Public Map Service Platforms(PMSPs)provide embedded map services in domains such as forests and rivers.Users from different domains(Domain Users)prefer specific spatial features,and extracting the Browsing Interests o...Public Map Service Platforms(PMSPs)provide embedded map services in domains such as forests and rivers.Users from different domains(Domain Users)prefer specific spatial features,and extracting the Browsing Interests of Domain Users(BIDUs)can help elucidate users’access intentions and provide suitable recommendations.Previous research has found that access frequency of spatial features is an indicator of users’browsing interests;however,highfrequency spatial features are sparsely distributed,resulting in inaccurate extraction of browsing interests.Our objective is to model the spatial co-occurrence of spatial features and employ BIDUs extraction to address this limitation.First,to extract spatial features in tiles,we proposed a k-nearest neighbor method for Point-of-Interest(POI)extraction and a template-based method for Land Uses/Land Covers extraction.Then,we developed the word2vec model to construct a POI semantic space to quantify spatial co-occurrence and employed multi-domain user classification to verify its effectiveness.Finally,a combined word2vec and singular value decomposition model is proposed to perform topic extraction as a representation of BIDUs.Compared with the baseline models,the proposed model integrates spatial co-occurrence from massive POIs to achieve high-accuracy BIDU extraction.Our findings can help construct domain user profiles and support the development of intelligent PMSPs.展开更多
Maps have long been a part of everyday life for the general public,and even more so in today’s knowledge society.No doubt,cartography as a profession of map design is assuming a more important role in the formation o...Maps have long been a part of everyday life for the general public,and even more so in today’s knowledge society.No doubt,cartography as a profession of map design is assuming a more important role in the formation of intellectual skills in terms of spatial reasoning.Since its emergence as an academic discipline about 100 years ago,cartography has undergone many paradigm shifts.Its interaction with other disciplines has also constantly unfolded.These changes have left traces in cartographic education programs.In the age of big data,however,we are facing four fundamental challenges:(1) cartographic courses are being marginalized or even disappearing from degree programs in geospatial sciences;(2) the role of cartographers is increasingly eclipsed as a side effect of participatory cartography;(3) cartographers are blamed whenever something goes wrong with map use;and(4) professional map publishers can hardly compete with online mapping platforms dominated by Internet giants.Based on a contextual analysis of this seemingly gloomy situation,the paper reveals a number of proliferation points for the design of future cartographic curricula.First,cartography,once dedicated to supporting geospatial sciences,is thriving in the soil of data science,mapping not only the earth or other celestial bodies,but literally any kind of virtual space.Second,cartography has benefited from theoretical and technological advances in cognitive sciences,especially non-intrusive user studies,so that spatial cognition is becoming an integral component of cartographic education.Third,the role of scapegoat for wrongdoing of maps has accentuated cartographer’s overarching responsibility for quality and ethical issues in the geodata value chain.Finally,the diversification of the labor market requires new approaches to prepare future talents for a coopetition-oriented ecosystem in the marketplace.展开更多
基金supported by the National Natural Science Foundation of China[grant numbers:U20A209141771426]Zhizhuo Research Fund on Spatial-Temporal Artificial Intelligence[grant number ZZJJ202204]LIESMARS Special Research Funding.
文摘Public Map Service Platforms(PMSPs)provide embedded map services in domains such as forests and rivers.Users from different domains(Domain Users)prefer specific spatial features,and extracting the Browsing Interests of Domain Users(BIDUs)can help elucidate users’access intentions and provide suitable recommendations.Previous research has found that access frequency of spatial features is an indicator of users’browsing interests;however,highfrequency spatial features are sparsely distributed,resulting in inaccurate extraction of browsing interests.Our objective is to model the spatial co-occurrence of spatial features and employ BIDUs extraction to address this limitation.First,to extract spatial features in tiles,we proposed a k-nearest neighbor method for Point-of-Interest(POI)extraction and a template-based method for Land Uses/Land Covers extraction.Then,we developed the word2vec model to construct a POI semantic space to quantify spatial co-occurrence and employed multi-domain user classification to verify its effectiveness.Finally,a combined word2vec and singular value decomposition model is proposed to perform topic extraction as a representation of BIDUs.Compared with the baseline models,the proposed model integrates spatial co-occurrence from massive POIs to achieve high-accuracy BIDU extraction.Our findings can help construct domain user profiles and support the development of intelligent PMSPs.
文摘Maps have long been a part of everyday life for the general public,and even more so in today’s knowledge society.No doubt,cartography as a profession of map design is assuming a more important role in the formation of intellectual skills in terms of spatial reasoning.Since its emergence as an academic discipline about 100 years ago,cartography has undergone many paradigm shifts.Its interaction with other disciplines has also constantly unfolded.These changes have left traces in cartographic education programs.In the age of big data,however,we are facing four fundamental challenges:(1) cartographic courses are being marginalized or even disappearing from degree programs in geospatial sciences;(2) the role of cartographers is increasingly eclipsed as a side effect of participatory cartography;(3) cartographers are blamed whenever something goes wrong with map use;and(4) professional map publishers can hardly compete with online mapping platforms dominated by Internet giants.Based on a contextual analysis of this seemingly gloomy situation,the paper reveals a number of proliferation points for the design of future cartographic curricula.First,cartography,once dedicated to supporting geospatial sciences,is thriving in the soil of data science,mapping not only the earth or other celestial bodies,but literally any kind of virtual space.Second,cartography has benefited from theoretical and technological advances in cognitive sciences,especially non-intrusive user studies,so that spatial cognition is becoming an integral component of cartographic education.Third,the role of scapegoat for wrongdoing of maps has accentuated cartographer’s overarching responsibility for quality and ethical issues in the geodata value chain.Finally,the diversification of the labor market requires new approaches to prepare future talents for a coopetition-oriented ecosystem in the marketplace.
