Exploration of spatiotemporal and semantic clusters of Twitter data using unsupervised neural networks

ABSTRACT

The investigation of human activity patterns from location-based social networks like Twitter is an established approach of how to infer relationships and latent information that characterize urban structures. Researchers from various disciplines have performed geospatial analysis on social media data despite the data’s high dimensionality, complexity and heterogeneity. However, user-generated datasets are of multi-scale nature, which results in limited applicability of commonly known geospatial analysis methods. Therefore in this paper, we propose a geographic, hierarchical self-organizing map (Geo-H-SOM) to analyze geospatial, temporal and semantic characteristics of georeferenced tweets. The results of our method, which we validate in a case study, demonstrate the ability to explore, abstract and cluster high-dimensional geospatial and semantic information from crowdsourced data.     

Neighborhood-Based social capital and life satisfaction: the case of Rotterdam,The Netherlands

ABSTRACT

In this study, we examine the relationship between neighborhood-based social capital and residents’ life satisfaction by considering resident heterogeneity. Using a database of the city of Rotterdam, The Netherlands, we find a small but significant positive association between neighborhood-based social capital and individual life satisfaction. However, we also find considerable differences among residents because neighborhood-based social capital is important mainly for people who are more likely to spend considerable time in the neighborhood or who are more neighborhood dependent (i.e. less-educated people, people who live on welfare, people with poor health, retired people, and those who are divorced or widowed). Our results confirm the importance of neighborhood-based social capital for residents’ life satisfaction in terms of both actual social contacts with neighbors and the perceived social cohesion within a neighborhood. At the same time, the importance of neighborhood-based social capital varies among different groups of residents. These findings have important implications for policy-makers.     

Leveraging geotagged Twitter data to examine neighborhood happiness,diet, and physical activity

ObjectivesUsing publicly available, geotagged Twitter data, we created neighborhood indicators for happiness, food and physical activity for three large counties: Salt Lake, San Francisco and New York.MethodsWe utilize 2.8 million tweets collected between February–August 2015 in our analysis. Geo-coordinates of where tweets were sent allow us to spatially join them to 2010 census tract locations. We implemented quality control checks and tested associations between Twitter-derived variables and sociodemographic characteristics.ResultsFor a random subset of tweets, manually labeled tweets and algorithm labeled tweets had excellent levels of agreement: 73% for happiness; 83% for food, and 85% for physical activity. Happy tweets, healthy food references, and physical activity references were less frequent in census tracts with greater economic disadvantage and higher proportions of racial/ethnic minorities and youths.ConclusionsSocial media can be leveraged to provide greater understanding of the well-being and health behaviors of communities—information that has been previously difficult and expensive to obtain consistently across geographies. More open access neighborhood data can enable better design of programs and policies addressing social determinants of health.     

The Disparate Neighborhood Impacts of the Great Recession: Evidence from Chicago

Abstract

We advance scholarship about how macroeconomic forces differentially manifest themselves across local spaces by developing a holistic conceptual framework and empirical analyses involving multilevel change modeling. Unlike prior work, we examine differential rates of change in neighborhood indicators. We illustrate our approach with Chicago data measuring the crime, housing, and economic domains of neighborhood quality of life over the 2000–2009 period. We find that the local dynamic manifestations of macroeconomic cycles were far more nuanced than have been previously observed. Neighborhood indicators moved along distinct trajectories, sometimes but not necessarily tracking each other or the overall business cycle, and they changed with varied intensities. The Great Recession of 2006–2009 had disparate negative impacts on lower-income and minority-occupied neighborhoods' local job opportunities, home prices, and home foreclosures, though this was not true for credit or crime indicators. Credit indicators performed geographically much differently than in the prior Chicago recession.     

The Comparative Approach to the Study of the Americas

Abstract

The study of community helpers in second grade can be enriched by a unit on the location of neighborhood services. The school itself is a community service. Within a short distance of the school are located such services as a post office, a police station, a fire station, and a library. In addition to these public services, there are many small business establishments. Second-grade teachers can take advantage of these enterprises to help pupils learn the reasons for their locations. Additional benefits can be derived from this study; for instance, young children will be able to gather information from primary sources and to extract relationships from the data.     

The urban geopolitics of neighboring: conflict,encounter and class in Jerusalem’s settlement/neighborhood

This article examines a unique, yet paradigmatic, case study of a colonial neighborhood in East Jerusalem that is undergoing a significant demographic transformation.¹ The French Hill neighborhood, built in 1971, was one of the first settlements in East Jerusalem. Initially, it was populated primarily by upper-middle class secular-Jewish residents. This group has been steadily diminishing as two other distinct new groups moved into the neighborhood: Ultra-Orthodox Jews and Palestinians. This volatile social mix has caused intense inter-ethnic and intra-ethnic collisions. Based on qualitative and quantitative studies, we argue that the juxtaposition of colonial and neoliberal logics of space reveals a shared, yet fragile, middle-class identity. We suggest that this new geopolitical space of neighboring calls for a discussion of political conflict, housing and current colonial conditions that brings class back to our understanding of the production of contested space.     

Geostatistical space–time mapping of house prices using Bayesian maximum entropy

Mapping spatial processes at a small scale is a challenge when observed data are not abundant. The article examines the residential housing market in Fort Worth, Texas, and builds price indices at the inter- and intra-neighborhood levels. To accomplish our objectives, we initially model price variability in the joint space–time continuum. We then use geostatistics to predict and map monthly housing prices across the area of interest over a period of 4 years. For this analysis, we introduce the Bayesian maximum entropy (BME) method into real estate research. We use BME because it rigorously integrates uncertain or secondary soft data, which are needed to build the price indices. The soft data in our analysis are property tax values, which are plentiful, publicly available, and highly correlated with transaction prices. The results demonstrate how the use of the soft data provides the ability to map house prices within a small areal unit such as a subdivision or neighborhood.     

Mortgage Foreclosures,Race, and Postrecession Lending

This article examines the effect of high foreclosure rates on postrecession lending. Our hypothesis is that high neighborhood foreclosure rates will have a significant and positive effect on the likelihood of mortgage loan denial. In a case study on Toledo, Ohio, we explore the role of foreclosure activity, race, and racial disparities in lending practices and how they differ across neighborhoods. Our results suggest that applicants in high-foreclosure neighborhoods have a greater likelihood of loan denial (ceteris paribus). We also find that minority applicants face a higher probability of loan denial in high-foreclosure minority neighborhoods. Overall, the results depict highly variable lending practices where race seems to make a difference albeit in a small subset of neighborhoods deeply affected by the foreclosure crisis. There is also some indication of a chilling effect on minority loan applicants in Toledo during the postrecession period. Key Words: foreclosure, logistic regression, mortgage lending, neighborhood contingency, race discrimination.     

Using the Definition of Geography to Develop Teaching Strategies

Abstract

Climatic Change, Basingstoke and London: Macmillan Education, 1981. v and 34 pp., figs., tables, maps, refs., and index. $2.50 paper.

Vanishing Roadside America, Warren H. Anderson, Tucson: University of Arizona Press, 1981. 142 pp. and illus. $14.95 paper.

USSR in Maps, J.C. Dewdney, New York: Holmes &; Meier, 1982. vi and 117 pp., diags., maps, tables, graphs, biblio., and index. $29.50.     

The Trade and Industries of Western South America

Abstract

This research was based on an instructional module developed and used to investigate whether GIS can be used to enhance fourth grade students' geographic knowledge and map skills. Another goal was to identify challenges the teachers and the students face using GIS.

Findings from the study suggest that using GIS in the classroom helps students improve their geographic knowledge and maps skills. In addition, this study found that the students' geographic content knowledge tended to improve gradually and the knowledge transferred to the subsequent lessons, while certain map skills tended to develop in a more specific manner.     

The Educational Value of Geographical Exhibitions

Abstract

All maps lie, but some do so in especially interesting ways. Examples of errors or distortions can be found on maps appearing in magazines, newspapers, telephone directories, brochures, and even in geography textbooks. Special biases are often revealed in hand-drawn maps, or on written directions (virtual maps). Students can develop a critical eye by looking for, and collecting, maps that clearly, or cleverly, tell lies.     

Segregation as a multiscalar phenomenon and its implications for neighborhood-scale research: the case of South Seattle 1990–2010

Neighborhoods and neighborhood change are often at least implicitly understood in relation to processes taking place at scales both smaller than and larger than the neighborhood itself. Until recently our capacity to represent these multiscalar processes with quantitative measures has been limited. Recent work on “segregation profiles” by Reardon and collaborators expands our capacity to explore the relationship between population measures and scale. With the methodological tools now available, we need a conceptual shift in how we view population measures in order to bring our theories and measures of neighborhoods into alignment. I argue that segregation can be beneficially viewed as multiscalar; not a value calculable at some “correct” scale, but a continuous function with respect to scale. This shift requires new ways of thinking about and analyzing segregation with respect to scale that engage with the complexity of the multiscalar measure. Using block-level data for eight neighborhoods in Seattle, Washington, I explore the implications of a multiscalar segregation measure for understanding neighborhoods and neighborhood change from 1990 to 2010.     

Utilizing discriminant function analysis with a geographical information system to model ecological succession spatially

Abstract

A raster/quadtree geographical information system (GIS) was established For a 932 ha natural area in central Missouri. The GIS contained map layers depicting vegetative cover from 1939 to 1982, soils, topographic aspect and distance from a forest seed source. Discriminant function analysis was used to quantify and describe ecological succession on the area during this period. The calibration of discriminant functions is discussed, as are the statistical and spatial validations of the model. It was concluded that this approach provides a useful technique to examine long-term temporal phenomena in a spatial context.     

Simulating urban land use change by integrating a convolutional neural network with vector-based cellular automata

ABSTRACT

Vector-based cellular automata (VCA) models have been applied in land use change simulations at fine scales. However, the neighborhood effects of the driving factors are rarely considered in the exploration of the transition suitability of cells, leading to lower simulation accuracy. This study proposes a convolutional neural network (CNN)-VCA model that adopts the CNN to extract the high-level features of the driving factors within a neighborhood of an irregularly shaped cell and discover the relationships between multiple land use changes and driving factors at the neighborhood level. The proposed model was applied to simulate urban land use changes in Shenzhen, China. Compared with several VCA models using other machine learning methods, the proposed CNN-VCA model obtained the highest simulation accuracy (figure-of-merit = 0.361). The results indicated that the CNN-VCA model can effectively uncover the neighborhood effects of multiple driving factors on the developmental potential of land parcels and obtain more details on the morphological characteristics of land parcels. Moreover, the land use patterns of 2020 and 2025 under an ecological control strategy were simulated to provide decision support for urban planning.     

The Forest in the Future: A Response to Seeing the Forest for the Trees

Abstract

In this commentary, we highlight some of the strengths of the bibliometric analysis conducted by Qin et al. that examines the relationships between environmental and natural resource sociologies through citation networks, coauthorship, and keyword usage. We also suggest some ways that the analysis could be expanded or built upon, and ideas for further distinct, but related, inquiry. We also reflect on our own identification, training, and mentoring within the two subfields and draw upon responses from a small purposefully selected sample of other early/mid-career environmental and natural resource sociologists to start a conversation about what the relationship between the two fields might look like in the future.     

Delmarva Coastal Bays Map Contest for Fourth Graders

Abstract

This map contest is an exercise in geographic education for fourth grade students. It is sponsored by a grassroots, nonprofit environmental organization to raise the awareness and appreciation of students to the special features of their home region. The maps illustrate some aspect of the living resources or history of the region. As a case study of the map contest, this paper describes its design, publicity, appeal to teachers, judging of entries, and role of volunteers. It considers the research on map skills among young students and ways in which the contest supports geographic education.     

汉族女性妊娠期高血压疾病的流行病学及发病机制研究

目的 探讨汉族女性妊娠期高血压疾病的流行病学及发病机制研究。方法 选取笔者医院10年内妊娠期高血压疾病患者689例,作为病例组,选取689例正常妊娠的女性作为对照组,采用多中心、大规模、随机队列研究方法分析汉族女性妊娠期高血压疾病患者（病例组）和对照组的资料,并通过电话随访对家属进行固定问卷式问题,对对象的年龄、孕前体重指数、孕次、产次、流产次数、孕中期平均动脉压、子痫前期史、糖尿病或肾脏疾病史、多胎妊娠等相关因素进行分析,并进行Logistic回归分析;对两组研究对象的ACE基因和AT1R基因水平、Th1/Th2比值、胎盘生长因子（PLGF）、活性氧（ROS）水平和脂质过氧化物（LPO）,分析汉族女性妊娠期高血压疾病的发病与免疫学、遗传学、氧化应激的关系。结果 年龄>35岁的初产女性、过高或过低的孕前体重指数、孕中期平均动脉压高、流产次数高、具有子痫前期史、糖尿病或肾脏疾病史、多胎妊娠的女性是导致汉族女性妊娠期高血压疾病的主要单因素（P<0.05）;多因素分析年龄>35岁的初产女性、过高或过低的孕前体重指数、孕中期平均动脉压高、具有子痫前期史、糖尿病或肾脏疾病史、多胎妊娠是导致汉族女性妊娠期高血压疾病的危险因素（P<0.05）;病例组的ACE基因和AT1R基因、Th1/Th2比值、PLGF、ROS和LPO与对照组差异有统计学意义（P<0.05）。结论 汉族女性妊娠期高血压疾病的发病与免疫学、遗传学、胎盘或滋养细胞缺血、氧化应激中的相关指标有关,而且>35岁的初产女性、过高或过低的孕前体重指数、孕中期平均动脉压高、具有子痫前期史、糖尿病或肾脏疾病史、多胎妊娠是导致汉族女性妊娠期高血压疾病的危险因素。     

Organization of Feature-, Time-, and Location-Based Mental Models

This study considers how mental models are encoded into memory by viewing visual displays like maps. A mental model is an internal representation of a situation that links objects or concepts to other objects or concepts. Previous studies indicated location-based mental models are encoded when a series of propositional statements such as the object is in the location are read from a text. Evidence that locations were being used as the basic container for an organization of mental models is provided by a significant fan effect. A fan effect shows an increase in reaction time with the number of models considered when making a decision. Features, times, and locations were considered as possible containers in the mental models. Subjects created location-based mental models, but also encoded feature-based mental models. A reverse fan effect for time, found for a map animation, suggested the order of the presentation of maps could greatly affect the structure of learned information.     

Residential Location and White Attitudes Toward Mixed-Race Neighborhoods in Kalamazoo,Michigan

Abstract

Past studies have suggested that white attitudes toward mixed-race neighborhoods in northern metropolises vary spatially. Nonetheless, conflicting hypotheses exist in regard to the nature of these spatial patterns and explanations for them. Data gathered within the Kalamazoo Urbanized Area indicate that white attitudes are significantly related to both: 1) the level of interaction between whites and blacks, and 2) the distance between residence and the Negro neighborhood. Attitudes tend to be more favorable with higher interaction levels, and they tend to be less favorable as distance from the Negro neighborhood increases. When control is made for interaction, the relationship between attitude and distance is greatly weakened, indicating that interaction is the dominant variable. That does not eliminate the spatial component, however, because the racial interaction patterns in Kalamazoo are strongly related to distance from the black residential areas.     

Going beyond location: Thematic maps in the early elementary grades

Abstract

Cartographic research has long suggested that preschool and early elementary children possess advanced mapping behaviors in terms of interpreting, making, and using locational and wayfinding maps. To improve instruction in geographic concepts, it is necessary to see if these advanced mapping behaviors apply to thematic or special purpose maps as well, as an understanding of these types of maps is integral to the five fundamental themes of geography. An experiment was conducted to evaluate the thematic mapping abilities of second-grade students. Students viewed maps at the neighborhood, city, and national scales displaying different types of symbolization and presented in a random order. Results indicated that the map tasks were appropriate for this age level, and a statistical test of reaction times did not identify a best symbol type or scale, as all were appropriate for this age level. Responses to discussion questions indicated the students also have the ability to describe spatial patterns. The interpretation of quantitative information on maps is within the ability level of second grade students, and materials currently used in second grade should be revised to include these maps.