Abstract: Disclosed are various embodiments for delegated evaluation of a decision tree. A client device receives an expression and a plurality of responses from a second computing device, the expression providing an evaluation of a user input and each of the plurality of responses representing a potential response for the first computing device to provide to the user input. The client device then evaluates the user input with the expression received from the second computing device to determine a user intent. The client device then selects a response to the user intent from the plurality of responses and renders the response within a user interface.

Abstract: Disclosed are various embodiments for delegated evaluation of a decision tree. A client device receives an expression and a plurality of responses from a second computing device, the expression providing an evaluation of a user input and each of the plurality of responses representing a potential response for the first computing device to provide to the user input. The client device then evaluates the user input with the expression received from the second computing device to determine a user intent. The client device then selects a response to the user intent from the plurality of responses and renders the response within a user interface.

Abstract: Systems and methods are provided for spitting a population of users into electronic discussion groups or subgroups to facilitate more engaging conversations. Discussion profiles may be generated for individual users based on behavioral data, linguistic analysis, and demographic data. A target group size may be determined based on an analysis of user engagement levels within a number of discussion groups of varying sizes. One or more machine learning models may be configured to assign users to groups based on the users' similarity to each other and their conversation styles in order to maximize expected user engagement across the different groups.