Towards Building Economic Models of Conversational Search
This provides a theoretical framework to guide conversational search agent development, though it is incremental as it builds on existing descriptive models without empirical testing.
The paper tackles the lack of economic insights in conversational search by developing two theoretical models (Feedback First and Feedback After) based on observed patterns, showing that feedback amount depends on its efficiency and cost, but empirical validation is needed for specific predictions.
Various conceptual and descriptive models of conversational search have been proposed in the literature -- while useful, they do not provide insights into how interaction between the agent and user would change in response to the costs and benefits of the different interactions. In this paper, we develop two economic models of conversational search based on patterns previously observed during conversational search sessions, which we refer to as: Feedback First where the agent asks clarifying questions then presents results, and Feedback After where the agent presents results, and then asks follow up questions. Our models show that the amount of feedback given/requested depends on its efficiency at improving the initial or subsequent query and the relative cost of providing said feedback. This theoretical framework for conversational search provides a number of insights that can be used to guide and inform the development of conversational search agents. However, empirical work is needed to estimate the parameters in order to make predictions specific to a given conversational search setting.