Augmented conversational agent

An apparatus, comprising:

• at least one processor;
• and
• a computer readable storage medium having computer readable program code embodied therewith and executable by the at least one processor, the computer readable program code comprising:
• computer readable program code that receives, at a conversation agent, text-based input from a user and beginning a text-based conversation between the user and the conversation agent, wherein the conversation agent comprises an interactive virtual agent that communicates with the user using a text-based communication method;
• computer readable program code that captures at least one facial image of the user and analyzing the facial image to extract eye gaze information and facial expressions of the user;
• computer readable program code that identifies, within the text based conversation between the conversation agent and the user, a concept of interest to the user, wherein the identifying comprises analyzing the eye gaze information to identify a position within the text-based conversation and determining the concept corresponding to the position within the text-based conversation;
• computer readable program code that determines an emotion of the user in relation to the concept of interest, wherein the determining an emotion comprises analyzing the facial expressions of the user;
• and
• computer readable program code that provides, from the conversation agent, a text-based response to the user, wherein the text-based response is formulated in view of the determined emotion and the identified concept of interest.

A computer program product, comprising:

• a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code executable by a processor and comprising:
• computer readable program code that receives, at a conversation agent, text-based input from a user and beginning a text-based conversation between the user and the conversation agent, wherein the conversation agent comprises an interactive virtual agent that communicates with the user using a text-based communication method;
• computer readable program code that captures at least one facial image of the user and analyzing the facial image to extract eye gaze information and facial expressions of the user;
• computer readable program code that identifies, within the text based conversation between the conversation agent and the user, a concept of interest to the user, wherein the identifying comprises analyzing the eye gaze information to identify a position within the text-based conversation and determining the concept corresponding to the position within the text-based conversation;
• computer readable program code that determines an emotion of the user in relation to the concept of interest, wherein the determining an emotion comprises analyzing the facial expressions of the user;
• and
• computer readable program code that provides, from the conversation agent, a text-based response to the user, wherein the text-based response is formulated in view of the determined emotion and the identified concept of interest.

A method, comprising:

• utilizing at least one processor to execute computer code that performs the steps of:
• initiating, upon receipt of input by a user, text-based conversational session between an interactive virtual agent and the user, wherein the interactive virtual agent communicates with the user using a text-based communication method;
• determining a facial expression of the user by capturing, using at least one image capture device, at least one facial image of the user;
• identifying, within the text based dialog between the virtual agent and the user, a portion of the dialog of interest to the user, wherein the identifying comprises accessing eye gaze information contained within the at least one image and identifying a location within the text based dialog corresponding to a position of the gaze of the user;
• determining an emotion of the user in relation to the portion of the dialog of interest, wherein the determining an emotion comprises comparing the determined facial expression of the user to known facial expressions having a corresponding identified emotion;
• and
• providing, from the virtual agent, a text-based response to the user by correlating the determined emotion to the identified concept of interest and generating a text-based response comprising a text concept corresponding to the identified concept of interest and formulated in view of the determined emotion.