Article topic alignment

1. A method, comprising:

analyzing, by a computing device, a plurality of portions of a document;

determining, by the computing device and based on the analyzing, a concept of each of the portions of the document;

comparing, by the computing device, a title of the document with the concept of each of the portions of the document;

determining, by the computing device and based on the comparing, an alignment of the concept of each of the portions of the document with the title;

generating, by the computing device and based on the alignment, a propensity score for each of the portions of the document;

reordering, by the computing device and based on the propensity scores, the portions of the document from most aligned with the title to least aligned with the title; and

displaying, by the computing device, a user interface by which a user may interact with the reordered portions of the document.

2. The method of claim 1 , further comprising generating, by the computing device and based on the concept of each of the portions of the document, a caption for each of the portions of the document.

3. The method of claim 1 , wherein the portions of the document are paragraphs in the document.

4. The method of claim 1 , wherein the portions of the document are photographs in the document.

5. The method of claim 1 , wherein the document is an article.

6. The method of claim 1 , further comprising grouping, by the computing device and based on the concept of each of the portions of the document, one or more of the portions of the document into a group.

7. The method of claim 6 , wherein the grouping comprises applying unsupervised machine learning through clustering to determine which of the portions of the document to group together.

8. The method of claim 6 , further comprising generating, by the computing device and based on the grouping, a caption for the group.

9. The method of claim 1 , further comprising removing, by the computing device, the portions of the document that have the propensity score below a threshold.

10. The method of claim 1 , further comprising categorizing, by the computing device, a word in one of the portions of the document as high risk, wherein high risk indicates an undesirable word.

11. The method of claim 1 , further comprising determining, by the computing device, that the title is low risk, wherein low risk indicates a desirable title.

12. The method of claim 11 , further comprising determining, by the computing device, that a word in one of the portions of the document as high risk, wherein high risk indicates an undesirable word.

13. The method of claim 1 , further comprising:

deriving, by the computing device, attributes of the portions of the document;

assigning, by the computing device, weights to the attributes using deep learning; and

predicting, by the computing device, an intent of the document based on the weighted attributes.

14. A computer program product comprising one or more computer readable storage media having program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to:

analyze a plurality of portions of a document;

determine, based on the analyzing, a concept of each of the portions of the document;

compare a title of the document with the concept of each of the portions of the document;

determine, based on the comparing, an alignment of the concept of each of the portions of the document with the title;

generate, based on the alignment, a propensity score for each of the portions of the document;

generate, based on the concept of each of the portions of the document, a caption for each of the portions of the document; and

display a user interface by which a user may interact with the generated portions of the document.

15. The computer program product of claim 14 , further comprising program instructions executable to reorder, based on the propensity scores, the portions of the document from most aligned with the title to least aligned with the title.

16. The computer program product of claim 14 , further comprising program instructions executable to receive, from a user, a risk level designation of a particular word in the portions of the document, wherein the risk level indicates desirability of the particular word.

17. The computer program product of claim 14 , further comprising program instructions executable to:

derive attributes of the portions of the document;

assign weights to the attributes using deep learning; and

predict an intent of the document based on the weighted attributes.

18. The computer program product of claim 17 , further comprising program instructions executable to compare the concept of one of the portions of the document to the intent of the document.

19. The computer program product of claim 18 , further comprising program instructions executable to remove the one of the portions of the document based on the comparing the concept of the one of the portions of the document to the intent of the document.

20. A system comprising:

a processor, a computer readable memory, one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to:

analyze a plurality of portions of a document;

determine, based on the analyzing, a concept of each of the portions of the document;

compare a title of the document with the concept of each of the portions of the document;

determine, based on the comparing, an alignment of the concept of each of the portions of the document with the title;

generate, based on the alignment, a propensity score for each of the portions of the document;

reorder, based on the propensity scores, the portions of the document from most aligned with the title to least aligned with the title; and

provide a user interface for a user to view the reordered portions of the document.