This paper describes a constructive architecture for using large language model (LLM) in generating virtual personas with respect to the authors' proposed simulation-based quantitative persona creation method. This architecture consists of a layered structure for persona generation and the concept of operational evolution. The layered structure consists of a Fundamental Layer consisting of typified facts extracted from simulations, a Narrative Layer generated from facts typified by LLM, and a Presentation Layer that uses LLM to enhance the realism of the personas as personas. In the operational phase, this layered structure allows for easy modification and reflection based on feedback from the field and changes in the environment. The main findings of this study are as follow: our architecture could 1) achieve logical consistency with simulation and survey results, 2) generate stories with a certain paragraph structure, 3) inject external information and knowledge, and 4) derive the technical process naturally to generate the personas. In particular, we conduct specific demonstrations about 3) above mentioned; we found that it is possible to revise persona stories in a realistic manner by adding external information to them through prompt engineering methods like Reasoning and Action; ReAct.

As Japan’s labor force becomes increasingly reliant on foreign workers, linguistic barriers have emerged as a major challenge in workplace safety. This study explores the use of large language models (LLMs) to generate “Easy Japanese” from safety manuals in the manufacturing and agriculture sectors. Focusing on prompt design, we compare Zero-shot and One-shot input formats using GPT-4o and a specialized Easy Japanese model. We evaluate output using three methods: manual evaluation, automatic evaluation, and machine-based self-evaluation using ChatGPT. The results show that both input styles produce usable outputs, with One-shot offering greater accuracy and Zero-shot offering speed and ease of use. These findings highlight the potential of LLMs to support low-cost, multilingual workplace communication and promote multicultural inclusion.

This study aims to develop a participatory science platform in Japan by identifying design requirements for touch-points, participation pathways, and interaction mechanisms between citizens and the platform. Using semi-structured interviews and journey mapping, the research examines the motivations and behaviors of extreme users involved in participatory science projects with the "Minna no Midorimushi Project" serving as a case study. The study reveals three key functional structures. First, extreme users can serve as "participation catalysts". Second, citizen participation tends to evolve through a four-stage process: exploration → invitation → confirmation → further consideration; Finally, the visualization of individual contributions plays a significant role in sustaining motivation for continued engagement. Based on these findings, three design requirements for an effective participatory science platform emerged: touch-points, participation pathways, and interactions. These insights provide valuable implications for encouraging broader public engagement in participatory science.

Career education for children emphasizes the development of four key competencies: interpersonal and social abilities, self-understanding and self-management abilities, problem-solving ability, and career planning ability. This study examined the educational effects of the Learning Feedback System (LeaFeS), which was developed to enhance children’s problem-solving and career planning ability by promoting reflection after experiential learning. The system was implemented in “Children’s City,” a community-based activity designed and managed by children. Using data collected in 2024 (N = 59), pre- and post-activity comparisons showed a moderate improvement in problem-solving ability. A notable increase in career planning ability was observed, especially among participants who engaged for two to five hours. These findings suggest that LeaFeS effectively supports reflection and the development of sustainable learning and career awareness in children.

In healthcare, it is essential to consider not only individuals’ physical and mental conditions but also their life backgrounds. Therefore, the persona method—which designs services for the general public based on a typical user profile—is not always effective in care contexts. To better understand users for the purpose of care service design, this study emphasizes individual receptivity, empathy, and fragments of personal narratives (life stories) and self-disclosure. This paper proposes human-centered design that incorporates caregiver behaviors, tools, and operations in real-world settings. An interaction model between a caregiver as a service provider and a care recipient is proposed as a service design approach grounded in a view of humanity. Additionally, a narrative utilization ecosystem is proposed as a service system of operation in care-giving settings. A case study analyzing conversations between a person with dementia and their caregivers is also introduced as an experiment to examine the potential to collect narratives from care recipients.

Leveraging HCD competences and the HCD‑Net body of knowledge, this study investigates how formalized knowledge frameworks accelerate capability building in a design agency. We conducted semi‑structured interviews with three 2023 graduate designers at YUMEMI Inc. and thematically analyzed 185 minutes of transcripts. Five themes emerged—shared formal vocabulary, iterative skill rehearsal, acquisition of holistic project architecture, structured self‑reflection, and a culture that promotes risk‑taking—forming a stepwise learning ladder sustained by psychological safety. The findings visualize SECI knowledge conversion in practice and offer a transferable framework for organizations adopting an agency model of human‑centered design.

If all the characters at the head and tail of words are fixed, humans can read weird sentences in which some characters exchange their positions. The phenomenon is called typoglycemia. However, the relationship between the complexity level of typoglycemia and the reader's ability to recognize it is unclear. To disclose the relationship, we have defined the typoglycemia level and developed the experimental platform ReadabilityTest. This study presents the intention and overview of our challenge, and the results of the experiment reveal tendencies in the recognition process time for reading such typogricemified sentences.

Travel has long been a favorite pastime for many people. However, the factors that are important to people when they travel differ from person to person. Various factors, such as the comfort of accommodations, the convenience of transportation, and cost, influence decision-making. The purpose of this study is to identify the factors that travelers consider important when choosing a trip and analyze the trends in these factors to gain knowledge that will be used to develop marketing strategies for the travel industry.