Decoding communications with token sky maps

1. A computer-implemented method comprising:

receiving at least one electronic communication comprising emoticons having a non- original meaning;

determining a candidate meaning for the emoticons having the non-original meaning in the at least one electronic communication, the determining based at least in part on token neighborhood distribution structures, wherein the token neighborhood distribution structures comprise a first topological graph comprising first nodes and a second topological graph comprising second nodes, the first nodes being emoticon tokens as pictorial representations, the second nodes being plaintext tokens as words in plain text; and

causing the candidate meaning for the emoticons having the non-original meaning to be displayed on at least one device.

2. The computer-implemented method of claim 1 , wherein determining the candidate meaning for the emoticons having the non-original meaning in the at least one electronic communication comprises:

finding a match of the emoticons having the non-original meaning with the first nodes in the first topological graph of the token neighborhood distribution structures; and

using an overlap of the first nodes in the first topological graph and the second nodes in a the second topological graph of the token neighborhood distribution structures in order to determine the candidate meaning for the emoticons, the second topological graph comprising plaintext words.

3. The computer-implemented method of claim 1 , wherein the first topological graph and the second topological graph are each an undirected and unweighted topological graph.

4. The computer-implemented method of claim 1 , wherein:

the emoticons having the non-original meaning in the at least one electronic communication correlate to the first nodes in the first topological graph of the token neighborhood distribution structures; and

the first nodes overlap the second nodes in a-the second topological graph of the token neighborhood distribution structures, the second nodes having a plaintext meaning that corresponds to the candidate meaning for the emoticons.

5. The computer-implemented method of claim 1 , wherein the token neighborhood distribution structures comprise a non-original-meaning emoticon topological graph as the first topological graph and a plaintext topological graph as the second topological graph, the candidate meaning for the emoticons being determined based on a similarity between node embeddings of the non-original-meaning emoticon topological graph and the plaintext topological graph.

6. The computer-implemented method of claim 1 , wherein the candidate meaning for the emoticons is rendered in a graphical user interface to decode a representation of the emoticons.

7. A system comprising:

a memory having computer readable instructions; and

one or more processors for executing the computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising:

receiving at least one electronic communication comprising emoticons having a non-original meaning;

determining a candidate meaning for the emoticons having the non-original meaning in the at least one electronic communication, the determining based at least in part on token neighborhood distribution structures, wherein the token neighborhood distribution structures comprise a first topological graph comprising first nodes and a second topological graph comprising second nodes, the first nodes being emoticon tokens as pictorial representations, the second nodes being plaintext tokens as words in plain text; and

causing the candidate meaning for the emoticons having the non-original meaning to be displayed on at least one device.

8. The system of claim 7 , wherein determining the candidate meaning for the emoticons having the non-original meaning in the at least one electronic communication comprises:

finding a match of the emoticons having the non-original meaning with the first nodes in the first topological graph of the token neighborhood distribution structures; and

using an overlap of the first nodes in the first topological graph and the second nodes in a the second topological graph of the token neighborhood distribution structures in order to determine the candidate meaning for the emoticons, the second topological graph comprising plaintext words.

9. The system of claim 7 , wherein the first topological graph and the second topological graph are each an undirected and unweighted topological graph.

10. The system of claim 7 , wherein:

the emoticons having the non-original meaning in the at least one electronic communication correlate to the first nodes in a-the first topological graph of the token neighborhood distribution structures; and

the first nodes overlap the second nodes in a second topological graph of the token neighborhood distribution structures, the second nodes having a plaintext meaning that corresponds to the candidate meaning for the emoticons.

11. The system of claim 7 , wherein the token neighborhood distribution structures comprise a non-original-meaning emoticon topological graph as the first topological graph and a plaintext topological graph as the second topological graph, the candidate meaning for the emoticons being determined based on a similarity between node embeddings of the non-original-meaning emoticon topological graph and the plaintext topological graph.

12. The system of claim 7 , wherein the candidate meaning for the emoticons is rendered in a graphical user interface to decode a representation of the emoticons.

13. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by one or more processors to cause the one or more processors to perform operations comprising:

receiving at least one electronic communication comprising emoticons having a non-original meaning;

determining a candidate meaning for the emoticons having the non-original meaning in the at least one electronic communication, the determining based at least in part on token neighborhood distribution structures, wherein the token neighborhood distribution structures comprise a first topological graph comprising first nodes and a second topological graph comprising second nodes, the first nodes being emoticon tokens as pictorial representations, the second nodes being plaintext tokens as words in plain text; and

causing the candidate meaning for the emoticons having the non-original meaning to be displayed on at least one device.

14. The computer program product of claim 13 , wherein determining the candidate meaning for the emoticons having the non-original meaning in the at least one electronic communication comprises:

finding a match of the emoticons having the non-original meaning with the first nodes in the first topological graph of the token neighborhood distribution structures; and

using an overlap of the first nodes in the first topological graph and the second nodes in a second topological graph of the token neighborhood distribution structures in order to determine the candidate meaning for the emoticons, the second topological graph comprising plaintext words.

15. The computer program product of claim 13 , the first topological graph and the second topological graph are each an undirected and unweighted topological graph.

16. The computer program product of claim 13 , wherein:

the emoticons having the non-original meaning in the at least one electronic communication correlate to the first nodes in the first topological graph of the token neighborhood distribution structures; and

the first nodes overlap the second nodes in a second topological graph of the token neighborhood distribution structures, the second nodes having a plaintext meaning that corresponds to the candidate meaning for the emoticons.

17. The computer program product of claim 13 , wherein the token neighborhood distribution structures comprise a non-original-meaning emoticon topological graph as the first topological graph and a plaintext topological graph as the second topological graph, the candidate meaning for the emoticons being determined based on a similarity between node embeddings of the non-original-meaning emoticon topological graph and the plaintext topological graph.