Geolocating social media users aims to discover the real geographical locations of users from their publicly available data,which can support online location-based applications such as disaster alerts and local conten...Geolocating social media users aims to discover the real geographical locations of users from their publicly available data,which can support online location-based applications such as disaster alerts and local content recommen-dations.Social relationship-based methods represent a classical approach for geolocating social media.However,geographically proximate relationships are sparse and challenging to discern within social networks,thereby affecting the accuracy of user geolocation.To address this challenge,we propose user geolocation methods that integrate neighborhood geographical distribution and social structure influence(NGSI)to improve geolocation accuracy.Firstly,we propose a method for evaluating the homophily of locations based on the k-order neighbor-hood geographic distribution(k-NGD)similarity among users.There are notable differences in the distribution of k-NGD similarity between location-proximate and non-location-proximate users.Exploiting this distinction,we filter out non-location-proximate social relationships to enhance location homophily in the social network.To better utilize the location-proximate relationships in social networks,we propose a graph neural network algorithm based on the social structure influence.The algorithm enables us to perform a weighted aggregation of the information of users’multi-hop neighborhood,thereby mitigating the over-smoothing problem of user features and improving user geolocation performance.Experimental results on real social media dataset demonstrate that the neighborhood geographical distribution similarity metric can effectively filter out non-location-proximate social relationships.Moreover,compared with 7 existing social relationship-based user positioning methods,our proposed method can achieve multi-granularity user geolocation and improve the accuracy by 4.84%to 13.28%.展开更多
The teleseismic receiver functions of 48 stations belonging to the CCDSN are used to invert the crustal structure beneath each station with the neighborhood algorithm. Thin layers with low velocity have been found ben...The teleseismic receiver functions of 48 stations belonging to the CCDSN are used to invert the crustal structure beneath each station with the neighborhood algorithm. Thin layers with low velocity have been found beneath eight stations with ＂abnormal＂ observed receiver functions. Unreasonable results of few stations have been adjusted lightly with the trial-and-error method. The final result indicates that the crust in the western China is relatively thicker than the eastern China. The crust thickness beneath the Tibetan plateau is very large, which reaches 84 km at the station LSA. Double-crust structure exists below the stations LSA and CAD in Tibet, which might imply the collision between the Indian and Eurasian plates. A pronounced low velocity zone in the lower crust beneath the station TNC of Yunnan province might relate to the high temperature or emergence of partially molten material caused by Quaternary volcano, magma and geothermal activities in this area. The Moho is a transitional zone made up of thin layers instead of simple sharp discontinuity beneath several stations. The Conrad discontinuity is clearly identified beneath 20 stations mainly in the southeastern China, whereas it is blurry beneath 14 stations and uncertain beneath remaining stations.展开更多
The Neighborhood Preserving Embedding(NPE) algorithm is recently proposed as a new dimensionality reduction method.However, it is confined to linear transforms in the data space.For this, based on the NPE algorithm, a...The Neighborhood Preserving Embedding(NPE) algorithm is recently proposed as a new dimensionality reduction method.However, it is confined to linear transforms in the data space.For this, based on the NPE algorithm, a new nonlinear dimensionality reduction method is proposed, which can preserve the local structures of the data in the feature space.First, combined with the Mercer kernel, the solution to the weight matrix in the feature space is gotten and then the corresponding eigenvalue problem of the Kernel NPE(KNPE) method is deduced.Finally, the KNPE algorithm is resolved through a transformed optimization problem and QR decomposition.The experimental results on three real-world data sets show that the new method is better than NPE, Kernel PCA(KPCA) and Kernel LDA(KLDA) in performance.展开更多
The modernization of Shanghai has experienced two boosting periods.The first appeared in the 1930s,when it formed the civil society of Shanghai and initially facilitated the trade port into an international metropolis...The modernization of Shanghai has experienced two boosting periods.The first appeared in the 1930s,when it formed the civil society of Shanghai and initially facilitated the trade port into an international metropolis.The second started after the nation’s reform and opening-up,which attempted to promote the city into a global metropolis in the 2010s.In order to evaluate the socio-spatial transitions of communities in Shanghai during the process,Lilong historical neighborhoods in the 1930s and 2010s are successively chosen as research objects.Meanwhile,three specific neighborhoods in each period are selected for case study,so as to depict different symbiosis patterns of the socio-spatial structures under different spatiotemporal conditions by means of a cross-sectional analysis of the consumption level.By pointing out Shanghai in the 1930s was marked with social integration and local-based consumption,while it was inundated with administration tendency and global-oriented consumption in the 2010s,the article believes the dual integration of local-based and global-oriented consumptions is an alternative solution for Shanghai.Finally,the article proposes that Shanghai’s current urban regeneration should rely on the multi-centered symbiotic structure to create a compound network,during which territorial socio-spatial structures and basic living needs of the plebeian can be simultaneously preserved.展开更多
基金This work was supported by the National Key R&D Program of China(No.2022YFB3102904)the National Natural Science Foundation of China(No.62172435,U23A20305)Key Research and Development Project of Henan Province(No.221111321200).
文摘Geolocating social media users aims to discover the real geographical locations of users from their publicly available data,which can support online location-based applications such as disaster alerts and local content recommen-dations.Social relationship-based methods represent a classical approach for geolocating social media.However,geographically proximate relationships are sparse and challenging to discern within social networks,thereby affecting the accuracy of user geolocation.To address this challenge,we propose user geolocation methods that integrate neighborhood geographical distribution and social structure influence(NGSI)to improve geolocation accuracy.Firstly,we propose a method for evaluating the homophily of locations based on the k-order neighbor-hood geographic distribution(k-NGD)similarity among users.There are notable differences in the distribution of k-NGD similarity between location-proximate and non-location-proximate users.Exploiting this distinction,we filter out non-location-proximate social relationships to enhance location homophily in the social network.To better utilize the location-proximate relationships in social networks,we propose a graph neural network algorithm based on the social structure influence.The algorithm enables us to perform a weighted aggregation of the information of users’multi-hop neighborhood,thereby mitigating the over-smoothing problem of user features and improving user geolocation performance.Experimental results on real social media dataset demonstrate that the neighborhood geographical distribution similarity metric can effectively filter out non-location-proximate social relationships.Moreover,compared with 7 existing social relationship-based user positioning methods,our proposed method can achieve multi-granularity user geolocation and improve the accuracy by 4.84%to 13.28%.
基金supported by the basic research and development fund from Institute of Earthquake Science,China Earthquake Administration(grant No.2011IESLZ05)the National Natural Science Foundation of China(grant Nos.40374009and 40904014)
文摘The teleseismic receiver functions of 48 stations belonging to the CCDSN are used to invert the crustal structure beneath each station with the neighborhood algorithm. Thin layers with low velocity have been found beneath eight stations with ＂abnormal＂ observed receiver functions. Unreasonable results of few stations have been adjusted lightly with the trial-and-error method. The final result indicates that the crust in the western China is relatively thicker than the eastern China. The crust thickness beneath the Tibetan plateau is very large, which reaches 84 km at the station LSA. Double-crust structure exists below the stations LSA and CAD in Tibet, which might imply the collision between the Indian and Eurasian plates. A pronounced low velocity zone in the lower crust beneath the station TNC of Yunnan province might relate to the high temperature or emergence of partially molten material caused by Quaternary volcano, magma and geothermal activities in this area. The Moho is a transitional zone made up of thin layers instead of simple sharp discontinuity beneath several stations. The Conrad discontinuity is clearly identified beneath 20 stations mainly in the southeastern China, whereas it is blurry beneath 14 stations and uncertain beneath remaining stations.
文摘The Neighborhood Preserving Embedding(NPE) algorithm is recently proposed as a new dimensionality reduction method.However, it is confined to linear transforms in the data space.For this, based on the NPE algorithm, a new nonlinear dimensionality reduction method is proposed, which can preserve the local structures of the data in the feature space.First, combined with the Mercer kernel, the solution to the weight matrix in the feature space is gotten and then the corresponding eigenvalue problem of the Kernel NPE(KNPE) method is deduced.Finally, the KNPE algorithm is resolved through a transformed optimization problem and QR decomposition.The experimental results on three real-world data sets show that the new method is better than NPE, Kernel PCA(KPCA) and Kernel LDA(KLDA) in performance.
文摘The modernization of Shanghai has experienced two boosting periods.The first appeared in the 1930s,when it formed the civil society of Shanghai and initially facilitated the trade port into an international metropolis.The second started after the nation’s reform and opening-up,which attempted to promote the city into a global metropolis in the 2010s.In order to evaluate the socio-spatial transitions of communities in Shanghai during the process,Lilong historical neighborhoods in the 1930s and 2010s are successively chosen as research objects.Meanwhile,three specific neighborhoods in each period are selected for case study,so as to depict different symbiosis patterns of the socio-spatial structures under different spatiotemporal conditions by means of a cross-sectional analysis of the consumption level.By pointing out Shanghai in the 1930s was marked with social integration and local-based consumption,while it was inundated with administration tendency and global-oriented consumption in the 2010s,the article believes the dual integration of local-based and global-oriented consumptions is an alternative solution for Shanghai.Finally,the article proposes that Shanghai’s current urban regeneration should rely on the multi-centered symbiotic structure to create a compound network,during which territorial socio-spatial structures and basic living needs of the plebeian can be simultaneously preserved.
