Truth Is Beauty: Researching Embodied Conversational Agents

(1941) argues that the sole criterion for excellent research is that the researcher produces " beauty. " While seemingly ineffable and frustratingly imprecise, Hardy instead suggests that creating beauty is straightforward. First, the work must be accurate: erroneous results are useless. Second, one's peers must recognize the work to be interesting, exciting, elegant, and " cool. " While this second criterion might seem arbitrary, there is generally good agreement between scholars in a given community about " interesting " work (see Cole and Cole 1973 for a discussion), so one need not survey numerous researchers to ensure research is beautiful; asking a couple is equivalent to asking them all. With certain caveats, the work in embodied conversational agents (ECA) can make claims to beauty. ECAs are phenomenologically " accurate " to the extent that the agent's outward appearance objectively matches the appearance, language, attitudes and behavior of humans. Thus, questions that address manifestation accuracy include " Does the agent walk like a person walk? " and " Does the agent use language and make grammatical errors the same way a person does? " An alternative approach to accuracy, generally associated more with the artificial intelligence literature than with the ECA literature, assesses the extent to which the processes that produce aspects of the ECA are the same as the processes in humans. For example, " Does the muscle model of the character match how human muscles work? " or