Cognitive monitoring of online user profiles to detect changes in online behavior

1. A computer-implemented method comprising:

creating a baseline online behavior profile of a user at a time t 1 based on a usage of a social network by the user;

continuously monitoring an online behavior profile of the user on the social network;

in response to detecting a deviation between the online behavior profile and the baseline online behavior profile, creating a changed online behavior profile of the user at a time t 2 , t 2 >t 1 ;

extracting keywords from a plurality of online posts associated with the user, the online posts being from time t 1 until time t 2 ;

determining an event associated with the extracted keywords;

determining a confidence level for the event as cause of the deviation between the online behavior profile and the baseline online behavior profile by comparing the event with a measurement of stress level of the user from one or more activity monitoring devices of the user, where the confidence level is based on the stress level being within a predetermined range that is associated with the event;

in response to the confidence level being below a predetermined threshold, corroborating an occurrence of the event that is determined by receiving a verification from a second user, wherein the second user verifies that the event occurred via an electronic confirmation; and

in response to the corroboration from the second user, and in response to the event being of a predetermined type, sending a notification to a designated caretaker of the user.

2. The computer-implemented method of claim 1 , wherein the event is detected by correlating the extracted keywords with a taxonomy repository of keywords and events.

3. The computer-implemented method of claim 2 , wherein the taxonomy repository is generated by analyzing a plurality of online posts.

4. The computer-implemented method of claim 1 , wherein the deviation between the online behavior profile and the baseline online behavior profile is detected based on a change in at least one data parameter from a plurality of data parameters from the online behavior profile.

5. The computer-implemented method of claim 4 , the online behavior profile comprising a sentiment analysis, and an average frequency of usage of the social network by the user.

6. The computer-implemented method of claim 1 , further comprising generating content specifically for the user based on the event.

7. A system comprising:

an online social network;

a memory; and

a processor configured to monitor the online social network for a change in online behavior of a user when using the online social network by performing a method comprising:

creating a baseline online behavior profile of a user at a time t 1 based on a usage of a social network by the user;

continuously monitoring an online behavior profile of the user on the social network;

in response to detecting a deviation between the online behavior profile and the baseline online behavior profile, creating a changed online behavior profile of the user at a time t 2 , t 2 >t 1 ;

extracting keywords from a plurality of online posts associated with the user, the online posts being from time t 1 until time t 2 ;

determining an event associated with the extracted keywords;

determining a confidence level for the event as cause of the deviation between the online behavior profile and the baseline online behavior profile by comparing the event with a measurement of stress level of the user from one or more activity monitoring devices of the user, where the confidence level is based on the stress level being within a predetermined range that is associated with the event;

in response to the confidence level being below a predetermined threshold, corroborating an occurrence of the event that is determined by receiving a verification from a second user, wherein the second user verifies that the event occurred via an electronic confirmation; and

in response to the corroboration from the second user, and in response to the event being of a predetermined type, sending a notification to a designated caretaker of the user.

8. The system of claim 7 , wherein the event is detected by correlating the extracted keywords with a taxonomy repository of keywords and events.

9. The system of claim 8 , wherein the taxonomy repository is generated by analyzing a plurality of online posts.

10. The system of claim 7 , wherein the deviation between the online behavior profile and the baseline online behavior profile is detected based on a change in at least one data parameter from a plurality of data parameters from the online behavior profile.

11. The system of claim 10 , the online behavior profile comprising a sentiment analysis, and an average frequency of usage of the social network by the user.

12. The system of claim 7 , wherein the method further comprises generating content specifically for the user based on the event.

13. A computer program product comprising a computer readable storage medium having stored thereon program instructions executable by one or more processing devices to perform a method comprising:

creating a baseline online behavior profile of a user at a time t 1 based on a usage of a social network by the user;

continuously monitoring an online behavior profile of the user on the social network;

in response to detecting a deviation between the online behavior profile and the baseline online behavior profile, creating a changed online behavior profile of the user at a time t 2 , t 2 >t 1 ;

extracting keywords from a plurality of online posts associated with the user, the online posts being from time t 1 until time t 2 ;

determining an event associated with the extracted keywords;

determining a confidence level for the event as cause of the deviation between the online behavior profile and the baseline online behavior profile by comparing the event with a measurement of stress level of the user from one or more activity monitoring devices of the user, where the confidence level is based on the stress level being within a predetermined range that is associated with the event;

in response to the confidence level being below a predetermined threshold, corroborating an occurrence of the event that is determined by receiving a verification from a second user, wherein the second user verifies that the event occurred via an electronic confirmation; and

in response to the corroboration from the second user, and in response to the event being of a predetermined type, sending a notification to a designated caretaker of the user.

14. The computer program product of claim 13 , wherein the event is detected by correlating the extracted keywords with a taxonomy repository of keywords and events, the taxonomy repository is generated by analyzing a plurality of online posts.

15. The computer program product of claim 13 , wherein the deviation between the online behavior profile and the baseline online behavior profile is detected based on a change in at least one data parameter from a plurality of data parameters from the online behavior profile.

16. The computer program product of claim 15 , the online behavior profile comprising a sentiment analysis, and an average frequency of usage of the social network by the user.

17. The computer program product of claim 13 , the method further comprising generating content specifically for the user based on the event.