Keita Kiuchi

Dr. Keita Kiuchi

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 November 2023 in Behaviour & Information Technology
Verified
Journal Article
Open access
KKKeita Kiuchi
Keita Kiuchi
KOKouyou Otsu
Kouyou Otsu
YHYugo Hayashi
Yugo Hayashi

17 October 2020 in Asia Pacific Journal of Public Health
Verified
Journal Article
Open access
PDF file
KKKeita Kiuchi
Keita Kiuchi
KKKatsumasa Kishi
Katsumasa Kishi
KAKanto Araki
Kanto Araki
The spread of coronavirus disease 2019 has led to several subsidiary health problems for the general public. Therefore, verification of psychosomatic responses under various conditions is required. The current study examines the mental and physical responses of individuals in Japan in relation to differences in basic demographic information. A web survey was conducted among 1500 people. The results showed that differences in ethnicity, concurrence of physical or mental illness, the nature of those living in the same household (eg, high-risk individuals or preschoolers), household income, and employment status were associated with differences in physical and mental health, psychological distress, and/or suicidal ideation. Differences related to the degree of the spread of the infection in the area of residence, degree of engagement in essential work, and frequency of contact with others during normal times were not found. Future longitudinal studies and verification of the effects of multiple variables are required.

27 June 2024 in Healthcare
Verified
Journal Article
Open access
PDF file
KKKeita Kiuchi
Keita Kiuchi
HUHidehiro Umehara
Hidehiro Umehara
KIKoushi Irizawa
Koushi Irizawa
XKXin Kang
Xin Kang
MNMasahito Nakataki
Masahito Nakataki
KMKazuyuki Matsumoto
Kazuyuki Matsumoto
Recently, the use of digital technologies, such as avatars and virtual reality, has been increasingly explored to address university students’ mental health issues. However, there is limited research on the advantages and disadvantages of counselors using avatars in online video counseling. Herein, 25 university students were enrolled in a pilot online counseling session with a human counselor-controlled avatar, and asked about their emotional experiences and impressions of the avatar and to provide qualitative feedback on their communication experience. Positive emotions during the session were associated with impressions of the avatar’s intelligence and likeability. The anthropomorphism, animacy, likeability, and intelligent impressions of the avatar were interrelated, indicating that the avatar’s smile and the counselor’s expertise in empathy and approval may have contributed to these impressions. However, no associations were observed between participant experiences and their prior communication with avatars, or between participant experiences and their gender or the perceived gender of the avatar. Accordingly, recommendations for future practice and research are provided. Accumulating practical and empirical findings on the effectiveness of human-operated avatar counselors is crucial for addressing university students’ mental health issues.

29 December 2022 in Journal of Occupational and Environmental Medicine
Verified
Journal Article
Closed access
KKKeita Kiuchi
Keita Kiuchi
TSTakeshi Sasaki
Takeshi Sasaki
MTMasaya Takahashi
Masaya Takahashi
TKTomohide Kubo
Tomohide Kubo
TYToru Yoshikawa
Toru Yoshikawa
XLXinxin Liu
Xinxin Liu
Objectives: This study examines the mediating and moderating effects of psychological detachment (PD) based on the stressor-detachment model in the long term. Methods: Two waves of Web-based surveys, 28 months apart, yielded 3556 responses from Japanese workers. Comparisons between models that included mediating and moderating effects of PD and reverse direction mediating effects (strain → PD → stressor) were made by structural equation modeling. Differences in depression as a strain between combinations of high and low stressors and PD were also examined. Results: The best-fitting model was the moderation/reciprocal partial-mediation model. The effect of PD was significant in the group with stable or decreasing stressor. Conclusion: According to the worker's level of stressors, PD, and depression, targeted interventions may effectively prevent physical and mental health problems caused by chronic stress.

11 March 2024
Verified
Conference Paper
Open access
YHYugo Hayashi
Yugo Hayashi
KKKeita Kiuchi
Keita Kiuchi
This study examined an active listening counseling chatbot using Miracle Questions for addressing emotional distress in various age groups. It is based on Solution-Focused Brief Therapy (SFBT). The experiment targeted older people and young university students over three weeks, and changes in the expression of emotions in each generation were analyzed. The results showed qualitative differences in the vocabulary characteristics of the participants, with their positive emotion-expressive behavior increasing more significantly than their negative feelings. This suggests that active listening methods using the Miracle Question are promising for designing a dialogue system suitable for elderly patients. In the future, we will develop a dialogue model that provides topics based on the emotional expressions obtained in this text analysis and further implement this into an active listening counseling robot.

28 March 2026 in Brain Sciences
Verified
Journal Article
Open access
PDF file
KMKazuyuki Matsumoto
Kazuyuki Matsumoto
KKKeita Kiuchi
Keita Kiuchi
HUHidehiro Umehara
Hidehiro Umehara
MNMasahito Nakataki
Masahito Nakataki
SNShusuke Numata
Shusuke Numata
Background/Objectives: Multimodal depression detection research has traditionally relied on early or hybrid fusion strategies without systematically analyzing how dynamic fusion mechanisms interact with modality-specific pretraining. Although gated and attention-based architectures are increasingly adopted, their behavior is rarely examined within a structured fusion taxonomy framework. Methods: In this study, we conduct a controlled taxonomy-level evaluation of multimodal fusion strategies in a Japanese PHQ-9-annotated depression dataset. We compare four fusion paradigms (concatenation, summation, gated fusion, and cross-attention) across three integration stages, crossed with modality-specific affective pretraining configurations for visual (CMU-MOSI/MOSEI), acoustic (JTES), and textual (WRIME) encoders, yielding 512 experimental conditions. Results: The results reveal strong position-dependent effects of fusion strategy. Cross-attention fusion at the audio integration stage achieved the highest mean AUC (0.774) and PR-AUC (0.606), with statistically significant superiority over gated and concatenation-based fusion (Kruskal–Wallis H=86.28, p<0.001). In contrast, fusion effects at the text stage were non-significant in AUC but significant in PR-AUC, highlighting metric-sensitive behavior under class imbalance. Pretraining effects were modality-specific: SigLIP initialization produced significant positive transfer (Δ=+0.018, p<0.001), whereas audio pretraining on JTES resulted in negative transfer (Δ=−0.014, p=0.004), suggesting domain mismatch effects. Gate analysis further revealed condition-dependent modality dominance, including cases of semantic–geometric reversal under joint auxiliary augmentation. Conclusions: Our findings suggest that multimodal depression detection systems should not be interpreted through static fusion categories alone. Instead, modality contribution appears to be associated with structured interaction effects between fusion strategy, integration position, and affective pretraining. This work provides a controlled empirical bridge between fusion taxonomy and dynamic modality weighting in clinical multimodal modeling.