Centre dedocumentation
scientifique

A BiLSTM-CNN model for predicting users’ next locations based on geotagged social media / Yi Bao in International journal of geographical information science IJGIS, vol 35 n° 4 (April 2021)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 35 n° 4 (April 2021) . - pp 639 - 660 Titre : A BiLSTM-CNN model for predicting users’ next locations based on geotagged social media Type de document : Article/Communication Auteurs : Yi Bao, Auteur ; Zhou Huang, Auteur ; Linna Li, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 639 - 660 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse de groupement [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] données spatiotemporelles [Termes IGN] géopositionnement [Termes IGN] graphe [Termes IGN] modèle de simulation [Termes IGN] point d'intérêt [Termes IGN] réseau social [Termes IGN] service fondé sur la position [Termes IGN] utilisateur [Termes IGN] Wuhan (Chine) Résumé : (auteur) Location prediction based on spatio-temporal footprints in social media is instrumental to various applications, such as travel behavior studies, crowd detection, traffic control, and location-based service recommendation. In this study, we propose a model that uses geotags of social media to predict the potential area containing users’ next locations. In the model, we utilize HiSpatialCluster algorithm to identify clustering areas (CAs) from check-in points. CA is the basic spatial unit for predicting the potential area containing users’ next locations. Then, we use the LINE (Large-scale Information Network Embedding) to obtain the representation vector of each CA. Finally, we apply BiLSTM-CNN (Bidirectional Long Short-Term Memory-Convolutional Neural Network) for location prediction. The results show that the proposed ensemble model outperforms the single LSTM or CNN model. In the case study that identifies 100 CAs out of Weibo check-ins collected in Wuhan, China, the Top-5 predicted areas containing next locations amount to an 80% accuracy. The high accuracy is of great value for recommendation and prediction on areal unit. Numéro de notice : A2021-268 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2020.1808896 Date de publication en ligne : 26/08/2020 En ligne : https://doi.org/10.1080/13658816.2020.1808896 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97324 [article]

Spatial, temporal, and socioeconomic patterns in the use of Twitter and Flickr / Linna Li in Cartography and Geographic Information Science, vol 40 n° 2 (March 2013)  

Public [article]  inCartography and Geographic Information Science > vol 40 n° 2 (March 2013) . - pp 61 - 77 Titre : Spatial, temporal, and socioeconomic patterns in the use of Twitter and Flickr Type de document : Article/Communication Auteurs : Linna Li, Auteur ; Michael F. Goodchild, Auteur ; Bo Xu, Auteur Année de publication : 2013 Article en page(s) : pp 61 - 77 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse de données [Termes IGN] analyse socio-économique [Termes IGN] analyse spatiale [Termes IGN] Californie (Etats-Unis) [Termes IGN] données localisées des bénévoles [Termes IGN] Etats-Unis [Termes IGN] partage de données localisées [Termes IGN] réseau social [Termes IGN] Twitter Résumé : (Auteur) Online social networking and information sharing services have generated large volumes of spatio-temporal footprints, which are potentially a valuable source of knowledge about the physical environment and social phenomena. However, it is critical to take into consideration the uneven distribution of the data generated in social media in order to understand the nature of such data and to use them appropriately. The distribution of footprints and the characteristics of contributors indicate the quantity, quality, and type of the data. Using georeferenced tweets and photos collected from Twitter and Flickr, this research presents the spatial and temporal patterns of such crowd-sourced geographic data in the contiguous United States and explores the socioeconomic characteristics of geographic data creators by investigating the relationships between tweet and photo densities and the characteristics of local people using California as a case study. Correlations between dependent and independent variables in partial least squares regression suggest that well-educated people in the occupations of management, business, science, and arts are more likely to be involved in the generation of georeferenced tweets and photos. Further research is required to explain why some people tend to produce and spread information over the Internet using social media from the perspectives of psychology and sociology. This study would be informative to sociologists who study the behaviors of social media users, geographers who are interested in the spatial and temporal distribution of social media users, marketing agencies who intend to understand the influence of social media, and other scientists who use social media data in their research. Numéro de notice : A2013-743 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/SOCIETE NUMERIQUE Nature : Article DOI : 10.1080/15230406.2013.777139 En ligne : https://doi.org/10.1080/15230406.2013.777139 Format de la ressource électronique : url Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32879 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
032-2013021	RAB	Revue	Centre de documentation	En réserve L003	Disponible