Emoji disambiguation for online interactions

1. A method comprising:

constructing a new data structure of a social clustered topic model comprising new data, the new data being generated from content of online interactions using a processor and a memory;

analyzing, using a processor and a memory, a social media message to compute an emoji probability score reflecting a degree of correspondence between an emoji present in the social media message and a meaning extracted from the new social clustered topic model; and

modifying the social media message automatically, when the emoji probability score is above a threshold probability score, by adding additional data to the social media message, the additional data comprising the meaning.

2. The method of claim 1 , wherein constructing the new data structure of the social clustered topic model comprises:

determining, from content of online interactions, a topic corresponding to the content and a topic probability score reflecting a degree of correspondence between the topic and the content;

associating an emoji present in the content with the topic and the probability score;

constructing, from online interactions, a relationship model representing a relationship between a source user of an interaction and a destination user of the interaction; and

constructing, from the topic, the topic probability score, the emoji association, and the relationship model, the social clustered topic model.

3. The method of claim 2 , wherein the relationship model comprises a social graph.

4. The method of claim 2 , wherein analyzing the social media message further comprises:

determining, from the social media message, a message topic corresponding to the message and a message topic probability score reflecting a degree of correspondence between the topic and the message;

associating an emoji present in the message with the topic and the topic probability score;

determining, from a source user of the message, a destination user of the message, and the relationship model, a relationship between the source user and the destination user; and

computing, using the topic, the topic probability score, the emoji association, the relationship, and the social clustered topic model, the emoji probability score.

5. The method of claim 4 , further comprising:

updating, using the topic, the topic probability score, the emoji association, the relationship, and the emoji probability score, the social clustered topic model.

6. The method of claim 1 , further comprising:

modifying the social media message automatically, when the emoji probability score is above a threshold probability score, by adding additional data to the social media message, the additional data comprising the emoji probability score.

7. The method of claim 1 , further comprising:

modifying the social media message automatically, when a difference between the emoji probability score and a second emoji probability score corresponding to a second meaning of the emoji is below a threshold difference, by adding additional data to the social media message, the additional data comprising the meaning corresponding to the emoji probability score and the second meaning.

8. The method of claim 7 , further comprising:

modifying the social media message automatically by adding additional data, the additional data comprising the emoji probability score and the second emoji probability score.

9. 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 construct a new data structure of a social clustered topic model comprising new data, the new data being generated from content of online interactions using a processor and a memory;

program instructions to analyze, using a processor and a memory, a social media message to compute an emoji probability score reflecting a degree of correspondence between an emoji present in the social media message and a meaning; and

program instructions to modify the social media message automatically, when the emoji probability score is above a threshold probability score, by adding additional data to the social media message, the additional data comprising the meaning.

10. The computer usable program product of claim 9 , wherein program instructions to construct new data structure of the social clustered topic model comprises:

program instructions to determine, from content of online interactions, a topic corresponding to the content and a topic probability score reflecting a degree of correspondence between the topic and the content;

program instructions to associate an emoji present in the content with the topic and the probability score;

program instructions to construct, from online interactions, a relationship model representing a relationship between a source user of an interaction and a destination user of the interaction; and

program instructions to construct, from the topic, the topic probability score, the emoji association, and the relationship model, the social clustered topic model.

11. The computer usable program product of claim 10 , wherein the relationship model comprises a social graph.

12. The computer usable program product of claim 10 , wherein program instructions to analyze the social media message further comprises:

program instructions to determine, from the social media message, a message topic corresponding to the message and a message topic probability score reflecting a degree of correspondence between the topic and the message;

program instructions to associate an emoji present in the message with the topic and the topic probability score;

program instructions to determine, from a source user of the message, a destination user of the message, and the relationship model, a relationship between the source user and the destination user; and

program instructions to compute, using the topic, the topic probability score, the emoji association, the relationship, and the social clustered topic model, the emoji probability score.

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

program instructions to update, using the topic, the topic probability score, the emoji association, the relationship, and the emoji probability score, the social clustered topic model.

14. The computer usable program product of claim 9 , further comprising:

program instructions to modify the social media message automatically, when the emoji probability score is above a threshold probability score, by adding additional data to the social media message, the additional data comprising the emoji probability score.

15. The computer usable program product of claim 9 , further comprising:

program instructions to modify the social media message automatically, when a difference between the emoji probability score and a second emoji probability score corresponding to a second meaning of the emoji is below a threshold difference, by adding additional data to the social media message, the additional data comprising the meaning corresponding to the emoji probability score and the second meaning.

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

program instructions to modifying the social media message automatically by adding additional data, the additional data comprising the emoji probability score and the second emoji probability score.

17. The computer usable program product of claim 9 , 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.

18. The computer usable program product of claim 9 , 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.

19. 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 analyze, from a live streaming of a main content, an already streamed portion of the main content to identify an occurrence of a climactic event in the main content;

program instructions to construct a new data structure of a social clustered topic model comprising new data, the new data being generated from content of online interactions using a processor and a memory;

program instructions to analyze, using a processor and a memory, a social media message to compute an emoji probability score reflecting a degree of correspondence between an emoji present in the social media message and a meaning; and

program instructions to modify the social media message automatically, when the emoji probability score is above a threshold probability score, by adding additional data to the social media message, the additional data comprising the meaning.

20. The system of claim 19 , wherein program instructions to construct new data structure of the social clustered topic model comprises:

program instructions to determine, from content of online interactions, a topic corresponding to the content and a topic probability score reflecting a degree of correspondence between the topic and the content;

program instructions to associate an emoji present in the content with the topic and the probability score;

program instructions to construct, from online interactions, a relationship model representing a relationship between a source user of an interaction and a destination user of the interaction; and

program instructions to construct, from the topic, the topic probability score, the emoji association, and the relationship model, the social clustered topic model.