Cognitive adjustment of social interactions to edited content

1. A method comprising:

computing, a shift in sentiment using a natural language processing engine of a data processing system, the shift comprising a difference between an original sentiment value of an original content of a post on social media and an edited sentiment value of an edited content of the post, wherein the post has an associated reaction value;

computing, by applying a function to the shift, an action value, the action value corresponding to a type of action that can be used to manipulate the reaction value;

selecting an action corresponding to the type of action, wherein the type of action is a change type, wherein the action corresponding to the change type is at least one of a reset action and a reverse action, wherein the reset action resets the reaction value to a null value, and wherein the reverse action changes the reaction value to an opposite value; and

sending, to a social media server, an instruction to perform the action relative to the reaction value associated with the post, wherein the instruction causes the reaction value to be manipulated responsive to the shift in sentiment.

2. The method of claim 1 , further comprising:

determining, using historical data about the post, a number of edits performed on the post;

computing, responsive to the number of edits exceeding a threshold number, a factor value corresponding to the number of edits; and

using the factor value in the function to compute the action value.

3. The method of claim 1 , further comprising:

determining, using historical data about the post, a number of edits performed on a set of posts by the author of the post;

computing, responsive to the number of edits exceeding a threshold number, a factor value corresponding to the number of edits; and

using the factor value in the function to compute the action value.

4. The method of claim 1 , further comprising:

determining, using historical data about the post, a number of reaction values that have been changed relative to the post;

computing, responsive to the number of reaction values that have been changed exceeding a threshold number, a factor value corresponding to the number of reaction values that have been changed; and

using the factor value in the function to compute the action value.

5. The method of claim 1 , further comprising:

computing a confidence value corresponding to the shift in sentiment, wherein the confidence value corresponds to a confidence level associated with a sentiment analysis of the edited content.

6. The method of claim 5 , further comprising:

using the confidence value in the function to compute the action value.

7. The method of claim 1 , wherein the action corresponding to the change type is the reset action.

8. The method of claim 1 , wherein the action corresponding to the change type is the reverse action.

9. The method of claim 1 , wherein the type of action is a notification type, wherein the action corresponding to the notification type is a notification action, further comprising: sending information about the shift in sentiment to a user who supplied the reaction value.

10. The method of claim 1 , further comprising:

parsing, using Natural Language Processing (NLP), the original content to determine an original sentiment;

computing a first value corresponding to the original sentiment, the first value forming the original sentiment value;

parsing, using NLP, the edited content to determine an edited sentiment; and

computing a second value corresponding to the edited sentiment, the second value forming the edited sentiment value.

11. A computer usable program product comprising one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices, the stored program instructions comprising:

program instructions to compute, a shift in sentiment using a natural language processing engine of a data processing system, the shift comprising a difference between an original sentiment value of an original content of a post on social media and an edited sentiment value of an edited content of the post, wherein the post has an associated reaction value;

program instructions to compute, by applying a function to the shift, an action value, the action value corresponding to a type of action that can be used to manipulate the reaction value;

program instructions to select an action corresponding to the type of action, wherein the type of action is a change type, wherein the action corresponding to the change type is at least one of a reset action and a reverse action, wherein the reset action resets the reaction value to a null value, and wherein the reverse action changes the reaction value to an opposite value; and

program instructions to send, to a social media server, an instruction to perform the action relative to the reaction value associated with the post, wherein the instruction causes the reaction value to be manipulated responsive to the shift in sentiment.

12. The computer usable program product of claim 11 , further comprising:

program instructions to determine, using historical data about the post, a number of edits performed on the post;

program instructions to compute, responsive to the number of edits exceeding a threshold number, a factor value corresponding to the number of edits; and

program instructions to use the factor value in the function to compute the action value.

13. The computer usable program product of claim 11 , further comprising:

program instructions to determine, using historical data about the post, a number of edits performed on a set of posts by the author of the post;

program instructions to compute, responsive to the number of edits exceeding a threshold number, a factor value corresponding to the number of edits; and

program instructions to use the factor value in the function to compute the action value.

14. The computer usable program product of claim 11 , further comprising:

program instructions to determine, using historical data about the post, a number of reaction values that have been changed relative to the post;

program instructions to compute, responsive to the number of reaction values that have been changed exceeding a threshold number, a factor value corresponding to the number of reaction values that have been changed; and

program instructions to use the factor value in the function to compute the action value.

15. The computer usable program product of claim 11 , further comprising:

program instructions to compute a confidence value corresponding to the shift in sentiment, wherein the confidence value corresponds to a confidence level associated with a sentiment analysis of the edited content.

16. The computer usable program product of claim 15 , further comprising:

program instructions to use the confidence value in the function to compute the action value.

17. The computer usable program product of claim 11 , wherein the action corresponding to the change type is the reset action.

18. The computer usable program product of claim 11 , wherein the computer usable code is stored in a computer readable storage device in a data processing system, and wherein the computer usable code is transferred over a network from a remote data processing system.

19. The computer usable program product of claim 11 , wherein the computer usable code is stored in a computer readable storage device in a server data processing system, and wherein the computer usable code is downloaded over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system.

20. A computer system comprising one or more processors, one or more computer-readable memories, and one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:

program instructions to compute, a shift in sentiment using a natural language processing engine of a data processing system, the shift comprising a difference between an original sentiment value of an original content of a post on social media and an edited sentiment value of an edited content of the post, wherein the post has an associated reaction value;

program instructions to compute, by applying a function to the shift, an action value, the action value corresponding to a type of action that can be used to manipulate the reaction value;

program instructions to select an action corresponding to the type of action, wherein the type of action is a change type, wherein the action corresponding to the change type is at least one of a reset action and a reverse action, wherein the reset action resets the reaction value to a null value, and wherein the reverse action changes the reaction value to an opposite value; and

program instructions to send, to a social media server, an instruction to perform the action relative to the reaction value associated with the post, wherein the instruction causes the reaction value to be manipulated responsive to the shift in sentiment.