wherein the first representation includes a plurality of entities that are derived from at least one corpus of documents and wherein each entity of the plurality of entities is associated with a probability score that is based at least in part on engagement signals received from one or more users in the geographical location, wherein one or more entities of the plurality of entities are labels derived from the at least one corpus;

use the first representation, a similarity measure, and a second representation to create rankings of a plurality of ingested articles received by a content-aggregation service, wherein each ingested article of the plurality of ingested articles is represented by the second representation that associates an about score from each entity of the plurality of entities;

receive a request for access to the content-aggregation service from a new or infrequent user from the geographical location; and

serve the new or infrequent user a content stream based at least in part on the rankings.

11. The one or more computer-readable media of claim 10 , wherein the geographical location is a city.

12. The one or more computer-readable media of claim 10 , wherein the first representation and the second representation are vectors.

13. The one or more computer-readable media of claim 10 , comprising an operation of updating the plurality of entities with new signals in real-time or near-real-time, using stream processing.

14. The one or more computer-readable media of claim 10 , wherein the similarity measure is cosine similarity.

15. The one or more computer-readable media of claim 10 , wherein the labels are nodes in a taxonomy created at least in part from documents previously ingested by the content-aggregation service.

16. The one or more computer-readable media of claim 10 , wherein each entity of the plurality of entities is associated with an expected value, wherein the expected value reflects a conditional probability of a positive user engagement with an entity, given the geographical location.

17. The one or more computer-readable media of claim 10 , wherein the geographical location of the new or infrequent user is determined from an internet-protocol (IP) address associated with the new or infrequent user.

18. The one or more computer-readable media of claim 10 , comprising an operation of applying a threshold to a z-statistic.

19. A method, comprising:

generating a first representation of interests for a city, wherein the first representation includes a plurality of entities that are derived from at least one corpus of documents and wherein each entity of the plurality of entities is associated with an expected value that is based at least in part on engagement signals received by a content-aggregation service from one or more users in the city, wherein one or more entities of the plurality of entities are labels derived from the at least one corpus; and

using the first representation, a similarity measure, and a second representation to create rankings of a plurality of ingested articles, wherein each ingested article of the plurality of ingested articles is represented by the second representation that associates an about score from each entity of the plurality of entities and wherein the first representation and the second representation are vectors and the similarity measure is cosine similarity.

20. The method of claim 19 , wherein the city is determined from an internet-protocol (IP) address.