The Trusted Caregiver: The Influence of Eye and Mouth Design Incorporating the Baby Schema Effect in Virtual Humanoid Agents on Older Adults Users' Perception of Trustworthiness
November 27, 2024 Β· Declared Dead Β· π Proceedings of the Twelfth International Symposium of Chinese CHI
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Jennifer Hu
arXiv ID
2411.18047
Category
cs.HC: Human-Computer Interaction
Citations
1
Venue
Proceedings of the Twelfth International Symposium of Chinese CHI
Last Checked
4 months ago
Abstract
The increasing proportion of the older adult population has made the smart home care industry one of the critical markets for virtual human-like agents. It is crucial to effectively promote a trustworthy human-computer partnership with older adults, enhancing service acceptance and effectiveness. However, few studies have focused on the facial features of the agents themselves, where the "baby schema" effect plays a vital role in enhancing trustworthiness. The eyes and mouth, in particular, attract most of the audience's attention and are especially significant. This study explores the impact of eye and mouth design on users' perception of trustworthiness. Specifically, a virtual humanoid agents model was developed, and based on this, 729 virtual facial images of children were designed. Participants (N=162) were asked to evaluate the impact of variations in the size and positioning of the eyes and mouth regions on the perceived credibility of these virtual agents. The results revealed that when the facial aspect ratio (width and height denoted as W and H, respectively) aligned with the "baby schema" effect (eye size at 0.25W, mouth size at 0.27W, eye height at 0.64H, eye distance at 0.43W, mouth height at 0.74H, and smile arc at 0.043H), the virtual agents achieved the highest facial credibility. This study proposes a design paradigm for the main facial features of virtual humanoid agents, which can increase the trust of older adults during interactions and significantly contribute to the research on the trustworthiness of virtual humanoid agents.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Human-Computer Interaction
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Improving fairness in machine learning systems: What do industry practitioners need?
R.I.P.
π»
Ghosted
Identifying Stable Patterns over Time for Emotion Recognition from EEG
R.I.P.
π»
Ghosted
Questioning the AI: Informing Design Practices for Explainable AI User Experiences
R.I.P.
π»
Ghosted
Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
R.I.P.
π»
Ghosted
Educational data mining and learning analytics: An updated survey
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted