Centre dedocumentation
scientifique

Correlation of road network structure and urban mobility intensity: An exploratory study using geo-tagged tweets / Li Geng in ISPRS International journal of geo-information, vol 12 n° 1 (January 2023)  

Public [article]  inISPRS International journal of geo-information > vol 12 n° 1 (January 2023) . - n° 7 Titre : Correlation of road network structure and urban mobility intensity: An exploratory study using geo-tagged tweets Type de document : Article/Communication Auteurs : Li Geng, Auteur ; Ke Zhang, Auteur Année de publication : 2023 Article en page(s) : n° 7 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] corrélation automatique de points homologues [Termes IGN] données issues des réseaux sociaux [Termes IGN] Etats-Unis [Termes IGN] géobalise [Termes IGN] mobilité urbaine [Termes IGN] OpenStreetMap [Termes IGN] réseau routier [Termes IGN] Twitter Résumé : (auteur) Urban planners have been long interested in understanding how urban structure and activities are mutually influenced. Human mobility and economic activities naturally drive the formation of road network structure and the accessibility of the latter shapes the patterns of movement flow across urban space. In this paper, we perform an exploratory study on the relationship between the street network structure and the intensity of human movement in urban areas. We focus on two cities and we utilize a dataset of geo-tagged tweets that can form a proxy to urban mobility and the corresponding street networks as obtained from OpenStreetMap. We apply three network centrality measures, including closeness, betweenness and straightness centrality, calculated at a global or local scale, as well as under mixed or individual transportation mode (e.g., driving, biking and walking) with its directional accessibility, to uncover the structural properties of urban street networks. We further design an urban area transition network and apply PageRank to capture the intensity of human mobility. Our correlation analysis indicates different centrality metrics have different levels of correlation with the intensity of human movement. The closeness centrality consistently shows the highest correlation (with a coefficient around 0.6) with human movement intensity when calculated at a global scale, while straightness centrality often shows no correlation at the global scale or weaker correlation ρ≈0.4 at the local scale. The correlation levels further depend on the type of directional accessibility and of various types of transportation modes. Hence, the directionality and transportation mode, largely ignored in the analysis of road networks, are crucial. Furthermore, the strength of the correlation varies in the two cities examined, indicating potential differences in urban spatial structure and human mobility patterns. Numéro de notice : A2023-105 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueNat DOI : 10.3390/ijgi12010007 Date de publication en ligne : 28/12/2022 En ligne : https://doi.org/10.3390/ijgi12010007 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102433 [article]

Evaluation of GNSS-based volunteered geographic information for assessing visitor spatial distribution within protected areas: A case study of the Bavarian Forest National Park, Germany / Laura Horst in Applied Geography, vol 150 (January 2023)  

Public [article]  inApplied Geography > vol 150 (January 2023) . - n° 102825 Titre : Evaluation of GNSS-based volunteered geographic information for assessing visitor spatial distribution within protected areas: A case study of the Bavarian Forest National Park, Germany Type de document : Article/Communication Auteurs : Laura Horst, Auteur ; Karolina Taczanowska, Auteur ; Florian Porst, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : n° 102825 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] aire protégée [Termes IGN] ArcGIS [Termes IGN] Bavière (Allemagne) [Termes IGN] distribution spatiale [Termes IGN] données GNSS [Termes IGN] données issues des réseaux sociaux [Termes IGN] données localisées des bénévoles [Termes IGN] géodatabase [Termes IGN] parc naturel national [Termes IGN] piéton Résumé : (auteur) Systematic monitoring of recreational use in vulnerable ecosystems is crucial to balance human needs and site capacities. Recently, publicly available digital data, including Global Navigation Satellite System-based Volunteered Geographic Information, gained attention as a potential resource depicting visitor movement. However, there is a need to critically assess its reliability for visitor monitoring across countries, regions and available databases. Our research evaluates the usability of GNSS-based VGI-data obtained from three common platforms: GPSies, Outdooractive, and Komoot for assessing the spatial distribution of hikers in the Bavarian Forest National Park. A total sample of 1742 GNSS-tracks uploaded between 2013 and 2018 were compared across data platforms. Additionally, available systematic field counts, carried out between 2013 and 2014 (11 Eco-Counter sensors), were compared to GNSS-based VGI data uploaded within the corresponding period. The comparisons at individual and collective levels (route lengths, kernel density, optimized hotspot analysis along with fishnet-based counts of GNSS-tracks) showed similarities between VGI data platforms. Data obtained from GPSies and Outdooractive displayed a higher correlation with each other than with those obtained from Komoot. Also, for GPSies, there was a significant positive correlation between VGI-data and field count data. Data sample of Outdooractive and Komoot within the specified spatio-temporal frame was too small to compare with available field count data. We highlight the necessity of systematic validation of GNSS-based VGI data resources, being complementary rather than the primary data source in visitor monitoring and recreation planning. Also, systematic long-term visitor monitoring using other methods is crucial to assess the validity of novel data resources, such as GNSS-based VGI. Numéro de notice : A2023-020 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1016/j.apgeog.2022.102825 Date de publication en ligne : 25/11/2023 En ligne : https://doi.org/10.1016/j.apgeog.2022.102825 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102220 [article]

Understanding public perspectives on fracking in the United States using social media big data / Xi Gong in Annals of GIS, vol 29 n° 1 (January 2023)  

Public [article]  inAnnals of GIS > vol 29 n° 1 (January 2023) . - pp 21 - 35 Titre : Understanding public perspectives on fracking in the United States using social media big data Type de document : Article/Communication Auteurs : Xi Gong, Auteur ; Yujian Lu, Auteur ; Daniel Beene, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 21 - 35 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] analyse socio-économique [Termes IGN] données issues des réseaux sociaux [Termes IGN] données massives [Termes IGN] enquête sociologique [Termes IGN] Etats-Unis [Termes IGN] fracturation [Termes IGN] hétérogénéité spatiale [Termes IGN] régression géographiquement pondérée [Termes IGN] Twitter Résumé : (auteur) People’s attitudes towards hydraulic fracturing (fracking) can be shaped by socio-demographics, economic development, social equity and politics, environmental impacts, and fracking-related information. Existing research typically conducts surveys and interviews to study public attitudes towards fracking among a small group of individuals in a specific geographic area, where limited samples may introduce bias. Here, we compiled geo-referenced social media big data from Twitter during 2018–2019 for the entire United States to present a more holistic picture of people’s attitudes towards fracking. We used a multiscale geographically weighted regression (MGWR) to investigate county-level relationships between the aforementioned factors and percentages of negative tweets concerning fracking. Results indicate spatial heterogeneity and varying scales of those associations. Counties with higher median household income, larger African American populations, and/or lower educational level are less likely to oppose fracking, and these associations show global stationarity in all contiguous US counties. Eastern and Central US counties with higher unemployment rates, counties east of the Great Plains with less fracking sites nearby, and Western and Gulf Coast region counties with higher health insurance enrolments are more likely to oppose fracking activities. These three variables show clear East-West geographical divides in influencing public perspective on fracking. In counties across the southern Great Plains, negative attitudes towards fracking are less often vocalized on Twitter as the share of Republican voters increases. These findings have implications for both predicting public perspectives and needed policy adjustments. The methodology can also be conveniently applied to investigate public perspectives on other controversial topics. Numéro de notice : A2023-160 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/19475683.2022.2121856 Date de publication en ligne : 10/09/2022 En ligne : https://doi.org/10.1080/19475683.2022.2121856 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102862 [article]

Geographic named entity recognition by employing natural language processing and an improved BERT model / Liufeng Tao in ISPRS International journal of geo-information, vol 11 n° 12 (December 2022)  

Public [article]  inISPRS International journal of geo-information > vol 11 n° 12 (December 2022) . - n° 598 Titre : Geographic named entity recognition by employing natural language processing and an improved BERT model Type de document : Article/Communication Auteurs : Liufeng Tao, Auteur ; Zhong Xie, Auteur ; Dexin Xu, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 598 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] Chine [Termes IGN] classification dirigée [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] données issues des réseaux sociaux [Termes IGN] données publiques [Termes IGN] jeu de données [Termes IGN] reconnaissance de caractères [Termes IGN] reconnaissance de noms [Termes IGN] test de performance [Termes IGN] toponyme [Termes IGN] traitement du langage naturel Résumé : (auteur) Toponym recognition, or the challenge of detecting place names that have a similar referent, is involved in a number of activities connected to geographical information retrieval and geographical information sciences. This research focuses on recognizing Chinese toponyms from social media communications. While broad named entity recognition methods are frequently used to locate places, their accuracy is hampered by the many linguistic abnormalities seen in social media posts, such as informal sentence constructions, name abbreviations, and misspellings. In this study, we describe a Chinese toponym identification model based on a hybrid neural network that was created with these linguistic inconsistencies in mind. Our method adds a number of improvements to a standard bidirectional recurrent neural network model to help with location detection in social media messages. We demonstrate the results of a wide-ranging evaluation of the performance of different supervised machine learning methods, which have the natural advantage of avoiding human design features. A set of controlled experiments with four test datasets (one constructed and three public datasets) demonstrates the performance of supervised machine learning that can achieve good results on the task, significantly outperforming seven baseline models. Numéro de notice : A2022 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.3390/ijgi11120598 Date de publication en ligne : 28/11/2022 En ligne : https://doi.org/10.3390/ijgi11120598 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102178 [article]

A machine learning approach for detecting rescue requests from social media / Zheye Wang in ISPRS International journal of geo-information, vol 11 n° 11 (November 2022)  

Public [article]  inISPRS International journal of geo-information > vol 11 n° 11 (November 2022) . - n° 570 Titre : A machine learning approach for detecting rescue requests from social media Type de document : Article/Communication Auteurs : Zheye Wang, Auteur ; Nina S.N. Lam, Auteur ; Mingxuan Sun, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 570 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] apprentissage automatique [Termes IGN] code postal [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] données issues des réseaux sociaux [Termes IGN] Etats-Unis [Termes IGN] filtrage d'information [Termes IGN] secours d'urgence [Termes IGN] tempête [Termes IGN] terminologie [Termes IGN] Twitter Résumé : (auteur) Hurricane Harvey in 2017 marked an important transition where many disaster victims used social media rather than the overloaded 911 system to seek rescue. This article presents a machine-learning-based detector of rescue requests from Harvey-related Twitter messages, which differentiates itself from existing ones by accounting for the potential impacts of ZIP codes on both the preparation of training samples and the performance of different machine learning models. We investigate how the outcomes of our ZIP code filtering differ from those of a recent, comparable study in terms of generating training data for machine learning models. Following this, experiments are conducted to test how the existence of ZIP codes would affect the performance of machine learning models by simulating different percentages of ZIP-code-tagged positive samples. The findings show that (1) all machine learning classifiers except K-nearest neighbors and Naïve Bayes achieve state-of-the-art performance in detecting rescue requests from social media; (2) using ZIP code filtering could increase the effectiveness of gathering rescue requests for training machine learning models; (3) machine learning models are better able to identify rescue requests that are associated with ZIP codes. We thereby encourage every rescue-seeking victim to include ZIP codes when posting messages on social media. This study is a useful addition to the literature and can be helpful for first responders to rescue disaster victims more efficiently. Numéro de notice : A2022-846 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi11110570 Date de publication en ligne : 16/11/2022 En ligne : https://doi.org/10.3390/ijgi11110570 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102081 [article]

An analysis of twitter as a relevant human mobility proxy / Fernando Terroso-Saenz in Geoinformatica, vol 26 n° 4 (October 2022)  

Permalink

Machine learning and natural language processing of social media data for event detection in smart cities / Andrei Hodorog in Sustainable Cities and Society, vol 85 (October 2022)  

Permalink

Predicting the variability in pedestrian travel rates and times using crowdsourced GPS data / Michael J. Campbell in Computers, Environment and Urban Systems, vol 97 (October 2022)  

Permalink

A geographical and content-based approach to prioritize relevant and reliable tweets for emergency management / A. Marcela Suarez in Cartography and Geographic Information Science, Vol 49 n° 5 (September 2022)  

Permalink

Point-of-interest detection from Weibo data for map updating / Xue Yang in Transactions in GIS, vol 26 n° 6 (September 2022)  

Permalink

Detecting spatiotemporal traffic events using geosocial media data / Shishuo Xu in Computers, Environment and Urban Systems, vol 94 (June 2022)  

Permalink

The effect of intra-urban mobility flows on the spatial heterogeneity of social media activity: investigating the response to rainfall events / Sidgley Camargo de Andrade in International journal of geographical information science IJGIS, vol 36 n° 6 (June 2022)  

Permalink

ChineseTR: A weakly supervised toponym recognition architecture based on automatic training data generator and deep neural network / Qinjun Qiu in Transactions in GIS, vol 26 n° 3 (May 2022)  

Permalink

A GIS representation framework for location-based social media activities / Xuebin Wei in Transactions in GIS, vol 26 n° 3 (May 2022)  

Permalink

HiPerMovelets: high-performance movelet extraction for trajectory classification / Tarlis Tortelli Portela in International journal of geographical information science IJGIS, vol 36 n° 5 (May 2022)  

Permalink