ReviewUtilizing geo-referenced imagery for systematic social observation of neighborhood disorder
Introduction
In this review article, an overview of the developments in the use of geo-referenced imagery for the observation of neighborhood disorder is provided. The main purpose of this study is to outline the methodological advances and to focus on the empirical opportunities, and methodological challenges and prospects. We specifically focus on the developments in the use of systematic social observation (hereafter: SSO). SSO is considered as a combination of qualitative and quantitative methods, i.e. “in-depth observational work championed by ethnographers and the large-scale, systematic, and generalizable approaches of quantitative social science” (Brunton-Smith, 2018, p. 294). Reiss (1971) described SSO as a method where:
… observation and recording are done according to explicit procedures which permit replication and that rules are followed which permit the use of the logic of scientific inference. The means of observation and recording, whether a person or some form of technology, must be independent of that which is observed and the effects of observing and measuring must be measurable. (p. 4).
The occurring developments regarding SSO are considered on two axes: the first one based on the type of data used (primary versus secondary), and the second axis based on the nature of the data processing methods (manual versus automated). Those two axes can be represented as a quadrant, resulting in four possible combinations which can also be situated in time (see Fig. 1). Primary data are data collected by researchers for specific research goals and are used in that context. Secondary data are data that are not collected for specific research goals but are used in the context of research or primary data used secondary by other researchers (Hox & Boeije, 2005). In other words: with secondary data, existing data are used retroactively to answer a specific research question. Manual coding means that the researchers are responsible for the processing of the data, with human effort in the coding process itself. In the case of SSO, this often involves the systematic coding of observed facts in which the researcher is interested (e.g. number of graffiti-tags or -pieces, number of units of illegal waste, number of cigarette ends). Automated coding means that this coding is executed computationally, without human effort in the coding process itself. More specifically, techniques that belong to the field of computer vision are used for this automatic coding.
It is not the intention to provide a systematic overview of the use of geo-referenced imagery. For this, we refer to systematic reviews of previous research in different fields (e.g., Aghaabbasi, Moeinaddini, Shah, & Asadi-Shekari, 2018; Rzotkiewicz, Pearson, Dougherty, Shortridge, & Wilson, 2018; Vandeviver, 2014). This narrative review is centered around a number of seminal studies, that give an impetus to or are illustrative for the observation of neighborhood disorder. The aim is to give a concise description of how SSO using geo-referenced imagery is being applied, from a quantitative point of view. After all, social observation also has qualitative applications, such as spatial video geo-narratives1 (e.g., Bell, Phoenix, Lovell, & Wheeler, 2015; Curtis, Curtis, Porter, Jefferis, & Shook, 2016), but these will not be discussed further in this article. SSOs are leveraged across many disciplines, for example in public health (e.g., Bader et al., 2015), sociology (e.g., Hwang & Sampson, 2014), and geography (e.g., Conley, Stein, & Davis, 2014). In this article, we focus specifically on the application of SSO in the field of criminology, by applying it to the observation of social and physical neighborhood disorder, as initiated by Sampson and Raudenbush in the mid-90s.
In what follows, we will first focus on disorder and how this is traditionally measured (Section 2). Next, we will chronologically describe the considered developments, as visualized in Fig. 1. In the first phase, researchers used imagery that they collected themselves and then manually coded (Section 3). In the second phase, they started using secondary data that was being coded manually, this under the influence of an increase in the publicly available secondary imagery data (Section 4). In the third phase, researchers started applying automated coding (based on advances in computer sciences, in particular machine learning and more specifically computer vision) to the publicly available secondary imagery data (Section 5). In the last phase, researchers started the application of this automated coding on imagery data that they collected themselves (Section 6). In the concluding section of this article, we reflect on the relatively fast developments of this research domain and the practical implications of this (Section 7). Finally, we will also consider the promising avenues for future research (Section 8).
Section snippets
Disorder as a study object and its traditional measurement methods
Disorder, also known as incivilities, is a frequently studied phenomenon in criminology (see, among others, Kubrin, 2008; Skogan, 2012). Furthermore, disorder has already been studied for a long time in urban contexts and in particular in research into the relevant processes of social (dis)organization (O'Brien, Farrell, & Welsh, 2019). Disorder is associated with various negative effects, both on an ecological level as well as on an individual level. On an ecological level, we speak of
Primary data, manual coding
An important first step in the application of SSO was the collection of primary data that were coded manually. Since SSO was introduced by Reiss in sociology and criminology in the early 1970s, this research method has been applied on a small scale compared to the more established research methods, such as surveys and interviews. Reiss (1975 in Earls, Raudenbush, Reiss, & Sampson, 2005) states that SSO has several specific advantages, such as higher reliability than self-reports, more precise
Secondary data, manual coding
With the arrival of online mapping software, an important step was taken concerning the amount of (publicly) available imagery. This type of secondary data was first available in a bird's-eye view perspective. Later on, various applications of panoramic imagery on micro-level became available. Sampson (2013) states that “[o]ne of the world's powerful companies in effect implemented PHDCN SSO procedures for observing public places” (p. 9). Google Street View is by far the best known application
Secondary data, automated coding
The use of secondary data results in a significant improvement in efficiency with regard to the data collection, but not with regard to the data processing and analysis. The coding of imagery on a large scale, as described in the previous two paragraphs, still requires a large amount of resources in terms of time and labor costs (Hwang, 2017). The emergence of research and applications in the field of artificial intelligence has led to major advances in the automated coding of imagery data.
Primary data, automated coding
The last phase that we describe relates to developments that are visibly unfolding nowadays. New technologies and artificial intelligence offer perspectives in many areas, and thus also in the area of scientific research. As explained in the previous sections, the use of secondary data has important shortcomings. Efforts have already been made to increase the quality of secondary imagery using sparse representation-based image resolution improvement methods (see Li et al., 2018), but the
Discussion
Synthesizing prior research on the use of imagery in the context of SSO of neighborhood disorder learns that there are large opportunities for both the use of new technologies for the purpose of data collection and the use of artificial intelligent methods for the purpose of data processing in this research domain. These evolutions in the methodological toolkit perfectly align with the original purpose of systematic observation, as initiated in sociology and criminology by Albert J. Reiss Jr.
Avenues for future research
The combination of these ‘big primary data’ and the artificial intelligent data processing and analysis methods is for the time being largely unexplored territory with still plenty of room for exploratory research. The steps that could be taken in the coming years thanks to contemporary technological developments will not only enrich scientific research but will also benefit society when applications are developed and used to measure, detect and prevent disorder and crime. With the promises and
Funding
The authors received no financial support for the research, authorship, and/or publication of this article.
Declaration of Competing Interest
The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.
References (88)
- et al.
Addressing issues in the use of Google tools for assessing pedestrian built environments
Journal of Transport Geography
(2018) - et al.
Development and deployment of the computer assisted neighborhood visual assessment system (CANVAS) to measure health-related neighborhood conditions
Health & Place
(2015) - et al.
Using unmanned aerial systems (UAS) for remotely sensing physical disorder in neighborhoods
Landscape and Urban Planning
(2018) - et al.
Built environment and violent crime: An environmental audit approach using Google Street View
Computers, Environment and Urban Systems
(2017) - et al.
Data collection, primary vs. secundary
- et al.
A reliable, feasible method to observe neighborhoods at high spatial resolution
American Journal of Preventive Medicine
(2017) - et al.
A sparse representation-based image resolution improvement method by processing multiple dictionary pairs with latent Dirichlet allocation model for street view images
Sustainable Cities and Society
(2018) - et al.
Assessing neighborhood disorder: Validation of a three-factor observational scale
The European Journal of Psychology Applied to Legal Context
(2015) - et al.
Understanding social disparities in hypertension prevalence, awareness, treatment, & control: The role of neighborhood context
Social Science & Medicine
(2007) - et al.
Using Google Street View to audit neighborhood environments
American Journal of Preventive Medicine
(2011)
Systematic review of the use of Google Street View in health research: Major themes, strengths, weaknesses and possibilities for future research
Health & Place
The design of a multilevel survey of children, families, and communities: The Los Angeles family and neighborhood survey
Social Science Research
Testing the temporal nature of social disorder through abandoned buildings and interstitial spaces
Social Science Research
Neural networks and deep learning
Total error in a big data world: Adapting the TSE framework to big data
Journal of Survey Statistics and Methodology
Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI
Information Fusion
Using GPS and geo-narratives: A methodological approach for understanding and situating everyday green space encounters
Area
Promise into practice: Application of computer vision in empirical research on social distancing
An on-the-ground challenge to uses of spatial big data in assessing neighborhood character
Geographical Review
Understanding convolutional neural networks for NLP
Systematic social observation
Convergent and discriminant validation by the multitrait-multimethod matrix
Psychological Bulletin
Alcohol in urban streetscapes: A comparison of the use of Google street view and on-street observation
BMC Public Health
A spatial analysis of the neighborhood scale of residential perceptions of physical disorder
Applied Spatial Analysis and Policy
Context and spatial nuance inside a neighborhood’s drug hotspot: Implications for the crime-health nexus
Annals of the American Association of Geographers
Built environment attributes and crime: An automated machine learning approach
Crime Science
CNN architectures: LeNet, AlexNet, VGG, GoogLeNet, ResNet and more
Imagenet: A large-scale hierarchical image database [Paper presentation]
Project on Human Development in Chicago Neighborhoods (PHDCN): Systematic Social Observation, 1995
Robust physical-world attacks on deep learning visual classification [Paper presentation]
Broken windows or window dressing? Citizens’ (in)ability to tell the difference between disorder and crime
Criminology & Public Policy
Using deep learning and Google Street View to estimate the demographic makeup of neighborhoods across the United States
Proceedings of the National Academy of Sciences
Explaining and harnessing adversarial examples
arXiv
Survey Methodology
Total survey error: Past, present, and future
Public Opinion Quarterly
Explainable artificial intelligence (xai)
Making face recognition less biased doesn't make it less scary
A multilevel analysis of collective efficacy, neighborhood disorder, and individual social capital on avoidance behavior
Crime & Delinquency
Measuring the built environment with Google Street View and machine learning: Consequences for crime on street segments
Journal of Quantitative Criminology.
Measuring disorder: Observer bias in systematic social observations at streets and neighborhoods
Journal of Quantitative Criminology
Total twitter error: Decomposing public opinion measurement on Twitter from a total survey error perspective
Invited commentary: Observing neighborhood physical disorder in an age of technological innovation
American Journal of Epidemiology
Divergent pathways of gentrification: Racial inequality and the social order of renewal in Chicago neighborhoods
American Sociological Review
Cited by (4)
Research on Pedestrian Space Disorder in Old City Living Streets: A Case Study on the Anzipian Area of Harbin
2022, IOP Conference Series: Earth and Environmental Science