Constructing computer-based tutors that are socially sensitive: Politeness in educational software

Students rated 16 tutorial statements on negative politeness (i.e., how much the tutor “allows me freedom to make my own decisions”) and positive politeness (i.e., how much the tutor was “working with me”). Consistent with an adaptation of Brown and Levinson's [1987. Politeness: Some Universals in Language Use. Cambridge University Press, New York] politeness theory, (a) students rated direct commands and commands attributed to machines as lowest in negative and positive politeness, (b) students rated guarded suggestions and guarded questions as highest in negative politeness, and guarded suggestions and statements expressing a common goal as highest in positive politeness, and (c) the pattern of results was stronger for students with low rather than high computing experience. Results have implications for designing polite conversational agents in educational software.