System, method and computer product for classifying user expertise
A user expertise classifying method, system, and computer program product, include analyzing an input by a user based on at least one of vocabulary, orthography, and grammar of the user input, processing user background data obtained from a database, and calculating an expertise score of the user based on the analyzed user input and the processed background data.
1. A computer-implemented method for classifying user expertise, the method comprising:
receiving a user input related to a specific topical domain, the user input received via a chat interface as part of a chat session between a user and a chat bot;
calculating an expertise score of the user for the specific topical domain based on an analysis of the user input and background data associated with the user;
adjusting performance of the chat bot for the specific topical domain based on the expertise score of the user, the chat bot generating and presenting a response to the user input in the chat session based on the expertise score;
receiving a second user input from the user via the chat interface;
updating the expertise score of the user for the specific topical domain based on an interval of time between presenting the response to the user and receiving the second user input, yielding an updated expertise score; and
displaying, via a Graphical User Interface (GUI), a pop-up with the updated expertise score.
2. A computer program product for user expertise classifying, the computer program product comprising a computer-readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform:
receiving a user input related to a specific topical domain, the user input received via a chat interface as part of a chat session between a user and a chat bot;
calculating an expertise score of the user for the specific topical domain based on an analysis of the user input and background data associated with the user;
adjusting performance of the chat bot for the specific topical domain based on the expertise score of the user, the chat bot generating and presenting a response to the user input in the chat session based on the expertise score;
receiving a second user input from the user via the chat interface;
updating the expertise score of the user for the specific topical domain based on an interval of time between presenting the response to the user and receiving the second user input, yielding an updated expertise score; and
displaying, via a Graphical User Interface (GUI), a pop-up with the updated expertise score.
3. A user expertise classifying system, said system comprising:
a processor; and
a memory, the memory storing instructions to cause the processor to:
receiving a user input related to a specific topical domain, the user input received via a chat interface as part of a chat session between a user and a chat bot;
calculating an expertise score of the user for the specific topical domain based on an analysis of the user input and background data associated with the user;
adjusting performance of the chat bot for the specific topical domain based on the expertise score of the user, the chat bot generating and presenting a response to the user input in the chat session based on the expertise score;
receiving a second user input from the user via the chat interface;
updating the expertise score of the user for the specific topical domain based on an interval of time between presenting the response to the user and receiving the second user input, yielding an updated expertise score; and
displaying, via a Graphical User Interface (GUI), a pop-up with the updated expertise score.
4. The computer-implemented user expertise classifying method of claim 1 , wherein the calculating repeats the calculating for a second expertise score for a second specific topical domain when the chat bot is for the second specific topical domain.
5. The computer-implemented user expertise classifying method of claim 1 , further comprising increasing the expertise score of the user in a subsequent user input if an amount of time between the user input and the subsequent user input is less than a predetermined threshold time.
6. The computer-implemented user expertise classifying method of claim 1 , wherein the chat bot comprises a conversational artificial intelligence agent.
7. The computer-implemented method of claim 1 , wherein the expertise score indicates a knowledge level of the user in the specific topical domain of the input.
8. The computer-implemented method of claim 1 , wherein the expertise score comprises a plurality of predetermined levels of expertise, and
wherein the calculating determines a level of the predetermined levels of expertise in which the user can understand an answer to the input according to the expertise score of the user being higher than a base amount for the level of the predetermined levels.
9. The computer-implemented method of claim 1 , wherein the input by the user comprises a query to a question-and-answer system.
10. The computer-implemented method of claim 1 , wherein the background data is selected from a group consisting of:
social media data;
a biography of the user;
wearable data; and
educational data.
11. The computer-implemented method of claim 1 , further comprising refining the expertise score based on historical data about the user, the historical data being selected from a group consisting of:
a shopping history of the user;
a search history of the user;
a list of presentations by the user; and
a list of publications by the user.
12. The computer-implemented method of claim 1 , further comprising assigning a weight to each item of the background data based on a recency of the item of the background data.
13. The computer-implemented method of claim 1 , further comprising adjusting the expertise score according to a feedback by the user indicating an understanding of a response by the chat bot based on the expertise score.
14. The computer-implemented method of claim 1 , embodied in a cloud-computing environment.
15. The computer-implemented method of claim 1 , wherein the chat bot produces a combination of a display response and an audio response based on the expertise score.
16. The computer-implemented user expertise classifying method of claim 1 , wherein the GUI includes a configurable interface to adjust the calculated expertise score.