Taylor Anderson

Henrique F. de Arruda, Sandro M. Reia, Shiyang Ruan et al.

Building type information is crucial for population estimation, traffic planning, urban planning, and emergency response applications. Although essential, such data is often not readily available. To alleviate this problem, this work creates a comprehensive dataset by providing residential/non-residential building classification covering the entire United States. We propose and utilize an unsupervised machine learning method to classify building types based on building footprints and available OpenStreetMap information. The classification result is validated using authoritative ground truth data for select counties in the U.S. The validation shows a high precision for non-residential building classification and a high recall for residential buildings. We identified various approaches to improving the quality of the classification, such as removing sheds and garages from the dataset. Furthermore, analyzing the misclassifications revealed that they are mainly due to missing and scarce metadata in OSM. A major result of this work is the resulting dataset of classifying 67,705,475 buildings. We hope that this data is of value to the scientific community, including urban and transportation planners.

Yonchanok Khaokaew, Flora D. Salim, Andreas Züfle et al.

Generative agents have been increasingly used to simulate human behaviour in silico, driven by large language models (LLMs). These simulacra serve as sandboxes for studying human behaviour without compromising privacy or safety. However, it remains unclear whether such agents can truly represent real individuals. This work compares survey data from the Understanding America Study (UAS) on healthcare decision-making with simulated responses from generative agents. Using demographic-based prompt engineering, we create digital twins of survey respondents and analyse how well different LLMs reproduce real-world behaviours. Our findings show that some LLMs fail to reflect realistic decision-making, such as predicting universal vaccine acceptance. However, Llama 3 captures variations across race and Income more accurately but also introduces biases not present in the UAS data. This study highlights the potential of generative agents for behavioural research while underscoring the risks of bias from both LLMs and prompting strategies.