Cognitive determination of message suitability
Cognitive determination of whether a message is suitable for sending over a data communications network can include extracting tokens from the message prior to transmitting the message. One or more intended recipients of the message can be determined from the tokens. A machine learning classification model corresponding to the one or more recipients of the message can be selected. The machine learning classification model can be constructed based on tokens extracted from prior messages, which are combined to create a plurality of documents for training the machine learning classification model. The one or more tokens extracted from the message can be classified using the machine learning classification model. An alert message can be generated in response to determining based on the classifying that the message is unsuited for sending.
1. A method, comprising:
extracting, with computer hardware, tokens from a message prior to transmitting the message over a communications network;
determining from the tokens one or more intended recipients of the message;
selecting a machine learning classification model corresponding to the one or more recipients of the message, the machine learning classification model constructed based on tokens extracted from prior messages, the prior messages being combined to create a plurality of documents for training the machine learning classification model;
classifying one or more tokens extracted from the message using the machine learning classification model; and
generating an alert message in response to determining based on the classifying that the message is unsuited for sending.
2. The method of claim 1 , wherein
the machine learning classification model is a probabilistic topic model that statistically predicts at least one topic for characterizing language content of the plurality of documents.
3. The method of claim 2 , wherein
the probabilistic topic model is an augmented latent Dirichlet allocation model augmented based on a group relationship graph.
4. The method of claim 1 , wherein
different ones of the plurality of documents are individually created at periodic intervals over a predetermined time period.
5. The method of claim 1 , wherein
at least one of the message or prior messages comprises a text string generated in response to identifying an object within an image using machine learning image recognition.
6. The method of claim 5 , wherein
the image recognition is performed by an enhanced neural net image caption generator.
7. The method of claim 1 , wherein
at least one of the message or prior messages comprises a text string that is generated by converting a voice-based message to text using a speech-to-text processor.
8. A system, comprising:
a hardware processor configured to initiate operations including:
extracting tokens from a message prior to transmitting the message over a communications network;
determining from the tokens one or more intended recipients of the message;
selecting a machine learning classification model corresponding to the one or more recipients of the message, the machine learning classification model constructed based on tokens extracted from prior messages, the prior messages being combined to create a plurality of documents for training the machine learning classification model;
classifying one or more tokens extracted from the message using the machine learning classification model; and
generating an alert message in response to determining based on the classifying that the message is unsuited for sending.
9. The system of claim 8 , wherein
the machine learning classification model is a probabilistic topic model that statistically predicts at least one topic for characterizing language content of the plurality of documents.
10. The system of claim 9 , wherein
the probabilistic topic model is an augmented latent Dirichlet allocation model augmented based on a group relationship graph.
11. The system of claim 8 , wherein
different ones of the plurality of documents are individually created at periodic intervals over a predetermined time period.
12. The system of claim 8 , wherein
at least one of the message or prior messages comprises a text string generated in response to identifying an object within an image using machine learning image recognition.
13. The system of claim 12 , wherein
the image recognition is performed by an enhanced neural net image caption generator.
14. A computer program product, the computer program product comprising:
one or more computer-readable storage media and program instructions collectively stored on the one or more computer-readable storage media, the program instructions executable by a processor to cause the processor to initiate operations including:
extracting tokens from a message prior to transmitting the message over a communications network;
determining from the tokens one or more intended recipients of the message;
selecting a machine learning classification model corresponding to the one or more recipients of the message, the machine learning classification model constructed based on tokens extracted from prior messages, the prior messages being combined to create a plurality of documents for training the machine learning classification model;
classifying one or more tokens extracted from the message using the machine learning classification model; and
generating an alert message in response to determining based on the classifying that the message is unsuited for sending.
15. The computer program product of claim 14 , wherein
the machine learning classification model is a probabilistic topic model that statistically predicts at least one topic for characterizing language content of the plurality of documents.
16. The computer program product of claim 15 , wherein
the probabilistic topic model is an augmented latent Dirichlet allocation model augmented based on a group relationship graph.
17. The computer program product of claim 14 , wherein
different ones of the plurality of documents are individually created at periodic intervals over a predetermined time period.
18. The computer program product of claim 14 , wherein
at least one of the message or prior messages comprises a text string generated in response to identifying an object within an image using machine learning image recognition.
19. The computer program product of claim 18 , wherein
the image recognition is performed by an enhanced neural net image caption generator.
20. The computer program product of claim 14 , wherein
at least one of the message or prior messages comprises a text string that is generated by converting a voice-based message to text using a speech-to-text processor.