arXiv subjects

Takahiro Yabe

Publications and source records attributed to Takahiro Yabe.

At least 19 recordsLinked to original sources

arXiv2026

Towards welfare-oriented recommendations in activity-travel behavior

While mainstream recommender systems (RS) rely on diverse heuristics to rank alternatives, they generally lack a principled account of user welfare (i.e., whether accepting the recommendation will leave the user better off than other alternatives). The problem is particularly acute in activity-based travel behavior, where users incur costs they cannot recoup (i.e., energy, time) regardless of eventual satisfaction. As a result, existing systems may recommend options based on popularity or collaborative filtering, but may still leave users worse off than nearby or self-selected alternatives. We address this gap by introducing a welfare-oriented framework for activity recommendation that evaluates suggestions in terms of net utility, defined as experienced benefit minus travel costs. Specifically, we formalize two operational decision criteria: Positive Utility Probability (PUP) recommends only when the probability of non-negative net utility exceeds a threshold, while Regret Minimization (RM) recommends only when expected regret relative to the user's best organic alternative falls below a tolerance level. To evaluate these criteria, we develop an agent-based simulation in which heterogeneous synthetic travelers interact with multiple RS over time in a spatial environment with realistic travel costs, congestion, and behavioral feedback loops. This framework enables controlled counterfactual evaluations, and offers a practical foundation for designing RS that treat user welfare as a primary objective rather than an incidental byproduct.

cs.IR↗

arXiv2026

nD-RoPE: A Generalized RoPE for n-Dimensional Position Embedding

Rotary Position Embedding (RoPE) is widely adopted in Transformer models, yet its extension to high-dimensional domains lacks a unified theoretical formulation. Most existing approaches either apply rotations independently along each axis or empirically mix frequencies, which limits cross-dimensional interactions and yields direction-dependent representations. To address these limitations, we propose nD-RoPE, a decomposition-free generalization of RoPE to arbitrary dimensions. From a translation-invariant formulation in continuous Hilbert space, we derive a spectral condition for isotropy that requires treating positions and frequencies as coupled \(n\)-dimensional vectors. We instantiate this formulation with a multi-scale regular-simplex wave-vector design, which provides non-degenerate spatial coverage and a symmetric, directionally balanced second-order response. Experiments across images, videos, and point clouds demonstrate consistent performance gains and improved generalization in high-dimensional settings.

cs.LG↗

arXiv2026

Disaster-induced behavioral change restructures social networks toward bonding ties

Population displacement following environmental shocks reshapes the spatial organization of social interactions, often fragmenting existing ties and weakening community cohesion. Although social capital is widely recognized as a key determinant of resilience, its dynamic restructuring after disruption remains poorly quantified. Here, we develop a spatially embedded, dynamic network framework that operationalizes social capital as a network of repeated encounter opportunities inferred from large-scale mobility data. We construct temporal co-presence networks at third places to track how socio-spatial networks reorganize under disruption. We apply this framework to communities affected by the 2021 Marshall Fire in Colorado. We find that disaster-induced displacement leads to substantial contraction of socio-spatial networks, with mean weighted degree decreasing by 48%. To isolate underlying mechanisms, we develop two counterfactual models: a random node removal model and a behaviour-informed model in which individuals are removed based on their estimated propensity to evacuate. Both counterfactuals predict substantially lower connectivity than observed, indicating that post-disaster connectivity remains systematically higher than expected based on displacement behavior alone. Structural analysis of the network reveals that this residual connectivity is disproportionately concentrated among bonding ties between sociodemographically similar individuals, while bridging ties are comparatively fragile. Furthermore, interaction becomes increasingly located around third places, suggesting that these places act as spatial anchors for the persistence of social ties under disruption. Together, these findings provide a first empirical view of how behavioral responses to disruption shape community resilience through the reorganization of social networks.

physics.soc-ph↗

arXiv2026

Using large scale GPS data to reveal EV driver activity patterns beyond charging sessions

Accurate insights into electric vehicle (EV) driver behavior are essential for long-term infrastructure planning, grid management, and understanding downstream economic impacts, yet individual level data on EV mobility remains limited. Here, we develop a scalable framework to infer EV ownership and charging behavior from passively collected, high-resolution mobility traces covering over 760,000 drivers across four major U.S. metropolitan areas. We identify likely EV drivers based on distinctive visitation patterns to charging stations and gas stations, frequency of visits, and daily travel behavior, and calibrate cohort size using aggregate EV registration statistics. The resulting EV cohort closely matches official registration data at the zip code level and exhibits charging patterns consistent with independent, charger level benchmark datasets, providing external validation of the inferred population. Leveraging this inferred cohort, we reconstruct charging events and associated activity patterns to examine how EV drivers interact with surrounding urban amenities. Compared to non-EV drivers, EV drivers exhibit systematically higher visitation rates to nearby cafes and restaurants during charging sessions, revealing significant economic spillover effects. Furthermore, we find EV drivers exhibit trip bundling behavior, visiting more POIs over less time and distance on days where they charge versus all other days. These patterns are not observable in conventional charging session data, which lack behavioral context beyond the charging event itself. Our results demonstrate the potential of using mobility data to enable a richer, behaviorally grounded understanding of the off-plug needs of EV drivers, providing a foundation for optimizing charging infrastructure deployment and co-locating complementary urban amenities in an increasingly electrified transportation landscape.

physics.soc-ph↗

arXiv2026

Assessing the Feasibility of a Video-Based Conversational Chatbot Survey for Measuring Perceived Cycling Safety: A Pilot Study in New York City

Bicycle safety is important for bikeability and transportation efficiency. However, conventional surveys often fall short in capturing how people actually perceive cycling environments because they rely heavily on respondents' recall rather than in-the-moment experience. By leveraging large language models (LLMs), this study proposes a new method of combining video-based surveys with a conversational AI chatbot to collect human perceptions of cycling safety and the reasons behind these perceptions. The paper developed the AI chatbot using a modular LLM architecture, integrating prompt engineering, state management, and rule-based control to support the structure of human-AI interaction. This paper evaluates the feasibility of the proposed video-based conversational chatbot using complete responses from sixteen participants to the pilot survey across nine street segments in New York City. The method feasibility was assessed using a seven-point scale rating for user experience (i.e., ease of use, supportiveness, efficiency) and a five-point scale for chatbot usability (i.e., personality, roboticness, friendliness), yielding positive results with mean scores of 5.00 out of 7 (standard deviation = 1.6) and 3.47 out of 5 (standard deviation = 0.43), respectively. The data feasibility was assessed using multiple techniques: (1) Natural language processing (NLP), such as KeyBERT, for overall safety and feature analysis to extract built-environment attributes; (2) K-means clustering for semantic analysis to identify reasons and suggestions; and (3) regression to estimate the effects of built-environment and demographic variables on perceived safety outcomes. The results show the potential of AI chatbots as a novel approach to collecting data on human perception, behavior, and future visions for transport planning.

cs.CY↗

arXiv2026

Exploring Sidewalk Sheds in New York City through Chatbot Surveys and Human Computer Interaction

Sidewalk sheds are a common feature of the streetscape in New York City, reflecting ongoing construction and maintenance activities. However, policymakers and local business owners have raised concerns about reduced storefront visibility and altered pedestrian navigation. Although sidewalk sheds are widely used for safety, their effects on pedestrian visibility and movement are not directly measured in current planning practices. To address this, we developed an AI-based chatbot survey that collects image-based annotations and route choices from pedestrians, linking these responses to specific shed design features, including clearance height, post spacing, and color. This AI chatbot survey integrates a large language model (e.g., Google's Gemini-1.5-flash-001 model) with an image-annotation interface, allowing users to interact with street images, mark visual elements, and provide structured feedback through guided dialogue. To explore pedestrian perceptions and behaviors, this paper conducts a grid-based analysis of entrance annotations and applies logistic mixed-effects modeling to assess sidewalk choice patterns. Analysis of the dataset (n = 25) shows that: (1) the presence of scaffolding significantly reduces pedestrians' ability to identify ground-floor retail entrances, and (2) variations in weather conditions and shed design features significantly influence sidewalk selection behavior. By integrating generative AI into urban research, this study demonstrates a novel method for evaluating sidewalk shed designs and provides empirical evidence to support adjustments to shed guidelines that improve the pedestrian experience without compromising safety.

cs.HC↗

arXiv2026

Correcting temporal bias in mobility data using time-use surveys

GPS mobility data is a valuable source of behavioral measurement which is subject to systematic biases including the over- or under-representation of demographic groups, and variations in the quality of location sampling across time. In this paper, we address the challenge of temporal bias in mobility data, which can skew the representation of mobility behaviors due to the event-based nature of location data sampling. We use the American Time Use Survey (ATUS) to assess the accuracy of a place-based measure of economic segregation drawn from large-scale mobility data across 11 U.S. cities. We show that comparisons with high quality time use surveys such as the ATUS can validate behavioral insights from mobility data, while quantifying uncertainty and highlighting areas of relative instability in analytical findings. We also propose a temporal re-weighting method that can complement existing bias-mitigation techniques to improve the accuracy of conclusions drawn from GPS-based mobility data.

physics.soc-ph↗

arXiv2025

MoE-TransMov: A Transformer-based Model for Next POI Prediction in Familiar & Unfamiliar Movements

Accurate prediction of the next point of interest (POI) within human mobility trajectories is essential for location-based services, as it enables more timely and personalized recommendations. In particular, with the rise of these approaches, studies have shown that users exhibit different POI choices in their familiar and unfamiliar areas, highlighting the importance of incorporating user familiarity into predictive models. However, existing methods often fail to distinguish between the movements of users in familiar and unfamiliar regions. To address this, we propose MoE-TransMov, a Transformer-based model with a Transformer model with a Mixture-of-Experts (MoE) architecture designed to use one framework to capture distinct mobility patterns across different moving contexts without requiring separate training for certain data. Using user-check-in data, we classify movements into familiar and unfamiliar categories and develop a specialized expert network to improve prediction accuracy. Our approach integrates self-attention mechanisms and adaptive gating networks to dynamically select the most relevant expert models for different mobility contexts. Experiments on two real-world datasets, including the widely used but small open-source Foursquare NYC dataset and the large-scale Kyoto dataset collected with LY Corporation (Yahoo Japan Corporation), show that MoE-TransMov outperforms state-of-the-art baselines with notable improvements in Top-1, Top-5, Top-10 accuracy, and mean reciprocal rank (MRR). Given the results, we find that by using this approach, we can efficiently improve mobility predictions under different moving contexts, thereby enhancing the personalization of recommendation systems and advancing various urban applications.

cs.LG↗

arXiv2025

Causal spillover effects of electric vehicle charging station placement on local businesses: a staggered adoption study

Understanding the economic impacts of the placement of electric vehicle charging stations (EVCSs) is crucial for planning infrastructure systems that benefit the broader community. Theoretical models have been used to predict human behavior during charging events, however, these models have often neglected the complexity of trip patterns, and have underestimated the real-world impacts of such infrastructure on the local economy. In this paper, we design a quasi-experiment using mobile phone GPS location and EVCS deployment history data to analyze the causal impact of EVCS placement on visitation patterns to businesses. More specifically, we leverage the staggered placement of EVCSs in New York City and California Bay Area to match treated and control businesses that share similar characteristics including the business sector, location, and pre-treatment visitation count. By comparing three alternative matching strategies, we show that staggered adoption avoids selecting controls from non-treated clusters, and yields greater spatial overlap in dense urban areas. We find that EVCS installations significantly increase customer traffic, with effects concentrated in recreational venues in New York City and routine destinations such as groceries, pharmacies, and cafes in California Bay Area. Our results suggest that the economic spillovers of EVCSs vary across urban contexts and highlight the effectiveness of leveraging the staggered nature of adoption timings for evaluating infrastructure impacts in heterogeneous urban environments.

physics.soc-ph↗

arXiv2025

Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency

Time series forecasting plays a pivotal role in critical domains such as energy management and financial markets. Although deep learning-based approaches (e.g., MLP, RNN, Transformer) have achieved remarkable progress, the prevailing "long-sequence information gain hypothesis" exhibits inherent limitations. Through systematic experimentation, this study reveals a counterintuitive phenomenon: appropriately truncating historical data can paradoxically enhance prediction accuracy, indicating that existing models learn substantial redundant features (e.g., noise or irrelevant fluctuations) during training, thereby compromising effective signal extraction. Building upon information bottleneck theory, we propose an innovative solution termed Adaptive Masking Loss with Representation Consistency (AMRC), which features two core components: 1) Dynamic masking loss, which adaptively identified highly discriminative temporal segments to guide gradient descent during model training; 2) Representation consistency constraint, which stabilized the mapping relationships among inputs, labels, and predictions. Experimental results demonstrate that AMRC effectively suppresses redundant feature learning while significantly improving model performance. This work not only challenges conventional assumptions in temporal modeling but also provides novel theoretical insights and methodological breakthroughs for developing efficient and robust forecasting models.

cs.LG↗

arXiv2025

Social homophily predicts evacuation destination choice and long-term displacement decisions after the Marshall Fire

Rapid urbanization and climate change have contributed to a significant rise in the frequency and intensity of disasters, which have resulted in three million adults being displaced from their homes in the United States during the past year. Using large-scale mobility data, it is now possible to observe and analyze post-disaster mobility dynamics across a longer time period, compared to household surveys which are often limited in scale. However, much of the mobility data-driven research on evacuation and displacement destination choice behavior has often underemphasized the role of social factors, including individual preferences and social connections. To this end, we use large-scale data of anonymized GPS traces and online social connections from the Marshall Fires in Colorado, USA, to unravel the associations between social and behavioral factors and evacuation destinations and long-term displacement decisions. We find that behavioral characteristics and social homophily play a significant role in post-disaster mobility decisions. Conditioned on the same evacuation distance, evacuees chose locations that have a high sociodemographic homophily with their home locations, and locations that have more friendship connections, compared to the level of homophily they are spatially exposed to. The social homophily effect is stronger among White and educated populations than low income, and Black and Asian populations. This effect has significant implications for long-term disaster impacts and policymaking, as it is a significant predictor of displacement and return decisions. Our findings highlight the importance of incorporating the social, behavioral, and economic characteristics to better understand and predict evacuation and displacement dynamics after disasters.

physics.soc-ph↗

arXiv2025

Causal Impacts of Protected Bike Lanes on Cycling Behavior with Demographic Disparities

Cities around the world face significant barriers to grow urban cycling, including competing budgetary priorities and car-centric streets. Thus, when making decisions regarding the installation of bicycle infrastructure, it is crucial to understand if and to what extent different bicycle-lane types increase bicycle ridership. However, associations between bicycle infrastructure and bicycle ridership have primarily been studied in the context of individual lanes and corridors, or when analyzed at the scale of entire cities, generalized across different bike-lane types. Drawing upon 72 million bikeshare trips from Citi Bike in New York, we demonstrate that there is an approximately 18% increase in bikeshare trips at adjacent stations in the 12 months following the installation of protected bike lanes (those with a physical barrier between cyclists and automobile traffic) and a 14% increase associated with painted bike lanes (where a line of pavement marking is present) and `sharrows' (where a normal traffic lane is marked with a bike stencil). However, using a difference-in-differences analysis, we detect a causal effect on bikeshare ridership only following the installation of protected bike lanes, with an average monthly increase of 379 rides per station (p<0.001). Despite this causal effect being pronounced among census block groups with higher percentages of older adults (688 rides per month per station, p<0.001), the causal effect of protected bike lanes on bikeshare ridership is absent in census block groups where the percentage of Black residents is medium to high. Taken together, these findings indicate that planners must emphasize protected bike lanes to spur ridership, and simultaneously target policies and programming to communities of color, to ensure that such infrastructure makes urban cycling a viable option for all residents.

physics.soc-ph↗

arXiv2025

MobiCLR: Mobility Time Series Contrastive Learning for Urban Region Representations

Recently, learning effective representations of urban regions has gained significant attention as a key approach to understanding urban dynamics and advancing smarter cities. Existing approaches have demonstrated the potential of leveraging mobility data to generate latent representations, providing valuable insights into the intrinsic characteristics of urban areas. However, incorporating the temporal dynamics and detailed semantics inherent in human mobility patterns remains underexplored. To address this gap, we propose a novel urban region representation learning model, Mobility Time Series Contrastive Learning for Urban Region Representations (MobiCLR), designed to capture semantically meaningful embeddings from inflow and outflow mobility patterns. MobiCLR uses contrastive learning to enhance the discriminative power of its representations, applying an instance-wise contrastive loss to capture distinct flow-specific characteristics. Additionally, we develop a regularizer to align output features with these flow-specific representations, enabling a more comprehensive understanding of mobility dynamics. To validate our model, we conduct extensive experiments in Chicago, New York, and Washington, D.C. to predict income, educational attainment, and social vulnerability. The results demonstrate that our model outperforms state-of-the-art models.

cs.LG↗

arXiv2023

Behavior-based dependency networks between places shape urban economic resilience

Urban economic resilience is intricately linked to how disruptions caused by pandemics, disasters, and technological shifts ripple through businesses and urban amenities. Disruptions, such as closures of non-essential businesses during the COVID-19 pandemic, not only affect those places directly but also influence how people live and move, spreading the impact on other businesses and increasing the overall economic shock. However, it is unclear how much businesses depend on each other in these situations. Leveraging large-scale human mobility data and millions of same-day visits in New York, Boston, Los Angeles, Seattle, and Dallas, we quantify dependencies between points-of-interest (POIs) encompassing businesses, stores, and amenities. Compared to places' physical proximity, dependency networks computed from human mobility exhibit significantly higher rates of long-distance connections and biases towards specific pairs of POI categories. We show that using behavior-based dependency relationships improves the predictability of business resilience during shocks, such as the COVID-19 pandemic, by around 40% compared to distance-based models. Simulating hypothetical urban shocks reveals that neglecting behavior-based dependencies can lead to a substantial underestimation of the spatial cascades of disruptions on businesses and urban amenities. Our findings underscore the importance of measuring the complex relationships woven through behavioral patterns in human mobility to foster urban economic resilience to shocks.

physics.soc-ph↗

arXiv2023

Metropolitan Scale and Longitudinal Dataset of Anonymized Human Mobility Trajectories

Modeling and predicting human mobility trajectories in urban areas is an essential task for various applications. The recent availability of large-scale human movement data collected from mobile devices have enabled the development of complex human mobility prediction models. However, human mobility prediction methods are often trained and tested on different datasets, due to the lack of open-source large-scale human mobility datasets amid privacy concerns, posing a challenge towards conducting fair performance comparisons between methods. To this end, we created an open-source, anonymized, metropolitan scale, and longitudinal (90 days) dataset of 100,000 individuals' human mobility trajectories, using mobile phone location data. The location pings are spatially and temporally discretized, and the metropolitan area is undisclosed to protect users' privacy. The 90-day period is composed of 75 days of business-as-usual and 15 days during an emergency. To promote the use of the dataset, we will host a human mobility prediction data challenge (`HuMob Challenge 2023') using the human mobility dataset, which will be held in conjunction with ACM SIGSPATIAL 2023.

cs.SI↗

arXiv2022

GEO-BLEU: Similarity Measure for Geospatial Sequences

In recent geospatial research, the importance of modeling large-scale human mobility data and predicting trajectories is rising, in parallel with progress in text generation using large-scale corpora in natural language processing. Whereas there are already plenty of feasible approaches applicable to geospatial sequence modeling itself, there seems to be room to improve with regard to evaluation, specifically about measuring the similarity between generated and reference trajectories. In this work, we propose a novel similarity measure, GEO-BLEU, which can be especially useful in the context of geospatial sequence modeling and generation. As the name suggests, this work is based on BLEU, one of the most popular measures used in machine translation research, while introducing spatial proximity to the idea of n-gram. We compare this measure with an established baseline, dynamic time warping, applying it to actual generated geospatial sequences. Using crowdsourced annotated data on the similarity between geospatial sequences collected from over 12,000 cases, we quantitatively and qualitatively show the proposed method's superiority.

cs.LG↗

arXiv2022

Behavioral changes during the pandemic worsened income diversity of urban encounters

Diversity of physical encounters and social interactions in urban environments are known to spur economic productivity and innovation in cities, while also to foster social capital and resilience of communities. However, mobility restrictions during the pandemic have forced people to substantially reduce urban physical encounters, raising questions on the social implications of such behavioral changes. In this paper, we study how the income diversity of urban encounters have changed during different periods throughout the pandemic, using a large-scale, privacy-enhanced mobility dataset of more than one million anonymized mobile phone users in four large US cities, collected across three years spanning before and during the pandemic. We find that the diversity of urban encounters have substantially decreased (by 15% to 30%) during the pandemic and has persisted through late 2021, even though aggregated mobility metrics have recovered to pre-pandemic levels. Counterfactual analyses show that while the reduction of outside activities (higher rates of staying at home) was a major factor that contributed to decreased diversity in the early stages of the pandemic, behavioral changes including lower willingness to explore new places and changes in visitation preferences further worsened the long-term diversity of encounters. Our findings suggest that the pandemic could have long-lasting negative effects on urban income diversity, and provide implications for managing the trade-off between the stringency of COVID-19 policies and the diversity of urban encounters as we move beyond the pandemic.

physics.soc-ph↗

arXiv2022

Universal decomposition algebras and the classification of 2-generated non-primitive axial algebras of Jordan type

Decomposition algebras and axial decomposition algebras are classes of commutative nonassociative algebras which are generalizations of axial algebras. The classes decomposition algebras, axial decomposition al;gebras and non-primitive axial algebras also have univesal algebras. Furthermore, by using the existence of a universal algebra, 2-generated non-primitive axial algebras of Jordan type is classified.

math.RA↗