Context-based personalized communication presentation
A method, system, and computer program product for generating context-based tailored emoticons within a communication scenario are provided. The method receives detects an emotion of a user within a communication stream. A set of candidate emojis are generated. A set of emoticons are generated from the set of candidate emojis and a representation of the user. The set of emoticons are presented to the user in a user interface on a computing device associated with the user. The method incorporates a selected emoticon of the set of emoticons into the communication stream with the selected emoticon being selected by the user from the user interface.
1. A computer-implemented method, comprising:
detecting an emotion of a user within a communication stream;
generating a set of candidate emojis for the emotion based in part on a set of historic emojis previously selected by the user that correspond to the emotion, wherein the user's past observed patterns of selecting emojis related to the emotion determine the set of historic emojis;
generating a set of emoticons from the set of candidate emojis and a representation of the user;
presenting the set of emoticons to the user in a user interface on a computing device associated with the user; and
incorporating a selected emoticon of the set of emoticons into the communication stream, the selected emoticon selected by the user from the user interface.
2. The method of claim 1 , wherein detecting the emotion of the user further comprises:
identifying a set of image features from the communication stream;
identifying a set of text features from the communication stream;
identifying a set of audio features from the communication stream; and
detecting the emotion of the user within the communication stream based on the set of image features and the set of text features.
3. The method of claim 2 , wherein detecting the emotion of the user further comprises:
performing image recognition of the user in a video portion of the communication stream; and
identifying the set of image features for the user based on the image recognition, the image features representing at least a portion of an emotional context for the user.
4. The method of claim 2 , wherein detecting the emotion of the user further comprises:
performing natural language processing on a text portion of the communication stream;
performing natural language processing on a text history of the user; and
identifying the set of text features based on the text portion of the communication stream and the text history of the user, the text features representing at least a portion of an emotional context of the user.
5. The method of claim 2 , wherein generating the set of candidate emojis further comprises:
embedding the set of image features, the set of text features, and the set of audio features into a vector.
6. The method of claim 5 , wherein the set of emoticons are generated by a generative adversarial network using the vector and the set of candidate emojis.
7. The method of claim 3 , wherein detecting the emotion of the user further comprises:
obtaining an interactive pattern history associated with the user by combining a current motion map generated from the communication stream with historical motion maps associated with the user; and
determining emotional context of the user, based in part, on the interactive pattern history.
8. A system, comprising:
one or more processors; and
a computer-readable storage medium, coupled to the one or more processors, storing program instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
detecting an emotion of a user within a communication stream;
generating a set of candidate emojis for the emotion based in part on a set of historic emojis previously selected by the user that correspond to the emotion, wherein the user's past observed patterns of selecting emojis related to the emotion determine the set of historic emojis;
generating a set of emoticons from the set of candidate emojis and a representation of the user;
presenting the set of emoticons to the user in a user interface on a computing device associated with the user; and
incorporating a selected emoticon of the set of emoticons into the communication stream, the selected emoticon selected by the user from the user interface.
9. The system of claim 8 , wherein detecting the emotion of the user further comprises:
identifying a set of image features from the communication stream;
identifying a set of text features from the communication stream;
identifying a set of audio features from the communication stream; and
detecting the emotion of the user within the communication stream based on the set of image features and the set of text features.
10. The system of claim 9 , wherein detecting the emotion of the user further comprises:
performing image recognition of the user in a video portion of the communication stream; and
identifying the set of image features for the user based on the image recognition, the image features representing at least a portion of an emotional context for the user.
11. The system of claim 9 , wherein detecting the emotion of the user further comprises:
performing natural language processing on a text portion of the communication stream;
performing natural language processing on a text history of the user; and
identifying the set of text features based on the text portion of the communication stream and the text history of the user, the text features representing at least a portion of an emotional context of the user.
12. The system of claim 9 , wherein generating the set of candidate emojis further comprises:
embedding the set of image features, the set of text features, and the set of audio features into a vector.
13. The system of claim 12 , wherein the set of emoticons are generated by a generative adversarial network using the vector and the set of candidate emojis.
14. The system of claim 10 , wherein detecting the emotion of the user further comprises:
obtaining an interactive pattern history associated with the user by combining a current motion map generated from the communication stream with historical motion maps associated with the user; and
determining emotional context of the user, based in part, on the interactive pattern history.
15. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions being executable by one or more processors to cause the one or more processors to perform operations comprising:
detecting an emotion of a user within a communication stream;
generating a set of candidate emojis for the emotion based in part on a set of historic emojis previously selected by the user that correspond to the emotion, wherein the user's past observed patterns of selecting emojis related to the emotion determine the set of historic emojis;
generating a set of emoticons from the set of candidate emojis and a representation of the user;
presenting the set of emoticons to the user in a user interface on a computing device associated with the user; and
incorporating a selected emoticon of the set of emoticons into the communication stream, the selected emoticon selected by the user from the user interface.
16. The computer program product of claim 15 , wherein detecting the emotion of the user further comprises:
identifying a set of image features from the communication stream;
identifying a set of text features from the communication stream;
identifying a set of audio features from the communication stream; and
detecting the emotion of the user within the communication stream based on the set of image features and the set of text features.
17. The computer program product of claim 16 , wherein detecting the emotion of the user further comprises:
performing image recognition of the user in a video portion of the communication stream; and
identifying the set of image features for the user based on the image recognition, the image features representing at least a portion of an emotional context for the user.
18. The computer program product of claim 16 , wherein detecting the emotion of the user further comprises:
performing natural language processing on a text portion of the communication stream;
performing natural language processing on a text history of the user; and
identifying the set of text features based on the text portion of the communication stream and the text history of the user, the text features representing at least a portion of an emotional context of the user.
19. The computer program product of claim 16 , wherein generating the set of candidate emojis further comprises:
embedding the set of image features, the set of text features, and the set of audio features into a vector; and
generating the set of emoticons by a generative adversarial network using the vector and the set of candidate emojis.
20. The computer program product of claim 17 , wherein detecting the emotion of the user further comprises:
obtaining an interactive pattern history associated with the user by combining a current motion map generated from the communication stream with historical motion maps associated with the user; and
determining emotional context of the user, based in part, on the interactive pattern history.