Systems and methods for evaluating diversity of content based on content properties

1. A computer-implemented method comprising:

acquiring, by a computing system, a set of properties associated with a set of content items, wherein the set of properties includes at least an author of a content item and a topic of a content item;

selecting, by the computing system, a plurality of property combinations from the set of properties, wherein the plurality of property combinations are selected such that each of the plurality of property combinations includes a respective unique property from the set of properties including at least an author of a content item and a topic of a content item;

determining, by the computing system, a plurality of numbers of unique properties associated with the plurality of property combinations selected from the set of properties associated with the set of content items, the determining further comprising:

identifying, by the computing system, a respective quantity of times each unique property is present in the set of properties, wherein the plurality of numbers includes the respective quantity of times for each unique property;

generating, by the computing system, a diversity metric for the set of content items based on at least some of the plurality of numbers of unique properties associated with the plurality of property combinations including the respective quantity of times each unique property is present in the set of properties;

comparing, by the computing system, the diversity metric for the set of content items with a diversity metric determined for a second set of content items;

determining, by the computing system, that the set of content items is more diverse in content than the second set of content items based at least in part on the comparison of the diversity metric for the set of content items with the diversity metric for the second set of content items; and

performing, by the computing system, a ranking for at least some content items out of the set of content items for presentation in a feed, the ranking being performed based on the diversity metric for the set of content items.

2. The computer-implemented method of claim 1 , wherein the set of content items is ranked based on an order produced from one or more content ranking algorithms, and wherein the set of properties is representable as a series of properties based on the order.

3. The computer-implemented method of claim 2 , wherein the plurality of property combinations are selected to represent differing segments of the series of properties.

4. The computer-implemented method of claim 3 , wherein determining the plurality of numbers of unique properties associated with the plurality of property combinations further comprises:

identifying one or more sets of property combinations that are each associated with a respective segment length; and

determining one or more pre-defined minimum numbers of unique properties associated with the one or more sets of property combinations, wherein each of the one or more pre-defined minimum numbers of unique properties is determined for each of the one or more sets of property combinations, and wherein the plurality of numbers of unique properties includes the one or more pre-defined minimum numbers of unique properties.

5. The computer-implemented method of claim 4 , wherein generating the diversity metric for the set of content items further comprises:

producing one or more normalized values based on dividing each of the one or more pre-defined minimum numbers of unique properties by the respective segment length associated with each of the one or more sets of property combinations;

generating a sum of the one or more normalized values; and

dividing the sum by a total segment length associated with the series of properties to produce a resulting value, wherein the diversity metric is based on the resulting value.

6. The computer-implemented method of claim 1 , wherein generating the diversity metric for the set of content items further comprises:

producing a respective probability value for each unique property based on dividing the respective quantity of times for each unique property by a total amount of properties in the set of properties; and

calculating an entropic value based on the respective probability value for each unique property, wherein the diversity metric is based on the entropic value.

7. The computer-implemented method of claim 1 , wherein the set of properties further includes at least one of a tag, a location, an object, or a classification.

8. A system comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the system to perform:

acquiring a set of properties associated with a set of content items, wherein the set of properties includes at least an author of a content item and a topic of a content item;

selecting a plurality of property combinations from the set of properties, wherein the plurality of property combinations are selected such that each of the plurality of property combinations includes a respective unique property from the set of properties including at least an author of a content item and a topic of a content item;

determining a plurality of numbers of unique properties associated with the plurality of property combinations selected from the set of properties associated with the set of content items, the determining further comprising:

identifying a respective quantity of times each unique property is present in the set of properties, wherein the plurality of numbers includes the respective quantity of times for each unique property;

generating a diversity metric for the set of content items based on at least some of the plurality of numbers of unique properties associated with the plurality of property combinations including the respective quantity of times each unique property is present in the set of properties;

comparing the diversity metric for the set of content items with a diversity metric determined for a second set of content items;

determining that the set of content items is more diverse in content than the second set of content items based at least in part on the comparison of the diversity metric for the set of content items with the diversity metric for the second set of content items; and

performing a ranking for at least some content items out of the set of content items for presentation in a feed, the ranking being performed based on the diversity metric for the set of content items.

9. The system of claim 8 , wherein the set of content items is ranked based on an order produced from one or more content ranking algorithms, and wherein the set of properties is representable as a series of properties based on the order.

10. The system of claim 9 , wherein the plurality of property combinations are selected to represent differing segments of the series of properties.

11. The system of claim 8 , wherein the set of properties further includes at least one of a tag, a location, an object, or a classification.

12. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:

acquiring a set of properties associated with a set of content items, wherein the set of properties includes at least an author of a content item and a topic of a content item;

selecting a plurality of property combinations from the set of properties, wherein the plurality of property combinations are selected such that each of the plurality of property combinations includes a respective unique property from the set of properties including at least an author of a content item and a topic of a content item;

determining a plurality of numbers of unique properties associated with the plurality of property combinations selected from the set of properties associated with the set of content items, the determining further comprising:

identifying a respective quantity of times each unique property is present in the set of properties, wherein the plurality of numbers includes the respective quantity of times for each unique property;

generating a diversity metric for the set of content items based on at least some of the plurality of numbers of unique properties associated with the plurality of property combinations including the respective quantity of times each unique property is present in the set of properties;

comparing the diversity metric for the set of content items with a diversity metric determined for a second set of content items;

determining that the set of content items is more diverse in content than the second set of content items based at least in part on the comparison of the diversity metric for the set of content items with the diversity metric for the second set of content items; and

performing a ranking for at least some content items out of the set of content items for presentation in a feed, the ranking being performed based on the diversity metric for the set of content items.

13. The non-transitory computer-readable storage medium of claim 12 , wherein the set of content items is ranked based on an order produced from one or more content ranking algorithms, and wherein the set of properties is representable as a series of properties based on the order.

14. The non-transitory computer-readable storage medium of claim 13 , wherein the plurality of property combinations are selected to represent differing segments of the series of properties.

15. The non-transitory computer-readable storage medium of claim 12 , wherein the set of properties further includes at least one of a tag, a location, an object, or a classification.