Analysis of the relationship between user response to dialog breakdown and personality traits

Abstract

AbstractAlthough automated dialog systems are now being used in various applications, it is difficult to say whether they will ever be able to acquire the ability to converse as naturally as people do. As a result, various methods for detecting dialog breakdowns have been proposed. However, the effect of the user's personality on breakdown detection accuracy and user response to these breakdowns have not been sufficiently examined. Therefore, in this study we analyze the relationship between user personality traits and individual differences in responses to dialog breakdowns by conducting dialog experiments.Keywords: Dialog systemdialog breakdownpersonality traits AcknowledgmentThis work was supported by JSPS KAKENHI Grant Numbers JP22K19793, JP23H00493.Disclosure statementNo potential conflict of interest was reported by the author(s).Notes1 https://taku910.github.io/mecab/.2 When we first calculated the correlations between the part of speech features and the overall personality trait scores, no strong correlations were observed, so we then used the personality trait scores of the upper and lower groups for each personality trait when performing the U-tests, in order to reveal possible relationships.Additional informationNotes on contributorsKazuya TsubokuraKazuya Tsubokura recieved his B.S. and M.S. degrees in Information Science and Technology from Aichi Prefectural University in 2021 and 2023, respectively. He is currently a Ph.D. student in Aichi Prefectural University. His research interests include spoken dialogue systems.Yurie IribeYurie Iribe received the B.E. degree in Systems Engineering from Nagoya Institute of Technology and M.S. degree in Human Informatics from Nagoya University in 1999 and 2001. She became a research associate in the Information and Media Center at Toyohashi University of Technology in 2004. She received her Ph.D. degree from Nagoya University in 2007. She is currently an Associate Professor in Aichi Prefectural University from 2017. Her research interests include speech processing and human interface.Norihide KitaokaNorihide Kitaoka received his B.S. and M.S. degrees from Kyoto University, Japan. In 1994, he joined DENSO CORPORATION. In 2000, he received his Ph.D. degree from Toyohashi University of Technology (TUT), Japan. He joined TUT as a research associate in 2001 and was a lecturer from 2003 to 2006. He was an associate professor at Nagoya University, Japan, from 2006 to 2014 and joined Tokushima University, Japan, as a professor in 2014. He has been a professor at TUT since 2018. His research interests include speech processing, speech recognition, and spoken dialog systems. He is a member of IEEE, International Speech Communication Association (ISCA), Asia Pacific Signal and Information Processing Association (APSIPA), The Institute of Electronics, Information and Communication Engineers (IEICE), Information Processing Society of Japan (IPSJ), Acoustical Society of Japan (ASJ), The Japanese Society for Artificial Intelligence (JSAI), and The Association for Natural Language Processing.