AI driven content correction built on personas
A machine learning (ML) module that analyzes multiple language-influencing factors to correct textual content in a more meaningful and efficient manner. In the context of product support, the ML module considers the factors such as a customer's persona that shapes the words a customer chooses while speaking/writing to a customer support agent, current social trends that create new words in the social media/social platforms related to the customer's support issue, and the device used by the customer to input the textual content because different words may be input by the customer when using a smart phone versus a desktop/laptop personal computer with a traditional keyboard. The ML module also may analyze the agent's persona to modify agent's response to the customer because the agent's persona can influence the content of the agent's text. The ML module automatically corrects textual content in real-time before it is sent to the relevant recipient.
1. A method comprising:
receiving, by a computing system, a first textual content sent by a first communicator for delivery to a second communicator;
determining, by the computing system using a machine learning (ML) module, a set of language-influencing factors affecting the first textual content sent by the first communicator, wherein the set of language-influencing factors comprises:
a first persona that reflects first communicator-specific individual characteristics shaping the first textual content generated by the first communicator,
an information available in social media related to the first textual content, and
a set of device properties specific to a device being used by the first communicator for sending the first textual content;
modifying, by the computing system using the ML module, the first textual content based on the set of language-influencing factors to generate a modified first textual content; and
sending, by the computing system, the modified first textual content to the second communicator instead of the first textual content.
2. The method of claim 1 , wherein modifying the first textual content comprises:
determining, by the computing system using the ML module, a second persona that reflects second communicator-specific individual characteristics shaping communication preferences of the second communicator; and
modifying, by the computing system using the ML module, the first textual content based on the set of language-influencing factors as well as the second persona to generate the modified first textual content.
3. The method of claim 2 , wherein the second persona comprises at least one of the following:
a personal identifier assigned to the second communicator;
a job profile associated with the second communicator;
a first score reflecting a subject matter expertise level of the second communicator;
a second score reflecting a typing level of the second communicator;
a third score reflecting prior performance history of the second communicator; and
a value identifying a level of prior communication between the first communicator and the second communicator.
4. The method of claim 1 , further comprising:
analyzing, by the computing system using the ML module, the set of language-influencing factors to determine a context of discussion relevant to the first textual content;
wherein sending the modified first textual content comprises:
sending, by the computing system, the modified first textual content along with the context of discussion to the second communicator.
5. The method of claim 1 , further comprising:
receiving, by the computing system, a second textual content sent by the second communicator for delivery to the first communicator;
modifying, by the computing system using the ML module, the second textual content based on the first persona and the set of device properties to generate a modified second textual content; and
sending, by the computing system, the modified second textual content to the first communicator instead of the second textual content.
6. The method of claim 5 , wherein one of the following applies:
the first textual content is an online search query and the second textual content is a search result generated in response to processing of the modified first textual content; and
the first textual content is an online chat message and the second textual content is an online chat response to the modified first textual content.
7. The method of claim 1 , wherein the first communicator is one of the following:
a human user requesting user-specific information from a corporate entity; and
a human operator associated with the corporate entity to provide customer support.
8. The method of claim 1 , wherein the second communicator is one of the following:
a human user requesting user-specific information from a corporate entity;
a human operator associated with the corporate entity to provide customer support; and
an online search facility deployed by the corporate entity to provide customer support.
9. The method of claim 1 , wherein the information available in social media comprises comments and discussion in social media tied to a line of business of a corporate entity related to the first textual content.
10. The method of claim 1 , wherein the first persona comprises at least one of the following:
an online browsing pattern of the first communicator prior to sending the first textual content;
an online search history of database searches performed by the first communicator prior to sending the first textual content;
a respective timestamp value for each database search in the online search history;
a customer profile associated with the first communicator;
a record of website pages visited by the first communicator prior to sending the first textual content;
a first history of one or more prior product orders placed by the first communicator with a corporate entity with which the second communicator is associated to provide customer support; and
a second history of one or more prior service orders placed by the first communicator with the corporate entity with which the second communicator is associated to provide customer support.
11. The method of claim 1 , wherein the set of device properties comprises at least one of the following:
a type of the device;
a brand of the device;
a device ID of the device;
physical dimensions of the device;
physical dimensions of a display screen of the device; and
an operating system of the device.
12. The method of claim 1 , further comprising:
analyzing, by the computing system using the ML module, the first textual content in view of the set of language-influencing factors to automatically identify a product support issue for which the first communicator is seeking resolution; and
providing, by the computing system using the ML module, details of the product support issue along with the modified first textual content to the second communicator.
13. A computing system comprising:
a memory storing program instructions; and
a processing unit coupled to the memory and operable to execute the program instructions, which, when executed by the processing unit, cause the computing system to:
receive a first textual content sent by a first communicator for delivery to a second communicator;
determine, using a machine learning (ML) module, a set of language-influencing factors affecting the first textual content sent by the first communicator, wherein the set of language-influencing factors comprises:
a first persona that reflects first communicator-specific individual characteristics shaping the first textual content generated by the first communicator,
an information available in social media related to the first textual content, and
a set of device properties specific to a device being used by the first communicator for sending the first textual content;
modify, using the ML module, the first textual content based on the set of language-influencing factors to generate a modified first textual content; and
send the modified first textual content to the second communicator instead of the first textual content.
14. The computing system of claim 13 , wherein the program instructions, upon execution by the processing unit, cause the computing system to further perform the following to generate the modified first textual content:
determine, using the ML module, a second persona that reflects second communicator-specific individual characteristics shaping communication preferences of the second communicator; and
modify, using the ML module, the first textual content based on the set of language-influencing factors as well as the second persona to generate the modified first textual content; and
wherein the program instructions, upon execution by the processing unit, cause the computing system to:
receive a second textual content sent by the second communicator for delivery to the first communicator;
modify, using the ML module, the second textual content based on the first persona and the set of device properties to generate a modified second textual content; and
send the modified second textual content to the first communicator instead of the second textual content.
15. The computing system of claim 14 , wherein one of the following applies:
the first textual content is an online search query and the second textual content is a search result generated in response to processing of the modified first textual content; and
the first textual content is an online chat message and the second textual content is an online chat response to the modified first textual content.
16. The computing system of claim 13 , wherein the first persona comprises at least one of the following:
an online browsing pattern of the first communicator prior to sending the first textual content;
an online search history of database searches performed by the first communicator prior to sending the first textual content;
a respective timestamp value for each database search in the online search history;
a customer profile associated with the first communicator;
a record of website pages visited by the first communicator prior to sending the first textual content;
a first history of one or more prior product orders placed by the first communicator with a corporate entity with which the second communicator is associated to provide customer support; and
a second history of one or more prior service orders placed by the first communicator with the corporate entity with which the second communicator is associated to provide customer support; and
wherein the set of device properties comprises at least one of:
a type of the device;
a brand of the device;
a device ID of the device;
physical dimensions of the device;
physical dimensions of a display screen of the device; and
an operating system of the device.
17. A computer program product comprising a non-transitory computer-usable medium having computer-readable program code embodied therein, the computer-readable program code adapted to be executed by a computing system to implement a method comprising:
receiving a first textual content sent by a first communicator for delivery to a second communicator;
determining, using a machine learning (ML) module, a set of language-influencing factors affecting the first textual content sent by the first communicator, wherein the set of language-influencing factors comprises:
a first persona that reflects first communicator-specific individual characteristics shaping the first textual content generated by the first communicator,
an information available in social media related to the first textual content, and
a set of device properties specific to a device being used by the first communicator for sending the first textual content;
modifying, using the ML module, the first textual content based on the set of language-influencing factors to generate a modified first textual content; and
sending the modified first textual content to the second communicator instead of the first textual content.
18. The computer program product of claim 17 , wherein modifying the first textual content comprises:
determining, using the ML module, a second persona that reflects second communicator-specific individual characteristics shaping communication preferences of the second communicator; and
modifying, using the ML module, the first textual content based on the set of language-influencing factors as well as the second persona to generate the modified first textual content; and
wherein the method further comprises:
receiving a second textual content sent by the second communicator for delivery to the first communicator;
modifying, using the ML module, the second textual content based on the first persona and the set of device properties to generate a modified second textual content; and
sending the modified second textual content to the first communicator instead of the second textual content.
19. The computer program product of claim 18 , wherein one of the following applies:
the first textual content is an online search query and the second textual content is a search result generated in response to processing of the modified first textual content; and
the first textual content is an online chat message and the second textual content is an online chat response to the modified first textual content.
20. The computer program product of claim 17 , wherein the first persona comprises at least one of the following:
an online browsing pattern of the first communicator prior to sending the first textual content;
an online search history of database searches performed by the first communicator prior to sending the first textual content;
a respective timestamp value for each database search in the online search history;
a customer profile associated with the first communicator;
a record of website pages visited by the first communicator prior to sending the first textual content;
a first history of one or more prior product orders placed by the first communicator with a corporate entity with which the second communicator is associated to provide customer support; and
a second history of one or more prior service orders placed by the first communicator with the corporate entity with which the second communicator is associated to provide customer support; and
wherein the set of device properties comprises at least one of the following:
a type of the device;
a brand of the device;
a device ID of the device;
physical dimensions of the device;
physical dimensions of a display screen of the device; and
an operating system of the device.