Automated conversational response generation
Systems, computer-implemented methods, and/or computer program products facilitating a process to identify and respond to a primary electronic message are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can include a determination component can determine that a primary electronic message has not received a response electronic message. An analysis component can generate a generated electronic message addressing the informational or emotional content of the primary electronic message. In one or more embodiments, an updating component can update the analytical model based on one or more feedbacks to the generated electronic message, where the analytical model can remain active while being updated. The one or more feedbacks can comprise a feedback from an entity-in-the-loop monitoring outputs of the analytical model including the generated electronic message.
1. A system, comprising:
a memory that stores computer executable components; and
a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise:
a determination component that determines that a primary electronic message has not received a response electronic message;
an analysis component that generates a generated electronic message addressing the informational or emotional content of the primary electronic message; and
a classification component that selects between two different types of messages, wherein the two different types of messages between which the classification component selects are emotional support seeking messages and informational support seeking messages and wherein the classification component classifies the primary electronic message as one of the two types of messages based on the selection by the classification component of the primary electronic message being one of the two types and not the other of the two types.
2. The system of claim 1 ,
wherein the analysis component further applies an analytical model to the primary electronic message to analyze content of the primary electronic message.
3. The system of claim 1 ,
wherein the determination component further labels the primary electronic message as an overlooked message based on the determination; and
wherein the analysis component performs the analysis of the primary electronic message based on the label of the primary electronic message as an overlooked message.
4. The system of claim 1 , wherein the computer executable components further comprise:
an updating component that updates the analytical model based on one or more feedbacks to the generated electronic message, wherein the analytical model remains active while being updated.
5. The system of claim 4 ,
wherein the one or more feedbacks comprise a feedback from an entity-in-the-loop monitoring outputs of the analytical model including the generated electronic message.
6. The system of claim 4 ,
wherein the one or more feedbacks comprise a response electronic message posted, or uploaded, subsequent to the determination by the determination component.
7. A computer-implemented method, comprising:
determining, by a system operatively coupled to a processor, that a primary electronic message has not received a response electronic message;
generating, by the system, a generated electronic message addressing the informational or emotional content of the primary electronic message;
selecting, by the system, between two different types of messages, wherein the two different types of messages between which the selection is performed are emotional support seeking messages and informational support seeking messages; and
classifying, by the system, the primary electronic message as either an emotional support seeking message and not an informational support seeking message or an informational support seeking message and not an emotional support seeking message.
8. The computer-implemented method of claim 7 , further comprising:
applying, by the system, an analytical model to the primary electronic message to analyze content of the primary electronic message.
9. The computer-implemented method of claim 7 , further comprising:
labeling, by the system, the primary electronic message as an overlooked message based on the determination; and
performing, by the system, the analysis of the primary electronic message based on the label of the primary electronic message as an overlooked message.
10. The computer-implemented method of claim 7 , further comprising:
updating, by the system, the analytical model based on one or more feedbacks to the generated electronic message, wherein the analytical model remains active while being updated.
11. The computer-implemented method of claim 10 , wherein the one or more feedbacks comprise a feedback from an entity-in-the-loop monitoring outputs of the analytical model including the generated electronic message.
12. The computer-implemented method of claim 10 , wherein the one or more feedbacks comprise a response electronic message posted, or uploaded, subsequent to the determination by the determination component.
13. A computer program product facilitating a process to identify and respond to a primary electronic message, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
determine, by the processor, that a primary electronic message has not received a response electronic message;
generate, by the processor, a generated electronic message addressing the informational or emotional content of the primary electronic message;
select, by the processor, between two different types of messages, wherein the two different types of messages between which the selection is performed are emotional support seeking messages and informational support seeking messages; and
classify, by the processor, the primary electronic message as either an emotional support seeking message and not an informational support seeking message or an informational support seeking message and not an emotional support seeking message.
14. The computer program product of claim 13 , wherein the program instructions are further executable by the processor to:
apply, by the processor, an analytical model to the primary electronic message to analyze content of the primary electronic message.
15. The computer program product of claim 13 , wherein the program instructions are further executable by the processor to:
labeling, by the processor, the primary electronic message as an overlooked message based on the determination; and
perform, by the processor, the analysis of the primary electronic message based on the label of the primary electronic message as an overlooked message.
16. The computer program product of claim 13 ,
update, by the processor, the analytical model based on one or more feedbacks to the generated electronic message, wherein the analytical model remains active while being updated.
17. The computer program product of claim 16 , wherein the one or more feedbacks comprise a feedback from an entity-int-the-loop monitoring outputs of the analytical model including the generated electronic message.
18. The computer program product of claim 16 , wherein the one or more feedbacks comprise a response electronic message posted, or uploaded, subsequent to the determination by the determination component.
19. A system, comprising:
a memory that stores computer executable components; and
a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise:
a determination component that determines that a primary electronic message has not received a response electronic message;
an analysis component that generates a generated electronic message addressing the content of the primary electronic message; and
a monitoring component that enables entity-in-the-loop feedback to the generated electronic message, wherein the entity-in-the-loop feedback results causes a denial of the generated electronic message.
20. The system of claim 19 , wherein the computer executable components further comprise:
an updating component that updates an analytical model in response to the entity-in-the-loop feedback, wherein the analytical model remains active while being updated.
21. A system, comprising:
a memory that stores computer executable components; and
a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise:
a determination component that determines that a primary electronic message has not received a response message; and
an updating component that updates an analytical model at least partially in response to entity-in-the-loop feedback applied to a generated electronic message in response to the primary electronic message, wherein the updating component further updates the analytical model at least partially in response to a response electronic message uploaded subsequent to the determination by the determination component.