Users, Tasks, and Conversational Agents: A Personality Study

Quentin Roy, Moojan Ghafurian, Wei Li, and Jesse Hoey. HAI '21.
EndNote
%0 Conference Paper
%8 2021-11
%D 2021
%A Roy, Quentin
%A Ghafurian, Moojan
%A Li, Wei
%A Hoey, Jesse
%I Association for Computing Machinery
%P 174-182
%T Users, Tasks, and Conversational Agents: A Personality Study
%U https://doi.org/10.1145/3472307.3484173
%X Conversational Agents (CA) have become one of the common user interfaces in many online domains. In this paper, we ask whether users have a preference about the personality of CAs, and whether this preference changes depending on the length and type of the tasks CAs are used for. In an online study (N = 410), we investigated three different CA personalities (introvert, extrovert, and non-personified) in four different tasks with different natures and lengths (teaching, booking, todo, and weather). Most of the participants preferred to interact with a conversational agent (introvert or extrovert) as opposed to a non-personified interface, regardless of their own personality. Results suggested that this preference may be task dependent: when CA’s goal was to provide information, participants preferred an extrovert agent. We did not observe a difference between the preference for introvert and extrovert agents when the task’s goal was to complete an assignment. 
Download icondownload