Modeling Human Interaction to Design a Human-Computer Dialog System

TL;DR

This paper introduces a conversational agent for health information search that models human interaction to improve user engagement and understanding, based on analyzing real human dialogs and cognitive processes.

Contribution

It presents a novel model of human-computer interaction for dialog systems, grounded in empirical analysis of human search dialogs and cognitive principles.

Findings

Establishment of common ground in dialogs

Accommodation effects observed in user interactions

A guiding model for artificial agents in health information search

Abstract

This article presents the Cogni-CISMeF project, which aims at improving the health information search engine CISMeF, by including a conversational agent that interacts with the user in natural language. To study the cognitive processes involved during information search, a bottom-up methodology was adopted. An experiment has been set up to obtain human dialogs related to such searches. The analysis of these dialogs underlines the establishment of a common ground and accommodation effects to the user. A model of artificial agent is proposed, that guides the user by proposing examples, assistance and choices.