A Comparison of Praising Skills in Face-to-Face and Remote Dialogues
13269Authors
nan
Abstract
AbstractPraising behavior is considered to an important method of communication in daily life and social activities. An engineering analysis of praising behavior is therefore valuable. However, a dialogue corpus for this analysis has not yet been developed. Therefore, we develop corpuses for face-to-face and remote two-party dialogues with ratings of praising skills. The corpuses enable us to clarify how to use verbal and nonverbal behaviors for successfully praise. In this paper, we analyze the differences between the face-to-face and remote corpuses, in particular the expressions in adjudged praising scenes in both corpuses, and also evaluated praising skills. We also compare differences in head motion, gaze behavior, facial expression in high-rated praising scenes in both corpuses. The results showed that the distribution of praising scores was similar in face-to-face and remote dialogues, although the ratio of the number of praising scenes to the number of utterances was different. In addition, we confirmed differences in praising behavior in face-to-face and remote dialogues.
Keywords
Full Content
Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 5805–5812 Marseille, 20-25 June 2022 © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0 5805 A Comparison of Praising Skills in Face-to-Face and Remote Dialogues Toshiki Onishi1,∗, Asahi Ogushi1,∗, Yohei Tahara2,∗, Ryo Ishii3,†, Atsushi Fukayama3,†, Takao Nakamura3,†, Akihiro Miyata2,‡ 1Graduate School of Integrated Basic Sciences, Nihon University, Tokyo, Japan 2College of Humanities and Sciences, Nihon University, Tokyo, Japan 3NTT Human Informatics Laboratories, NTT Corporation, Kanagawa, Japan ∗{chto22002, chas22009, chyo19046}@g.nihon-u.ac.jp †{ryo.ishii.ct, atsushi.fukayama.ap, takao.nakamura.vp}@hco.ntt.co.jp ‡miyata.akihiro@acm.org Abstract Praising behavior is considered to an important method of communication in daily life and social activities. An engineering analysis of praising behavior is therefore valuable. However, a dialogue corpus for this analysis has not yet been developed. Therefore, we develop corpuses for face-to-face and remote two-party dialogues with ratings of praising skills. The corpuses enable us to clarify how to use verbal and nonverbal behaviors for successfully praise. In this paper, we analyze the differences between the face-to-face and remote corpuses, in particular the expressions in adjudged praising scenes in both corpuses, and also evaluated praising skills. We also compare differences in head motion, gaze behavior, facial expression in high-rated praising scenes in both corpuses. The results showed that the distribution of praising scores was similar in face-to-face and remote dialogues, although the ratio of the number of praising scenes to the number of utterances was different. In addition, we confirmed differences in praising behavior in face-to-face and remote dialogues. Keywords: multimodal interaction, dialogue corpus, praise 1. Introduction Praising behavior is considered an important method of communication in daily life and social activities. Praise is a verbal and nonverbal behaviors expression of approval that is directed toward the behavior and character of the target (Brophy, 1981; Jenkins et al., 2015; Kalis et al., 2007). In addition, praising behavior is considered to be a complex social communication rather than simple one-way communication of inten- tion from a person who gives praise to a person who receives praise (Henderlong and Lepper, 2002). Many studies on praising behavior have analyzed the results of questionnaires and evaluations conducted after spe- cific tasks to understand the effects and influences of praising behavior (Henderlong and Lepper, 2002; En- nis et al., 2018). An engineering analysis of praising behavior is valuable and would contribute to communi- cation in the scenes of business and education, as well as to the study of pedagogy and psychology. However, a dialogue corpus for this analysis has not yet been de- veloped. Therefore, we have not been able to clarify how to use verbal and nonverbal behaviors for success- fully praise. In addition, the influence of the COVID- 19 pandemic has increased the opportunities for remote communication. We consider that praising skills are also important in such situations. However, a corpus for the study of praising skills is not available. To the best of our knowledge, this is the first study to develop corpuses of face-to-face and remote two-party dialogues with ratings of praising skills. …
Content truncated to 500 words
Labeled Text
AbstractPraising behavior is considered to an important method of communication in daily life and social activities. An engineering analysis of praising behavior is therefore valuable. However, a dialogue corpus for this analysis has not yet been developed. Therefore, we develop corpuses for face-to-face and remote two-party dialogues with ratings of praising skills. The corpuses enable us to clarify how to use verbal and nonverbal behaviors for successfully praise. In this paper, we analyze the differences between the face-to-face and remote corpuses, in particular the expressions in adjudged praising scenes in both corpuses, and also evaluated praising skills. We also compare differences in head motion, gaze behavior, facial expression in high-rated praising scenes in both corpuses. The results showed that the distribution of praising scores was similar in face-to-face and remote dialogues, although the ratio of the number of praising scenes to the number of utterances was different. In addition, we confirmed differences in praising behavior in face-to-face and remote dialogues.
Publication Details
- Paper ID:
- 13269
- Year:
- 2022
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan