Timothy W. Bickmore
Carole D. Hafner, Michael Paasche-Orlow
Date of Award
Master of Science
Department or Academic Unit
College of Arts and Sciences. College of Computer and Information Science
computer science, conversational agent, informed consent
Research has shown that the comprehension of documents written by professionals for laypersons - such as Research Informed Consent forms - is a challenging task for many due to low literacy level, lack of prerequisite domain knowledge, and the use of arcane, complex language that is above the individual's reading level.
Prior work has demonstrated that an Embodied Conversational Agent can successfully explain Research Informed Consent documents to participants, resulting in higher comprehension and satisfaction compared to self-study of the document. However, this prior work relied on scripted explanation dialogue, limiting the ability of the system to be deployed across a large number of studies.
In this thesis I describe a system that automatically and dynamically generates the explanation for a Research Informed Consent document and delivers the explanation via an Embodied Conversational Agent, given a machine-readable description of the document's contents and structure. This system is evaluated in an empirical study that compares two versions of the automated approach with self-study of the document. Results indicate that participants learned more when forced to hear more information from the agent, although they were less satisfied with this version of the system compared to a version that attempted to dynamically tailor information to the participant's prior knowledge.
Fernando, Rukmal, "Automated explanation of research informed consent by embodied conversational agents" (2009). Computer Science Master's Theses. Paper 3. http://hdl.handle.net/2047/d20000286
Click button above to open, or right-click to save.