Skin-toned emojis are crucial for fostering personal identity and social inclusion in online communication. As AI models, particularly Large Language Models (LLMs), increasingly mediate interactions on web platforms, the risk that these systems perpetuate societal biases through their representation of such symbols is a significant concern. This paper presents the first large-scale comparative study of bias in skin-toned emoji representations across two distinct model classes. We systematically evaluate dedicated emoji embedding models (emoji2vec, emoji-sw2v) against four modern LLMs (Llama, Gemma, Qwen, and Mistral). Our analysis first reveals a critical performance gap: while LLMs demonstrate robust support for skin tone modifiers, widely-used specialized emoji models exhibit severe deficiencies. More importantly, a multi-faceted investigation into semantic consistency, representational similarity, sentiment polarity, and core biases uncovers systemic disparities. We find evidence of skewed sentiment and inconsistent meanings associated with emojis across different skin tones, highlighting latent biases within these foundational models. Our findings underscore the urgent need for developers and platforms to audit and mitigate these representational harms, ensuring that AI's role on the web promotes genuine equity rather than reinforcing societal biases.

Spatiotemporal prediction plays a critical role in numerous real-world applications such as urban planning, transportation optimization, disaster response, and pandemic control. In recent years, researchers have made significant progress by developing advanced deep learning models for spatiotemporal prediction. However, most existing models are deterministic, i.e., predicting only the expected mean values without quantifying uncertainty, leading to potentially unreliable and inaccurate outcomes. While recent studies have introduced probabilistic models to quantify uncertainty, they typically focus on a single phenomenon (e.g., taxi, bike, crime, or traffic crashes), thereby neglecting the inherent correlations among heterogeneous urban phenomena. To address the research gap, we propose a novel Graph Neural Network with Uncertainty Quantification, termed UQGNN for multivariate spatiotemporal prediction. UQGNN introduces two key innovations: (i) an Interaction-aware Spatiotemporal Embedding Module that integrates a multivariate diffusion graph convolutional network and an interaction-aware temporal convolutional network to effectively capture complex spatial and temporal interaction patterns, and (ii) a multivariate probabilistic prediction module designed to estimate both expected mean values and associated uncertainties. Extensive experiments on four real-world multivariate spatiotemporal datasets from Shenzhen, New York City, and Chicago demonstrate that UQGNN consistently outperforms state-of-the-art baselines in both prediction accuracy and uncertainty quantification. For example, on the Shenzhen dataset, UQGNN achieves a 5% improvement in both prediction accuracy and uncertainty quantification.

1. Human dynamics has become a central frontier in GIScience. Defined as the study of human activities, interactions, and mobility across space and time in today’s hybrid physical-virtual world, it...

Extracting spatial network structure (SNS) from large-scale origin-destination flow data is an important approach for understanding interregional association patterns and interaction laws. Currently, the extraction of SNS primarily relies on complex network clustering or aggregated statistics with predefined regional constraints. However, these methods often overlook one or more fundamental principles essential for ensuring correctness and accuracy: 1) Aggregation of spatially proximate nodes is necessary when strong interactions exist, whereas separation is preferred in the absence of such interactions. 2) It is crucial to maintain strong interactions between non-spatially proximate nodes. 3) Ultimately, nodes within each group should exhibit spatial continuity. To address these challenges, a multi-hierarchical SNS extraction method is proposed, which focuses on raw node aggregating and generalization, measurement of interaction volume and strength between node groups and strategies for node/edge filtering. The effectiveness and value of the proposed method are demonstrated through a case study using city population migration data. Furthermore, the method provides a general approach for extracting SNSs from any origin-destination flow dataset that includes locations and weights, facilitating effective flow map generalization through aggregation of origin destination (OD) flow data.

An organized knowledge base can facilitate the exploration of existing knowledge and the detection of emerging topics in a domain. Knowledge about and around Geographic Information Science and its associated system technologies (GIS) is complex, extensive and emerging rapidly. Taking the challenge, we built a GIS knowledge graph (GIS-KG) by (1) merging existing GIS bodies of knowledge to create a hierarchical ontology and then (2) applying deep-learning methods to map GIS publications to the ontology. We conducted several experiments on information retrieval to evaluate the novelty and effectiveness of the GIS-KG. Results showed the robust support of GIS-KG for knowledge search of existing GIS topics and potential to explore emerging research themes.

Street view imagery such as Google Street View is widely used in people’s daily lives. Many studies have been conducted to detect and map objects such as traffic signs and sidewalks for urban built-up environment analysis. While mapping objects in the horizontal dimension is common in those studies, automatic vertical measuring in large areas is underexploited. Vertical information from street view imagery can benefit a variety of studies. One notable application is estimating the lowest floor elevation, which is critical for building flood vulnerability assessment and insurance premium calculation. In this article, we explored the vertical measurement in street view imagery using the principle of tacheometric surveying. In the case study of lowest floor elevation estimation using Google Street View images, we trained a neural network (YOLO-v5) for door detection and used the fixed height of doors to measure doors’ elevation. The results suggest that the average error of estimated elevation is 0.218 m. The depthmaps of Google Street View were utilized to traverse the elevation from the roadway surface to target objects. The proposed pipeline provides a novel approach for automatic elevation estimation from street view imagery and is expected to benefit future terrain-related studies for large areas.

A spatial social network (SSN) can be defined as a set of agent-based connections that are embedded in geographic space. SSNs range in size from small networks of connections within a group of peop...

Videos embedded with spatial coordinates, especially when combined with additional expert insights, offer the potential to acquire fine-scale multi-time period contextualized data for a variety of different environments. However, while these geospatial multimedia (GSMM) data include abundant spatiotemporal, semantic and visual information, the means to fully leverage their potential using a suite of visual and interactive analysis techniques and tools has thus far been lacking. In this paper, we address this gap by first identifying the types of tasks required of GSMM data, and then presenting a solution platform. This GeoVisuals system utilizes a visual analysis approach built on semantic data points that can be integrated spatially, which in turn enables management in a unified database with combined spatio-temporal and text querying. A set of visualization functions are integrated in two investigation modes: geo-video analysis and geo-location analysis.

In this paper, we present a community-focused drug abuse monitoring and supporting system, called DrugTracker, that utilizes social media and geospatial data in near real-time. Through the system, users can: (1) Detect drug abuse risk behaviors from social media platforms, e.g., Twitter; (2) Analyze drug abuse risk behaviors by querying consolidated and live datasets with keywords, spatial entities, and time constraints; and (3) Explore the query results and associated data through a web-based user interface in thematic choropleth, heatmap, and statistical charts. To protect the privacy of the Twitter users, whose data is collected, the system automatically hides the re-identification elements in tweets and aggregates the geo-tags into areas such as census tracts. For the demonstration purpose, our DrugTracker system is populated with a database that contains about 10 million tweets from the year 2017, that were annotated as drug abuse risk behavior positive by our deep learning model.

In police planning, a territory is often divided into several patrol districts with balanced workloads, in order to repress crime and provide better police service. Conventionally, in this districting problem, there is insufficient consideration of the impacts of street networks. In this study, we propose a street-network police districting problem (SNPDP) that explicitly uses streets as basic underlying units. This model defines the workload as a combination of different attributes and seeks an efficient and balanced design of districts. We also develop an efficient heuristic to generate high-quality districting plans in an acceptable time. The capability of the algorithm is demonstrated in comparison to an exact linear programming solver on simulated datasets. The SNPDP model is successfully implemented and tested in a case study in London, and the generated police districts have different characteristics that are consistent with the crime risk and land use distribution. Besides, we demonstrate that SNPDP is superior to an aggregation grid-based model regarding the solution quality. This model has the potential to generate street-based districts with balanced workloads for other districting problems, such as school districting and health care districting.

This article reports the findings from simulating the spatial diffusion processes of memes over social media networks by using the approach of agent-based modeling. Different from other studies, this article examines how space and distance affect the diffusion of memes. Simulations were carried out to emulate and to allow assessment of the different levels of efficiency that memes spread spatially and temporally. Analyzed network structures include random networks and preferential attachment networks. Simulated spatial processes for meme diffusion include independent cascade models and linear threshold models. Both simulated and real-world social networks were used in the analysis. Findings indicate that the numbers of information sources and opinion leaders affect the processes of meme diffusion. In addition, geography is still important in the processes of spatial diffusion of memes over social media networks.

The population distribution grid at fine scales better reflects the distribution of residents and plays an important role in investigating urban systems. The recent years have witnessed a growing trend of applying the nighttime light data to the estimation of population at micro levels. However, using the nighttime light data alone to estimate population may cause the overestimation problem due to excessively high light radiance in specific types of areas such as commercial zones and transportation hubs. In dealing with this issue, this study used taxi trajectory data that delineate people’s movements, and explored the utility of integrating the nighttime light and taxi trajectory data in the estimation of population in Shanghai at the spatial resolution of 500 m. First, the initial population distribution grid was generated based on the NPP-VIIRS nighttime light data. Then, a calibration grid was created with taxi trajectory data, whereby the initial population grid was optimized. The accuracy of the resultant population grid was assessed by comparing it with the refined survey data. The result indicates that the final population distribution grid performed better than the initial population grid, which reflects the effectiveness of the proposed calibration process.

The saturation of night light data caused by sensor defects conceals the differences and details of light luminance in the urban area, which greatly limits the application of Nighttime Light (NTL) in the study of urbanization. Although some methods have been proposed to mitigate the saturation of NTL data, the research of desaturation is worth further advancing due to its shortcomings in highlighting light differences and spatial resolution. Therefore, we propose a new spectral index, the Vector Data Adjusted NTL Index (VDANTLI) after analyzing the influence of different auxiliary parameters on saturation elimination. Then, we select the three most developed urban agglomerations in China and make a series of qualitative and quantitative analysis. The results of various assessments confirm that VDANTLI can effectively alleviate NTL saturation and enhance urban lighting differences. Moreover, by dynamically adjusting the length of the grid and single-phase vector data modified time-series NTL data, we further achieve the resolution-series and time-series VDANTLI. Therefore, compared with previous desaturation models, the VDANTLI can be used as an effective indicator and even an indispensable basic data for urbanization research and socio-economic spatial analysis because of its unique advantages in spatial resolution and the capability in time-series native NTL desaturation.

Social media analytics has become prominent in natural disaster management. In spite of a large variety of metadata fields in social media data, four dimensions (i.e. space, time, content and network) have been given particular attention for mining useful information to gain situational awareness and improve disaster response. In this article, we review how existing studies analyze these four dimensions, summarize common techniques for mining these dimensions, and then suggest some methods accordingly. We then propose a schema to categorize the gathered articles into 15 classes and facilitate the generation of data analysis tasks. We find that (1) a large part of studies involve multiple dimensions of social media data in their analyses, (2) there are both separate analyses for each dimension and simultaneous analyses for multiple dimensions and (3) there are fewer simultaneous analyses as dimensions increase. Finally, we suggest research opportunities and challenges in fusing social media data with authoritative datasets, i.e. census data and remote-sensing data.

News articles capture a variety of topics about our society. They reflect not only the socioeconomic activities that happened in our physical world, but also some of the cultures, human interests, and public concerns that exist only in the perceptions of people. Cities are frequently mentioned in news articles, and two or more cities may co-occur in the same article. Such co-occurrence often suggests certain relatedness between the mentioned cities, and the relatedness may be under different topics depending on the contents of the news articles. We consider the relatedness under different topics as semantic relatedness. By reading news articles, one can grasp the general semantic relatedness between cities; yet, given hundreds of thousands of news articles, it is very difficult, if not impossible, for anyone to manually read them. This paper proposes a computational framework which can ‘read’ a large number of news articles and extract the semantic relatedness between cities. This framework is based on a natural language processing model and employs a machine learning process to identify the main topics of news articles. We describe the overall structure of this framework and its individual modules, and then apply it to an experimental dataset with more than 500,000 news articles covering the top 100 US cities spanning a 10-year period. We perform exploratory visualizations of the extracted semantic relatedness under different topics and over multiple years. We also analyze the impact of geographic distance on semantic relatedness and find varied distance decay effects. The proposed framework can be used to support large-scale content analysis in city network research.

Information about the functions of urban buildings is helpful not only for developing a better understanding of how cities work, but also for establishing a basis for policy makers to evaluate and improve the effectiveness of urban planning. Despite these advantages, however, and perhaps simply due to a lack of available data, few academic studies to date have succeeded in integrating multi-source ‘big data’ to examine urban land use at the building level. Responding to this deficiency, this study integrated multi-source big data (WeChat users’ real-time location records, taxi GPS trajectories data, Points of Interest (POI) data, and building footprint data from high-resolution Quickbird images), and applied the proposed density-based method to infer the functions of urban buildings in Tianhe District, Guangzhou, China. The results of the study conformed to an overall detection rate of 72.22%. When results were verified against ground-truth investigation data, the accuracy rate remained above 65%. Two important conclusions can be drawn from our analysis: 1.The use of WeChat data delivers better inference results than those obtained using taxi data when used to identify residential buildings, offices, and urban villages. Conversely, shopping centers, hotels, and hospitals, were more easily identified using taxi data. 2. The use of integrated multi-source big data is more effective than single-source big data in revealing the relation between human dynamics and urban complexes at the building scale.

This paper introduces a new p-regions model called the Network-Max-P-Regions (NMPR) model. The NMPR is a regionalization model that aims to aggregate n areas into the maximum number of regions (max-p) that satisfy a threshold constraint and to minimize the heterogeneity while taking into account the influence of a street network. The exact formulation of the NMPR is presented, and a heuristic solution is proposed to effectively compute the near-optimized partitions in several simulation datasets and a case study in Wuhan, China.

Spatial clustering can be used to discover hotspots in trajectory data. A trajectory clustering approach based on decision graph and data field is proposed as an effective method to select parameters for clustering, to determine the number of clusters, and to identify cluster centers. Synthetic data and real-world taxi trajectory data are utilized to demonstrate the effectiveness of the proposed approach. Results show that the proposed method can automatically determine the parameters for clustering as well as perform efficiently in trajectory clustering. Hotspots are identified and visualized during different times of a single day and at the same times on different days. The dynamic patterns of hotspots can be used to identify crowded areas and events, which are crucial for urban transportation planning and management.

Human dynamics is a term that has been used and investigated by researchers in various fields from very different perspectives. Barabási’s (2005) publication of ‘The origin of bursts and heavy tail...