Geosocial Media Research Articles

Contextual Enrichment of Crowds from Mobile Phone Data through Multimodal Geo-Social Media Analysis

Contextual Enrichment of Crowds from Mobile Phone Data through Multimodal Geo-Social Media Analysis

A Breakdown of Subjective Reactions in Geo-Social Media and a Review of Their Cartographic Visualisation

A Breakdown of Subjective Reactions in Geo-Social Media and a Review of Their Cartographic Visualisation

Towards Mapping Place Semantics: A Geosocial Media Data Approach for Geo-Semantic Analysis and Place Similarity Computation

Towards Mapping Place Semantics: A Geosocial Media Data Approach for Geo-Semantic Analysis and Place Similarity Computation

Multimodal Geo-Information Extraction from Social Media for Supporting Decision-Making in Disaster Management

Abstract. Effective decision-making in natural disaster management relies heavily on a comprehensive understanding of the situation in affected areas. Social media has been established as a tool to monitor human response and damage assessment. Given the vast amounts of data available, computational methods such as topic modelling are typically employed to reduce information complexity. However, these methods mostly neglect aspects such as geographic location and emotional response, which frequently results in sequential workflows of initial semantic filtering and subsequent spatial or spatio-temporal analysis. This study presents a novel approach for multimodal information extraction from geo-social media data for aiding decision support in disaster management. The method leverages a spatial, temporal, semantic, and sentiment-based clustering approach of social media posts to extract clusters that provide insights into disaster-related content. A case study in the Ahr Valley region in Germany demonstrates the method’s effectiveness in providing actionable insights for disaster response and management. The approach offers a tool for the quick assessment of disaster-related information from social media, potentially aiding timely and informed decision-making.

Drowning in the Information Flood: Machine-Learning-Based Relevance Classification of Flood-Related Tweets for Disaster Management

In the early stages of a disaster caused by a natural hazard (e.g., flood), the amount of available and useful information is low. To fill this informational gap, emergency responders are increasingly using data from geo-social media to gain insights from eyewitnesses to build a better understanding of the situation and design effective responses. However, filtering relevant content for this purpose poses a challenge. This work thus presents a comparison of different machine learning models (Naïve Bayes, Random Forest, Support Vector Machine, Convolutional Neural Networks, BERT) for semantic relevance classification of flood-related, German-language Tweets. For this, we relied on a four-category training data set created with the help of experts from human aid organisations. We identified fine-tuned BERT as the most suitable model, averaging a precision of 71% with most of the misclassifications occurring across similar classes. We thus demonstrate that our methodology helps in identifying relevant information for more efficient disaster management.

Generative Text-to-Image Diffusion for Automated Map Production Based on Geosocial Media Data

The state of generative AI has taken a leap forward with the availability of open source diffusion models. Here, we demonstrate an integrated workflow that uses text-to-image stable diffusion at its core to automatically generate icon maps such as for the area of the Großer Garten, a tourist hotspot in Dresden, Germany. The workflow is based on the aggregation of geosocial media data from Twitter, Flickr, Instagram and iNaturalist. This data are used to create diffusion prompts to account for the collective attribution of meaning and importance by the population in map generation. Specifically, we contribute methods for simplifying the variety of contexts communicated on social media through spatial clustering and semantic filtering for use in prompts, and then demonstrate how this human-contributed baseline data can be used in prompt engineering to automatically generate icon maps. Replacing labels on maps with expressive graphics has the general advantage of reaching a broader audience, such as children and other illiterate groups. For example, the resulting maps can be used to inform tourists of all backgrounds about important activities, points of interest, and landmarks without the need for translation. Several challenges are identified and possible future optimizations are described for different steps of the process. The code and data are fully provided and shared in several Jupyter notebooks, allowing for transparent replication of the workflow and adoption to other domains or datasets.

Visualizing emoji usage in geo-social media across time, space, and topic

Social media is ubiquitous in the modern world and its use is ever-increasing. Similarly, the use of emojis within social media posts continues to surge. Geo-social media produces massive amounts of spatial data that can provide insights into users' thoughts and reactions across time and space. This research used emojis as an alternative to text-based social media analysis in order to avoid the common obstacles of natural language processing such as spelling mistakes, grammatical errors, slang, and sarcasm. Because emojis offer a non-verbal means to express thoughts and emotions, they provide additional context in comparison to purely text-based analysis. This facilitates cross-language studies. In this study, the spatial and temporal usage of emojis were visualized in order to detect relevant topics of discussion within a Twitter dataset that is not thematically pre-filtered. The dataset consists of Twitter posts that were geotagged within Europe during the year 2020. This research leveraged cartographic visualization techniques to detect spatial-temporal changes in emoji usage and to investigate the correlation of emoji usage with significant topics. The spatial and temporal developments of these topics and their respective emojis were visualized as a series of choropleth maps and map matrices. This geovisualization technique allowed for individual emojis to be independently analyzed and for specific spatial or temporal trends to be further investigated. Emoji usage was found to be spatially and temporally heterogeneous, and trends in emoji usage were found to correlate with topics including the COVID-19 pandemic, several political movements, and leisure activities.

From sunrise to sunset: Exploring landscape preference through global reactions to ephemeral events captured in georeferenced social media.

Events profoundly influence human-environment interactions. Through repetition, some events manifest and amplify collective behavioral traits, which significantly affects landscapes and their use, meaning, and value. However, the majority of research on reaction to events focuses on case studies, based on spatial subsets of data. This makes it difficult to put observations into context and to isolate sources of noise or bias found in data. As a result, inclusion of perceived aesthetic values, for example, in cultural ecosystem services, as a means to protect and develop landscapes, remains problematic. In this work, we focus on human behavior worldwide by exploring global reactions to sunset and sunrise using two datasets collected from Instagram and Flickr. By focusing on the consistency and reproducibility of results across these datasets, our goal is to contribute to the development of more robust methods for identifying landscape preference using geo-social media data, while also exploring motivations for photographing these particular events. Based on a four facet context model, reactions to sunset and sunrise are explored for Where, Who, What, and When. We further compare reactions across different groups, with the aim of quantifying differences in behavior and information spread. Our results suggest that a balanced assessment of landscape preference across different regions and datasets is possible, which strengthens representativity and exploring the How and Why in particular event contexts. The process of analysis is fully documented, allowing transparent replication and adoption to other events or datasets.

Mapping indicators of cultural ecosystem services use in urban green spaces based on text classification of geosocial media data

In our increasingly urbanized world, the cultural ecosystem services (CES) provided by urban nature play a crucial role in enabling and maintaining the well-being of urban dwellers. Despite the increased number of studies leveraging geosocial media data for more efficient and socio-cultural-oriented CES assessment, the high complexity and costs associated with existing methods such as manual or automated image classification hinder their application in urban planning and ecosystems management. This study introduces a novel method that draws on the semantic similarity between word2vec word embeddings to classify large volumes of geosocial media textual metadata and quantify indicators of CES use. We demonstrated the applicability of our approach by quantifying spatial patterns of aesthetic appreciation and wildlife recreation in the green spaces of the city of Dresden based on the classification of >50,000 geotagged Instagram and Flickr posts. Moreover, we analyzed and mapped semantic patterns embedded in geosocial media and gained essential insights that can contribute toward a context-dependent assessment of CES use, which in turn can help inform decision making for more sustainable planning and management of urban ecosystems. The performance evaluation of the classification proves the validity of the proposed unsupervised text classification approach as a practical, reliable, and more efficient alternative to laborious and expensive annotation efforts required by manual or supervised classification methods.

Follow the Geographic Information: The Challenges of Spatial Analysis in Digital Methods

In the digital environment, defined as a space with no anchors (Menduni 2014), the spatial dimension may have a significant role, mostly in relation to the Internet or digital studies. Social Media Geographic Information (Campagna et al. 2016), even if limited, can be highly useful to overcome some limitations of social media analysis and user generated content. With the objective to report the potential and limits of this approach, in this article a case study will be presented on the individual perception related to COVID-19 in Italy. Starting from the analysis of ecological data and the social media data, we reproduce three measures by exploring three different elements that could be anchored to a geographical dimension: the storytelling of COVID (COVID-Issues), the spread of infection (COVID-Spread), and the distribution of measures (COVID-Measures) to understand the regional trends of the second wave of the pandemic emergence that represent the timespan of this contribution. Keywords: geo-social media, twitter, ecological analysis, case study, API

Categorizing urban space based on visitor density and diversity: A view through social media data

Analyses of urban spaces have often stressed the importance of both the density and diversity of the people they attract. However, the diversity of people is a challenging concept to operationalize within the context of urban spaces, which is why many evaluations of urban space have relied primarily on density-based measures. We argue that a focus on only one of the two aspects misses important aspects of the variety of urban spaces in our cities. To address this, we design a methodology that evaluates both the density and diversity of human behavior in urban spaces based on geosocial media data. We operationalize density as the frequency of tweets from visitors to a particular location and diversity as the variety of the home neighborhoods of those visitors. Taking Singapore as a test case, we identify networks between the home neighborhoods of 28k Twitter users based on 2.2 million geolocated tweets collected between 2012 and 2016. Based on these data, we categorize the urban landscape of Singapore into four “performance” categories, namely High-Density/High-Diversity, High-Density/Low-Diversity, Low-Density/High-Diversity, and Low-Density/Low-Diversity. Our findings illustrate that this combined indicator provides useful nuance compared to differentiation between well and less performing spaces based on density alone. By enabling a categorization of urban spaces that fits closer to the diversity of human behavior in these spaces, human mobility data sets, such as the social media data we use, open the door to a practical evaluation of the design and planning of our heterogeneous urban environment.

Emojis as indicators of spatial-temporal-thematic developments in geo-social media

Emojis as indicators of spatial-temporal-thematic developments in geo-social media

The typicality measure as a novel tool for normalising geo-social media data

The typicality measure as a novel tool for normalising geo-social media data

Exploring spatiotemporal patterns of geosocial media data for urban functional zone identification

Urban Functional Zones (UFZs) can be identified by measuring the spatiotemporal patterns of activities that occur within them. Geosocial media data possesses abundant spatial and temporal information for activity mining. Identifying UFZs from geosocial media data aids urban planning, infrastructure, resource allocation, and transportation modernization in the complex urban system. In this work, we proposed an integrated approach by combining the spatiotemporal clustering method with a machine learning classifier. The spatiotemporal clustering method was used to mine the spatiotemporal patterns of activities, of which the distinctive features were extracted as inputs into a machine learning classifier for UFZ identification. The results show that more than 80% of the UFZs can be correctly identified by our proposed method. It reveals that this work serves as a functional groundwork for future studies, facilitating the understanding of urban systems as well as promoting sustainable urban development.

Analyzing the EU Migration Crisis as Reflected on Twitter

The proliferation of social media has resulted in its extensive use as a valuable source of information for researchers. This paper aims to use Twitter data to analyze and visualize tweets about the migration crisis in the European Union from 2016 to 2021. The paper uses a methodology to structure data for better understanding of complex social media data. The methods and metrics include the facet model of location based social media, the HyperLogLog data structure and novel uses of the metric typicality. The authors have also developed a web based interactive application closely following the methodology used to organize the dataset. Additionally the work also includes maps using spatial typicality which could be utilized for studying spatial phenomenon. The case study selected also provides unique insights and sets a template for working with multi-lingual geo-social media data. The authors believe that these methods and metrics could be reproduced for other case studies and aid in understanding and communication geo-social media data.

Detecting spatiotemporal traffic events using geosocial media data

Social media platforms enable efficient traffic event detection by allowing users to produce geo-tagged content (e.g., tweets) known as geosocial media data. Geosocial media data improve road safety by providing timely updates for traffic flow and traffic control. Recent studies on traffic event detection with geosocial media data have been focused around keyword-based query approaches, where the event content was inferred by predetermined categories, to retrieve relevant traffic events. Spatiotemporal features associated with traffic-related posts have not been fully investigated. In this study, we filtered irrelevant posts with association rules. A spatiotemporal clustering-based method was then used to retrieve traffic events from these filtered posts, where the content of detected events was automatically inferred with a set of representative terms. For comparison, a typical text classification-based method was also used by classifying the posts filtered from association rules into different categories. By validating the detection results with vehicle travel speed data, we demonstrate that the former outperforms the latter in terms of the number of correctly detected traffic events from one-year of Twitter data in Toronto, Canada. Our proposed approach helps organizations and governments to be aware of when and where traffic events occur by identifying event hotspots and peak periods, which improves both traffic management and urban planning.

Entangled footprints: Understanding urban neighbourhoods by measuring distance, diversity, and direction of flows in Singapore

Traditional approaches to human mobility analysis in Geography often rely on census or survey data that is resource-intensive to collect and often has a limited spatio-temporal scope. The advent of new technologies (e.g. geosocial media platforms) provides opportunities to overcome these limitations and, if properly leveraged, can yield more granular insights about human mobility. In this paper, we use an anonymized Twitter dataset collected in Singapore from 2012 to 2016 to investigate this potential to help understand the footprints of urban neighbourhoods from both a spatial and a relational perspective.We construct home-to-destination networks of individual users based on their inferred home locations. In aggregated form, these networks allow us to analyze three specific mobility indicators at the neighbourhood level, namely the distance, diversity, and direction of urban interactions. By mapping these three indicators of the spatial footprint of each neighbourhood, we can capture the nuances in the position of individual neighbourhoods within the larger urban network. An exploratory spatial regression reveals that socio-economic characteristics (e.g. share of rental housing) and the built environment (i.e. land use) only partially explain these three indicators and a residual analysis points to the need to explicitly include each neighbourhood's position within the transportation network in future work.

Utilizing Geo-Social Media as a Proxy Data for Enhanced Flood Monitoring

Utilizing Geo-Social Media as a Proxy Data for Enhanced Flood Monitoring

Evaluating the Representativeness of Socio-Demographic Variables over Time for Geo-Social Media Data

Geo-social media data are widely used as a data source to model populations and processes in a variety of contexts. However, if the data do not adequately represent the population they are drawn from, analysis results will be biased. Unaddressed, these biases may lead to false interpretations and conclusions. In this paper, we propose a generic methodology for investigating the representativeness of geo-social media data for population groups of similar statistical predictive power based on reference data. The groups are designed to be spatially coherent regions with similar prediction errors. Based on these units, we investigate the influence of different socio-demographic covariates on the representativeness. We perform experiments based on over 1.6 billion tweets and 90 socio-demographic covariates. We demonstrate that Twitter data representativeness varies strongly over time and space. Our results show that densely populated areas tend to be underrepresented consistently in non-spatial models. Over time, some covariates like the number of people aged 20 years exhibit highly different effects on the prediction models, whereas others are much more stable. The spatial effects can most frequently be explained using spatial error models, indicating spatially related errors that indicate the necessity of additional covariates. Finally, we provide hints for interpreting the results of our approach for researchers using the concepts presented in this paper.

Emphasising spatial structure in geosocial media data using spatial amplifier filtering

In this article, a new method called spatial amplifier filtering is proposed. The presented method is related to Moran eigenvector filtering and allows the accentuation of spatial structures in heterogeneous data sets. The spatial amplifier filtering technique is based on the inclusion of certain eigenvectors of a spatial weights matrix into a regression model. The application of this method can be seen as a pre-processing step prior to subsequent analyses, and to separate different types of spatially correlated components in a data set. For this purpose, three different types of the so-called spatial amplifiers are proposed, each consisting of different subsets of eigenvectors of the weights matrix. These amplifiers can either emphasise the positive or negative spatial autocorrelation, or spatial structuring in general. In this way, it is possible to make desired spatial structures more visible, especially in spatially highly mixed data sets, whereby the focus here is on geosocial media data. In the empirical part of the article, it is first shown why georeferenced social media data are difficult to handle from a spatial analysis perspective, motivating the need for the method proposed. Subsequently, the technique of amplifier filtering is applied to two data sets: a census data set from Brazil and Twitter data from London. The results obtained show that the method is capable of strengthening existing spatial structures and mitigating potentially disturbing spatial randomness patterns and other nuisances. This facilitates the interpretation especially of the Twitter data used. While the analysis of the unfiltered Twitter data with established methods reveals little information about possible spatial structures in the tweets, the filtered data offer a much clearer picture with distinguishable clusters. In addition, the method also provides insights into the internal irregularity of spatial clusters and thus complements the toolbox for investigating spatial heterogeneity.