Determining sentiment of content and selecting content items for transmission to devices

1. A method, comprising:

analyzing an informational database based upon a first entity to identify a first informational article associated with the first entity from a plurality of informational articles of the informational database;

analyzing the first informational article to identify:

one or more first references associated with a first sentiment category; and

one or more second references associated with a second sentiment category;

assigning one or more first sentiment tags, indicative of the first sentiment category, to one or more first reference content items associated with the one or more first references;

assigning one or more second sentiment tags, indicative of the second sentiment category, to one or more second reference content items associated with the one or more second references;

identifying a plurality of content items associated with the first entity;

for each content item of the plurality of content items:

determining a content item sentiment category associated with the content item based upon a comparison of the content item with the one or more first reference content items and the one or more second reference content items; and

assigning a sentiment tag, corresponding to the content item sentiment category, to the content item;

receiving a request for content associated with a client device;

analyzing a user profile associated with the client device to identify one or more first content items comprising at least one of:

one or more content items of the one or more first reference content items associated with the first sentiment category;

one or more content items of the one or more second reference content items associated with the second sentiment category; or

one or more content items of the plurality of content items;

identifying one or more sentiment tags associated with the one or more first content items;

generating, based upon the one or more sentiment tags, a user sentiment score associated with the first entity; and

selecting a transmission content item for transmission to the client device based upon the user sentiment score.

2. The method of claim 1 , wherein:

the informational database is associated with a web encyclopedia; and

each informational article of the plurality of informational articles corresponds to an entry of the web encyclopedia.

3. The method of claim 1 , comprising:

generating, based upon the one or more first reference content items, one or more first vector representations, wherein each vector representation of the one or more first vector representations corresponds to a content item of the one or more first reference content items;

generating, based upon the one or more second reference content items, one or more second vector representations, wherein each vector representation of the one or more second vector representations corresponds to a content item of the one or more second reference content items; and

generating, based upon the plurality of content items, a plurality of vector representations, wherein each vector representation of the plurality of vector representations corresponds to a content item of the plurality of content items.

4. The method of claim 3 , wherein for each content item of the plurality of content items:

the determining the content item sentiment category associated with the content item comprises comparing a vector representation corresponding to the content item with the one or more first vector representations and the one or more second vector representations to determine a plurality of similarities, wherein each similarity of the plurality of similarities corresponds to a similarity between the vector representation and a second vector representation of the one or more first vector representations or the one or more second vector representations; and

the content item sentiment category is determined based upon the one or more first vector representations, the one or more second vector representations and the plurality of similarities.

5. The method of claim 1 , wherein for each content item of the plurality of content items:

the content item sentiment category is determined based upon a second comparison of the content item with one or more third reference content items associated with a second informational article associated with a second entity.

6. The method of claim 1 , wherein the analyzing the first informational article to identify the one or more first references associated with the first sentiment category comprises:

identifying one or more sections, within the first informational article, associated with the first sentiment category;

identifying, within the one or more sections, indications of the one or more first references; and

determining, based upon the indications of the one or more first references being within the one or more sections associated with the first sentiment category, that the one or more first references are associated with the first sentiment category.

7. The method of claim 6 , wherein the identifying the one or more sections is performed based upon a determination that one or more headers associated with the one or more sections are associated with the first sentiment category.

8. The method of claim 6 , wherein the identifying the one or more sections is performed based upon a determination that each header of one or more headers associated with the one or more sections matches a header in a first list of headers associated with the first sentiment category.

9. The method of claim 1 , comprising transmitting the transmission content item to the client device.

10. A computing device comprising:

a processor; and

memory comprising processor-executable instructions that when executed by the processor cause performance of operations, the operations comprising:

analyzing an informational database based upon a first entity to identify a first informational article associated with the first entity from a plurality of informational articles of the informational database;

analyzing the first informational article to identify:

one or more first references determined to be associated with a first sentiment category based upon one or more indications of the one or more first references being within a section, of the first informational article, associated with the first sentiment category;

assigning one or more first sentiment tags, indicative of the first sentiment category, to one or more first reference content items associated with the one or more first references;

identifying a plurality of content items associated with the first entity; and

for each content item of the plurality of content items:

determining a content item sentiment category associated with the content item based upon a comparison of the content item with the one or more first reference content items; and

assigning a sentiment tag, corresponding to the content item sentiment category, to the content item.

11. The computing device of claim 10 , wherein:

the informational database is associated with a web encyclopedia; and

each informational article of the plurality of informational articles corresponds to an entry of the web encyclopedia.

12. The computing device of claim 10 , the operations comprising:

generating, based upon the one or more first reference content items, one or more first vector representations, wherein each vector representation of the one or more first vector representations corresponds to a content item of the one or more first reference content items;

and

generating, based upon the plurality of content items, a plurality of vector representations, wherein each vector representation of the plurality of vector representations corresponds to a content item of the plurality of content items.

13. The computing device of claim 12 , for each content item of the plurality of content items:

the determining the content item sentiment category associated with the content item comprises comparing a vector representation corresponding to the content item with the one or more first vector representations to determine a plurality of similarities, wherein each similarity of the plurality of similarities corresponds to a similarity between the vector representation and a second vector representation of the one or more first vector representations; and

the content item sentiment category is determined based upon the one or more first vector representations and the plurality of similarities.

14. The computing device of claim 10 , wherein for each content item of the plurality of content items:

the content item sentiment category is determined based upon a second comparison of the content item with one or more third reference content items associated with a second informational article associated with a second entity.

15. The computing device of claim 10 , the operations comprising:

analyzing the first informational article to identify one or more second references associated with a second sentiment category; and

assigning one or more second sentiment tags, indicative of the second sentiment category, to one or more second reference content items associated with the one or more second references, wherein the content item sentiment category is based upon the one or more second reference content items.

16. The computing device of claim 10 , the operations comprising identifying the sections based upon a determination that a header associated with the section is associated with the first sentiment category.

17. The computing device of claim 10 , the operations comprising identifying the sections based upon a determination that a header associated with the section matches a listed header in a first list of headers associated with the first sentiment category.

18. A non-transitory machine readable medium having stored thereon processor-executable instructions that when executed cause performance of operations, the operations comprising:

receiving a request for content associated with a client device;

analyzing a user profile associated with the client device to identify one or more first content items associated with a first entity;

determining a first sentiment tag, indicative of a first sentiment category, for a first content item of the one or more first content items, wherein the first sentiment tag is determined for the first content item based upon an indication of a first reference associated with the first content item being within a section, of an article associated with the first entity, associated with the first sentiment category;

identifying one or more sentiment tags, comprising the first sentiment tag, associated with the one or more first content items and the first entity;

generating, based upon the one or more sentiment tags, a user sentiment score associated with the first entity; and

selecting a transmission content item for transmission to the client device based upon the user sentiment score.

19. The non-transitory machine readable medium of claim 18 , the operations comprising transmitting the transmission content item to the client device.

20. The non-transitory machine readable medium of claim 18 , wherein the request for content is received from the client device.