Date of Award
Doctor of Philosophy in Information Systems (DISS)
College of Engineering and Computing
Maxine S. Cohen
Laurie P. Dringus
Steven R. Terrell
Human behavior varies widely as does the design of spoken dialog systems (SDS). The search for predictors to match a user’s preference and efficiency for a specific dialog interface type in an SDS was the focus of this research. By using personality as described by the Five-Factor Method (FFM) and the Wizard of Oz technique for delivering three system initiatives of the SDS, participants interacted with each of the SDS initiatives in scheduling an airline flight. The three system initiatives were constructed as strict system, which did not allow the user control of the interaction; mixed system, which allowed the user some control of the interaction but with a system override; and user system, which allowed the user control of the interaction. In order to eliminate gender bias in using the FFM as the instrument, participants were matched in gender and age. Participants were 18 years old to 70 years old, passed a hearing test, had no disability that prohibited the use of the SDS, and were native English speakers. Participants completed an adult consent form, a 50-question personality assessment as described by the FFM, and the interaction with the SDS. Participants also completed a system preference indication form at the end of the interaction. Observations for efficiency were recorded on paper by the researcher. Although the findings did not show a definitive predictor for a SDS due to the small population sample, by using a multinomial regression approach to the statistical analysis, odds ratios of the data helped draw conclusions that support certain personality factors as important roles in a user’s preference and efficiency in choosing and using a SDS. This gives an area for future research. Also, the presumption that preference and efficiency always match was not supported by the results from two of the three systems. An additional area for future research was discovered in the gender data. Although not an initial part of the research, the data shows promise in predicting preference and efficiency for certain SDS. Future research is indicated.
Teresa G. Carter. 2016. Five-Factor Model as a Predictor for Spoken Dialog Systems. Doctoral dissertation. Nova Southeastern University. Retrieved from NSUWorks, College of Engineering and Computing. (990)