Climate change associated with global warming is increasing disaster risk. This study explores information communication methods that promote effective evacuation behavior. Given the fact that disaster forecasting, and communication technologies have become more sophisticated over the years and that people do not evacuate even though disaster information is readily available, we analyzed how a combination of information, normative effects, and proximity effects can contribute to promoting evacuation behavior. The importance of approaching different personas and selecting the timing and content of information provision was clarified, and research was conducted on the importance of information communication strategies in disaster management.

As inclusive business progresses, estimating the annual income status of users on SNS offers the possibility of appropriate intervention methods for people with low incomes. This paper analyzed people with low incomes in Japan and the United States using Facebook advertising data. It used Random Forest to examine the differences between regions with high and low poverty rates. The results showed that high interest in tobacco in the United States is associated with poverty rates. However, there is room for improvement in the model's accuracy and the difficulty of estimating income status from Facebook advertising data. Future challenges include increasing the types of data and further consideration of analytical methods.

Currently, the emergence of technologies that significantly alter the framework of existing business operations, such as generative AI and Web3, along with the growing impor- tance of globally demanded knowledge and skills such as Digital Transformation (DX) and Green Transformation (GX), is evident. In Japan, there is a growing need for reskilling. However, many companies and employees are unable to adapt to technological and social changes, remaining at low productivity levels. This study aims to construct a simulation model that explores how companies adapt to the demand for new knowledge in society, depending on their organizational structure. The results revealed that differences in organizational structure can affect the speed of knowledge propagation and business performance utilizing new knowledge. Specifically, in organizations with employees having high learning capabilities, the acquisition of existing knowledge within the com- pany is quick, but there is a failure to adapt to new knowledge demanded by society. Additionally, it was found that organizations with a flat, non-hierarchical structure improve performance more quickly compared to those with defined hierarchies. Thus, this simulation was able to replicate the process of knowledge propagation influenced by organizational structure and corporate activities. Future efforts will focus on adding parameters to better represent the reality of organizations, conducting additional research to enhance the model 's validity, and aiming to apply it in the formulation of strategies in actual organizations.

In order to promote LGBT participation and acceptance in society, we need to develop indicators to compare the current status of each society. This study clarifies the differences in LGBT awareness in the language space of each country by analyzing the differences in perceptions of LGBT among the G20 countries that appear in Wikipedia articles.This paper uses a natural language processing model (BERT) to vectorize Wikipedia articles in each country's language and then uses dimensionality compression, clustering, and other processing to clarify the characteristics of LGBT awareness in each language space. We also find a correlation between LGBT awareness and the Gender Gap Index in each language space.

In facilities where indoor temperature and humidity are generally maintained at com- fortable levels, there is a lack of research into the reality of complaints regarding the thermal environment. There are many facilities that are not progressing. In this study, we used a dataset of actual facilities where workers complained about the thermal environment despite the fact that the indoor temperature and humidity were maintained at a level that people generally felt com- fortable in. We conducted an analysis to see if there are any differences in the way people feel. Analysis using feature engineering and machine learning (Randomforest) suggested that there are differences in the importance of features and trends in hot and cold complaints.

本研究では，我が国の農業法人の顧客ニーズを起点とする事業活動の実践(市場志向) が当該法人の市場成果にどのような影響を及ぼすのかについて検討する.全国の農業法人を対象にサーベイ調査を実施し，分析の結果，競争志向，製品志向，およびブランド志向は企業成果 に影響を及ぼさなかったが，顧客志向が企業成果に及ぼす影響を及ぼすことが示された.

We propose a method to apply human trajectory generation AI which uses natural language processing technology to customer flow within retail stores. Furthermore, by modeling purchasing behavior and integrating it into the AI, we enable the generation of not only foot traffic patterns but also purchases. The generated results demonstrate high reproducibility with real data in two aspects: 1) Heatmaps of in- store movement, and 2) Number of purchased items per zone.

Most simulation studies on MaaS focus on the efficient management of the systems. However, considering the current situation where some MaaS projects have failed, the most important issue is to acquire users and monetize the business. The purpose of this study is to explore scenarios where new services can acquire users against existing services. We constructed a multi-agent model consisting of two types of agents, services and users, and conducted simulations. As a result, we found that the availability of services is the most important factor in user acquisition, and that services specializing in a single characteristic are more likely to acquire many users.

This study focused on identifying the most effective and precise machine learning models for evaluating the effects of major sporting events. This study incorporates advanced selection techniques, such as Least Squares, Stepwise Regression, Support Vector Machines, Boosted Neural Networks, and KNN, to broaden the scope of machine learning applications. This study emphasizes the significance of key factors such as long-term investments, visitor numbers, and GDPs in assessing the impact of these events. This study assessed the contribution of the correlation between the variables and the principal components and each machine learning model performance during the training and validation phases. The results indicate that the Least Squares and Stepwise Regression models performed well during the training phase, whereas the neural-boosted model showed limitations in generalization.

In recent years, value creation through data exchange and distribution among different organizations has been attracting attention as a new source of innovation. However, the design and acquisition of data is highly specialized. Therefore, data exchange between others with different background knowledge involves risks such as the application of incorrect data analysis methods and inconsistencies during data integration. In this study, we believe that sharing not only the actual data but also the intrinsic meaning of the data is effective in addressing these issues. In this paper, we define "data morphemes" as the basic structure of data, and obtain the semantic units of data as the contexts and variables, and their relationships from textual information contained in metadata. We then discuss the results of our attempt to extract data morphemes using association analysis with network approach.

企業の広告活動と様々な社会・経済情勢の変化との関係を検討するため，TV-CMを出 稿した企業のネットワークについて時系列で構造変化を分析した.月次のテンポラルネットワークか ら得られたラプラシアン行列を用いて，ネットワークの状態の変化検知を行った.広告活動と景気後退や新メディアの登場といった様々な社会・経済情勢の変化との関係は，十分に検討されていない. 2008年1月から2020年6月までのデータを用いたクラスター分析の結果，ネットワークの状態の循環的な変化と構造的な変化が捉えられた.ネットワークの状態の変化は景気循環とは一致しておらず，構造的な変化は東日本震災やCovid-19蔓延の前後で急激に起こったことがわかった.このことは，企業の広告活動の構造的な変化は緩やかには起こらず，外生的なイベントによって非連続に実現する可能性を示唆する.

Although the size of consumer-to-consumer (C2C) markets has expanded in recent years, trust building has become a crucial issue in market services. Especially in online C2C shopping, where face-to-face interactions are impossible, efficient communication through product pages plays a key role. In this study, we analyze the items that buyers consider important when understanding the information on product pages through the evaluation of fictitious product pages. Furthermore, by conducting eye tracking simultaneously, we organize the methods of information processing by consumers.

As a case study of the Shibuya and Kanda Station area, a correlation analysis was conducted using building and location indicators including the visibility and the integration value based on the space syntax theory as factor variables and the capitalization rate as an objective variable. The multiple regression analysis was then conducted. The results showed that the integration value as the space syntax theory indicators had an impact on the capitalization rate.

In order to design social systems and infrastructure, a sustainable public mechanism operated by participants composed of citizens who engage in public interest activities for self-realization and companies who strive to fulfill their social responsibilities as going concerns will be increasingly required in the recent circumstances where governmental budget constraints are becoming tighten. In this paper, we investigated "One Person, One Flower" project promoted by Fukuoka local government. We design social activities taking into account society as a whole and each stakeholder that makes up that society and then we design a mechanism to make these activities sustainable.

As Japan's rural areas continue to suffer from the decline of population, various regional development approaches are attracting the attention to activate the local communities. The large commercial facilities have an economic impact on the local community. In this study, focusing on large commercial facilities widely located throughout Japan, we examined the impact of opening the facility on the land values in the areas located these facilities and its factor. The results suggest that the population size of the city in which the facility is located has an impact on the difference in the land values.

This study aimed to understand how employees feel about their work environment and the factors influencing those feelings, by analyzing reviews on job-switching websites. The data extracted using advanced natural language processing (BERT) revealed common factors affecting employee satisfaction, including workplace environment, career development, business growth, interpersonal relationships, and evaluation and rewards. Furthermore, by utilizing large language models to generate employee personas, the study identified specific challenges and motivations, suggesting the potential to infer employee characteristics and provide valuable insights for decision-making.

In recent years, several companies have issued integrated reports that disclose non-financial information such as environmental reports, CSR reports, and governance, in addition to financial information such as business performance, business overview, and management strategy. This paper focuses on the business reporting segments of the integrated reports issued by four major real estate developers. We extracted important words and phrases from the frequency of occurrence of the words and phrases in the integrated reports of each company and compared them with each other and over time to identify the transition of each company's business and the words and phrases of high importance.

This research delves into the contemporary challenges of the aging population and escalating healthcare costs, with a specific focus on the critical issue of elderly healthcare expenses. In the aftermath of the COVID-19 pandemic and amidst complex influences such as rising prices, healthcare reforms, and the promotion of primary care systems, clinics face an increased risk of bankruptcy. The paper centers on developing new strategies for clinic administrators amid the demanding conditions brought about by the 2024 medical fee revision. The primary emphasis is on optimizing clinic placement for sustained growth and survival. Recognizing the urgency of addressing diverse regional healthcare needs efficiently, the study considers the impact of perceived "attractiveness" from the patient's perspective on clinic success. The research aims to understand patients' decision -making processes in selecting healthcare institutions through real-world surveys and evaluates optimal clinic placement using attractiv eness assessments.The methodology involves dividing the analysis area into 500 -meter meshes, and synthesizing resident and household information from aggregated population data. Patient estimates for specific conditions are calculatedutilizingprescriptiondataatmunicipalandmesh levels.Aquestionnairesurvey,employingthe Analytic Hierarchy Process (AHP), explores patients' preferences for healthcare institutions. Distances from existing competitor medical facilities and a hypothetical clinic are calculated, incorpora ting AHP- derived attractiveness into the Huff model. Ultimately, the Huff model is expected to identify optimal locations for new clinic openings, providing valuable support for physicians in enhancing clinic management and sustaining operations amidst the dynamic healthcare landscape.

Customers utilize reviews as a valuable source of information when selecting cosmetic products, and reviews significantly influence social media platforms in marketing. This study analyzes the characteristics of cosmetic customer reviews and their effects on sales ranking. This study vectorized cosmetic reviews obtained from X (Twitter) using BERT and conducted hierarchi cal clustering with dimensionality reduction vectors. Analyzing each of the cluster's Word Clouds, we revealed characteristics of clusters along two axes: "product features and information - impre ssions and experiences" and "purchase reports - difficulty in purchasing reports." However, we could not observe a significant correlation between these characteristics and product rankings.

The congestion on university campuses, where numerous students traverse, needs to be alleviated for the prevention of crowd accidents and ensuring comfortable movement. Since modifying physical conditions such as building locations and pathway widths is challenging, this study focuses on controlling pedestrian flow and mitigating congestion by rearranging the arrangement of classrooms where lectures take place. While an ideal classroom arrangement, minimizing students' travel distances or times, would be effective in restraining pedestrian flow, it is impractical as it would result in repeatedly using only classrooms near campus entrances. Therefore, this research introduces the evaluation of movement costs considering congestion as a metric and utilizes genetic algorithms to explore classroom configurations that minimize these costs. Experimental results conducted on a timetable constructed based on real data confirm the effectiveness of dispersing classroom placements in alleviating congestion.

This research focuses on the decline in demand due to the spread of next-generation EV and hybrid vehicles, uses an agent-based model to predict gasoline demand, and predicts demand for a delivery model in which gasoline is delivered from a refinery or oil depot to a gas station by tank truck. We conducted a search for efficient delivery methods by reflecting the prediction results. The following results were obtained. Although oil depots have the function of reducing the number of tank trucks needed, using oil depots tends to increase delivery costs. If future gasoline demand decreases, the number of tanker trucks needed will also decrease. This is expected to reduce the need for the depot's ability to reduce the number of tanker trucks needed, making closure more economically advantageous.

Using data on the movement trajectories of approximately 15,000 people per day passing through Urayasu City, Chiba Prefecture, in August 2022, we confirmed that there is a strong correlation between the area and perimeter of the polygons they depict. The correlation parameters showed that the trajectories of people moving long distances of 5 (km) or more are linear. This trend is stronger on weekends and holidays. On the other hand, the trajectories of people moving short distances of less than 5 (km) are circular or square, enclosing a large area. This trend did not change significantly between weekdays and weekends or holidays. Analysis was also carried out according to the attributes of gender and age, which are added to the movement track data. The results showed that the linear trend for long-distance movement was stronger for women than for men. For age groups, the trend was stronger for those under 30 years of age. These results mean that long-distance movers have a specific destination and move in a straight line to and from that destination, and that this tendency is stronger among women under 30 years of age.

"Yandere" is an archetype among Japanese young adults that expresses characteristics such as an intense fear of being abandoned by one's partner and a tendency to constrain one's partner.This paper clarifies the components of this yandere tendency and the influence of the "Satisfaction of University Life" Scale on the yandere tendency. We administered questionnaires on the "Satisfaction of University Life" Scale and the "Yandere Tendency Scale" to about 60 university students and conducted a residue analysis and a Structural Equation Modeling. Residual analysis revealed nine associations between the scales, including "high anxiety about college life and frequency of alert behavior toward one's partner" and "high academic satisfaction and degree of service to one's partner." Structural Equation Modeling revealed that four factors, "emotional support," "desire to possess," "fear of abandonment," and "tendency toward self-sacrifice," explained the Yandere tendency scale. Furthermore, this analysis revealed a causal relationship between "commitment to university activities," a subscale of the college life fulfillment scale, and yandere tendency.

We propose a generative AI that applies the technique of diffusion models for image generation to replicate real financial time series data with extremely high precision. Financial time series data possess long-term memory processes, making it challenging to generate high-precision financial time series without setting the maximum sequence length in transformers to be very long. Therefore, by transforming time series data into frequency information through wavelet transformation and learning the long-term memory as images, we use a more lightweight diffusion model to generate real financial time series data with ultra-high precision.

The Bank for International Settlements defines zombie firms as companies with an interest coverage ratio of less than 1 for three consecutive years and operating for more than ten years. The phenomenon of zombie firms is on the rise, particularly in Japan amid the COVID-19 pandemic, and has garnered significant attention. This study try to construct and examine a dataset for assessing zombie firms using the EDINET API offered by the Financial Services Agency and to discern the determinants contributing to their emergence. The paper outlines the methodology employed to construct the dataset for analyzing zombie firms, presents visualizations of select data points, and discusses issues.