Effects of Speech Level Shift Tested by a Non-Task-Oriented Dialog System on Text Chat Dialog with Users in Japanese: A Pilot Study
Source abstract
Abstract
Recently, interaction between humans and dialog systems has become increasingly common and sophisticated. Humans establish good relationships with others using various linguistic considerations (e.g., politeness and speech level) in dialog. However, the effect of linguistic considerations used by dialog systems has remained unclear. This study examines the effects of the speech level shift used by a text chat dialog system in Japanese-language user dialog. We designed a rule-based, non-task-oriented text dialog system that controls formal and informal speech levels for Japanese dialog; the effects of a shift in the speech level used by the dialog system were verified through psychological experiments using text chats (n = 134). The speech level control method was constructed with reference to statistical information from the BTSJ Japanese natural conversation corpus and knowledge of linguistic considerations (politeness). The results of the experiment showed that 41.3% of the participants who interacted with the dialog system that shifted the speech level also shifted their speech levels in response. Moreover, a subjective evaluation revealed that participants who noticed the speech level shift of the dialog system felt that this system paid attention to its relationship with the participants. The experimental results suggest that a dialog system can realize dialog in which the user and system both adjust their relationship through dynamic speech level shifts. This study identifies the importance of dynamic speech level shifts, an important factor for expressing politeness, in interactions between humans and dialog systems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: AI in Service Interactions · Social Robot Interaction and HRI · Speech and dialogue systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Graduate School of Engineering, Tokyo Polytechnic University, Iiyama-Minami 45-1, Atsugi-shi 105-0123, Kanagawa, Japan
Graduate School of Informatics and Engineering, The University of Electro-Communications, 1-5-1 Chofugaoka, Chofu 182-8585, Tokyo, Japan
Funding
JSPS KAKENHI
References (62)
Show source-provided references
1. Apple (2023, April 21). Siri. Available online: https://www.apple.com/jp/siri/.
2. Wu, X., Ito, K., Iida, K., Tsuboi, K., and Klyen, M. (2016, January 8–10). Rinna: Zyosikousei zinkou tinou. Proceedings of the Twenty-Second Annual Meeting of the Association for Natural Language Processing, Sendai, Japan.
3. Honorifics seen from politeness, politeness seen from honorifics: An overview focusing on their pragmatic relativity
4. On styles in Japanese language: Focusing on ’Speech-Level Shift’ in Japanese conversational discourse
5. Miyamoto, T., Katagami, D., Tanaka, T., Kanamori, H., Yoshihara, Y., and Fujikake, K. (2021, January 9–11). Should a driving support agent provide explicit instructions to the user? Video-based study focused on politeness strategies. Proceedings of the Ninth International Conference on Human-Agent Interaction, Virtual Event.10.1145/3472307.3484160 ↗
6. Miyamoto, T., Katagami, D., Shigemitsu, Y., Usami, M., Tanaka, T., Kanamori, H., Yoshihara, Y., and Fujikake, K. (2021). Influence of Social Distance Expressed by Driving Support Agent’s Utterance on Psychological Acceptability. Front. Psychol., 12.10.3389/fpsyg.2021.526942 ↗
7. Bar-Or, E., Regev, T., Shaviv, P., and Tractinsky, N. (2022). Towards a sociolinguistics-based framework for the study of politeness in human-computer interaction. arXiv.
8. Miyamoto, T., Katagami, D., and Shigemitsu, Y. (2017, January 17–20). Improving relationships based on positive politeness between humans and life-like agents. Proceedings of the 5th International Conference on Human-Agent Interaction, Bielefeld, Germany.10.1145/3125739.3132585 ↗
9. Wang, N., and Johnson, W.L. (2008, January 23–27). The politeness effect in an intelligent foreign language tutoring system. Proceedings of the International Conference on Intelligent Tutoring Systems, Montreal, QC, Canada.10.1007/978-3-540-69132-7_31 ↗
10. Salem, M., Ziadee, M., and Sakr, M. (2013, January 27–29). Effects of politeness and interaction context on perception and experience of HRI. Proceedings of the International Conference on Social Robotics, Bristol, UK.10.1007/978-3-319-02675-6_53 ↗
11. Torrey, C., Fussell, S.R., and Kiesler, S. (2013, January 3–6). How a robot should give advice. Proceedings of the International Conference on Human-Robot Interaction, Tokyo, Japan.10.1109/HRI.2013.6483599 ↗
12. Takayama, L., Groom, V., and Nass, C. (2009, January 4–9). I’m sorry, Dave: I’m afraid I won’t do that: Social aspects of human-agent conflict. Proceedings of the CHI Conference on Human Factors in Computing Systems, Boston, MA, USA.10.1145/1518701.1519021 ↗
13. Srinivasan, V., and Takayama, L. (2016, January 7–12). Help me please: Robot politeness strategies for soliciting help from humans. Proceedings of the CHI Conference on Human Factors in Computing Systems, San Jose, CA, USA.10.1145/2858036.2858217 ↗
14. Lee, J.G., Lee, K.M., and Ryu, S.H. (2019). Vehicle politeness in driving situations. Future Internet, 11.10.3390/fi11020048 ↗
15. Polite speech strategies and their impact on drivers’ trust in autonomous vehicles10.1016/j.chb.2021.107015 ↗
16. Perceiving artificial social agents10.1016/j.chb.2006.02.017 ↗
17. Rana, K., Madaan, R., and Shukla, J. (2021, January 8–12). Effect of polite triggers in chatbot conversations on user experience across gender, age, and personality. Proceedings of the 30th IEEE International Conference on Robot & Human Interactive Communication, Vancouver, BC, Canada.10.1109/RO-MAN50785.2021.9515528 ↗
18. Being polite: Modeling politeness variation in a personalized dialog agent10.1109/TCSS.2022.3182986 ↗
19. Mukherjee, S., Hudeček, V., and Dušek, O. (2023, January 2–4). Polite Chatbot: A Text Style Transfer Application. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, Dubrovnik, Croatia.10.18653/v1/2023.eacl-srw.9 ↗
20. Appreciation vs. apology: Research on the influence mechanism of chatbot service recovery based on politeness theory10.1016/j.jretconser.2023.103323 ↗
21. Brown, P., and Levinson, S.C. (1987). Politeness: Some Universals in Language Usage, Cambridge University Press.10.1017/CBO9780511813085 ↗
22. Usami, M. (1993, January 8–14). Politeness in Japanese dyadic conversations between unacquainted people: The influence of power asymmetry. Proceedings of the 10th World Congress of Applied Linguistics, Amsterdam, The Netherlands.
23. Usami, M. (1994). Politeness and Japanese Conversational Strategies: Implications for the Teaching of Japanese. [Ph.D. Thesis, Harvard Graduate School of Education].
24. Formal forms and discernment: Two neglected aspects of universals of linguistic politeness10.1515/mult.1989.8.2-3.223 ↗
25. Kageyama, Y., Chiba, Y., Nose, T., and Ito, A. (2018, January 12–14). Improving user impression in spoken dialog system with gradual speech form control. Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, Melbourne, Australia.10.18653/v1/W18-5026 ↗
26. Khan, S., Fazil, M., Imoize, A.L., Alabduallah, B.I., Albahlal, B.M., Alajlan, S.A., Almjally, A., and Siddiqui, T. (2023). Transformer Architecture-Based Transfer Learning for Politeness Prediction in Conversation. Sustainability, 15.10.3390/su151410828 ↗
27. Mishra, K., Firdaus, M., and Ekbal, A. (2023). GenPADS: Reinforcing politeness in an end-to-end dialogue system. PLoS ONE, 18.10.1371/journal.pone.0278323 ↗
28. Mishra, K., Priya, P., and Ekbal, A. (2023, January 5–8). Help me heal: A reinforced polite and empathetic mental health and legal counseling dialogue system for crime victims. Proceedings of the AAAI Conference on Artificial Intelligence, Limassol, Cyprus.10.1609/aaai.v37i12.26685 ↗
29. A multi-task learning framework for politeness and emotion detection in dialogues for mental health counselling and legal aid10.1016/j.eswa.2023.120025 ↗
30. Mishra, K., Priya, P., and Ekbal, A. (2023, January 9–14). PAL to lend a helping hand: Towards building an emotion adaptive polite and empathetic counseling conversational agent. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, ON, Canada.10.18653/v1/2023.acl-long.685 ↗
31. Purohit, A.K., Upadhyaya, A., and Holzer, A. (2023, January 23–27). ChatGPT in Healthcare: Exploring AI Chatbot for Spontaneous Word Retrieval in Aphasia. Proceedings of the Companion Publication of the Conference on Computer Supported Cooperative Work and Social Computing, Virtual Event.10.1145/3584931.3606993 ↗
32. The role of politeness in human–machine interactions: A systematic literature review and future perspectives10.1007/s10462-023-10540-1 ↗
33. Reexamination of the universality of face: Politeness phenomena in Japanese10.1016/0378-2166(88)90003-3 ↗
34. Discourse politeness in Japanese conversation: Some implications for a universal theory of politeness
35. Usami, M. (2021). BTSJ-Japanese Natural Conversation Corpus with Transcripts and Recordings. NINJAL Institute-Based Projects: Multiple Approaches to Analyzing the Communication of Japanese Language Learners, National Institute for Japanese Language and Linguistics.
36. Miyamoto, T., Katagami, D., Shigemitsu, Y., Usami, M., Tanaka, T., Kanamori, H., Yoshihara, Y., and Fujikake, K. (2019, January 25–28). Proposal of driving support agent which speak based on politeness theory. Proceedings of the International Conference on Human-Computer Interaction 2019, Gipuzkoa, Spain.10.1007/978-3-030-22666-4_17 ↗
37. Evaluation of dialogue systems with different end of sentences using Seq2Seq model
38. Miyamoto, T., Katagami, D., and Usami, M. (2021, January 8–11). A politeness control method for conversational agents considering social relationships with users. Proceedings of the Advances in Artificial Intelligence-Selected Papers from the Annual Conference of Japanese Society of Artificial Intelligence, Virtual Event.10.1007/978-3-030-73113-7_22 ↗
39. Iwashita, M., and Katagami, D. (2020, January 19–24). Psychological effects of compliment expressions by communication robots on humans. Proceedings of the 2020 International Joint Conference on Neural Networks, Glasgow, UK.10.1109/IJCNN48605.2020.9206898 ↗
40. Is Politeness Better than Impoliteness? Comparisons of Robot’s Encouragement Effects Toward Performance, Moods, and Propagation10.1007/s12369-023-00971-9 ↗
41. (2023, April 21). MeCab. Available online: https://taku910.github.io/mecab/.
42. The dialogue system live competition 2
43. Spoken dialogue system development at the dialogue robot competition
44. (2023, April 21). Telegram. Available online: https://telegram.org/.
45. Measurement Instruments for the Anthropomorphism, Animacy, Likeability, Perceived Intelligence, and Perceived Safety of Robots10.1007/s12369-008-0001-3 ↗
46. Assessing Acceptance of Assistive Social Agent Technology by Older Adults: The Almere Model10.1007/s12369-010-0068-5 ↗
47. Higashinaka, R., D’Haro, L.F., Shawar, A., Bayan, B., Banchs, R., Funakoshi, K., Inaba, M., Tsunomori, Y., Takahashi, T., and Sedoc, J. (2019, January 24–26). Overview of the dialogue breakdown detection challenge 4. Proceedings of the Tenth International Workshop on Spoken Dialogue Systems Technology, Syracuse, Italy.
48. Is It Really Robust?10.1027/1614-2241/a000016 ↗
49. Summarizing Monte Carlo Results in Methodological Research: The One- and Two-Factor Fixed Effects ANOVA Cases10.3102/10769986017004315 ↗
50. Non-normal data: Is ANOVA still a valid option?10.7334/psicothema2016.383 ↗
51. The Small Sample Behavior of Some Statistics Which Test the Equality of Several Means10.1080/00401706.1974.10489158 ↗
52. Cohen, J. (1988). Statistical Power Analysis for the Behavioral Sciences, Lawrence Erlbaum Associates.
53. Open AI (2023, April 21). ChatGPT. Available online: https://openai.com/blog/chatgpt.
54. Makany, T., Roh, S., Hara, K., Hua, J.M., Goh Si Ying, F., and Teh Yang Jie, W. (2023, January 19–21). Beyond anthropomorphism: Unraveling the true priorities of chatbot usage in SMEs. Proceedings of the 5th International Conference on Conversational User Interfaces, Eindhoven, The Netherlands.10.1145/3571884.3604315 ↗
55. Dennett, D.C. (1989). The Intentional Stance, MIT Press.10.1017/S0140525X00058611 ↗
56. Reeves, B., and Nass, C. (1996). The Media Equation: How People Treat Computers, Television, and New Media Like Real People And Places, Cambridge University Press.
57. Luger, E., and Sellen, A. (2016, January 7–12). “Like having a really bad PA”: The gulf between user expectation and experience of conversational agents. Proceedings of the CHI Conference on Human Factors in Computing Systems, New York, NY, USA.10.1145/2858036.2858288 ↗
58. Danescu-Niculescu-Mizil, C., Sudhof, M., Jurafsky, D., Leskovec, J., and Potts, C. (2013, January 4–9). A computational approach to politeness with application to social factors. Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, ACL, Sofia, Bulgaria.
59. Polite dialogue generation without parallel data10.1162/tacl_a_00027 ↗
60. Nomura, T. (2017–1, January 28). Cultural differences in social acceptance of robots. Proceedings of the 26th IEEE International Symposium on Robot and Human Interactive Communication, Lisbon, Portugal.10.1109/ROMAN.2017.8172354 ↗
61. The influence of people’s culture and prior experiences with Aibo on their attitude towards robots10.1007/s00146-006-0052-7 ↗
62. Koda, T., and Takeda, Y. (2018, January 15–18). Perception of culture-specific gaze behaviors of agents and gender effects. Proceedings of the 6th International Conference on Human-Agent Interaction, Southampton, UK.10.1145/3284432.3284472 ↗