{"__content__"=>"\n Objectives\n \n \n Methods\n \n \n Results\n \n \n Conclusions\n \n ", "p"=>[{"__content__"=>"Integrating recent advances in computer vision techniques and mobile phone mobility data, this study extends journey-to-crime research by explicitly examining how burglars’ neighborhood context and spatial knowledge shape their interpretation of physical disorder during spatial target selection."}, {"__content__"=>"We measure observed and perceived physical disorder from a total of 107,858 street view images using computer vision algorithms. Geo-referenced mobile phone flows between 1,652 census units are used to approximate offenders’ potential spatial knowledge about target neighborhoods. Discrete choice models are estimated separately for burglars from disadvantaged and non-disadvantaged neighborhoods ( = 1,972).", "i"=>{"__content__"=>"N"}}, {"__content__"=>"While burglars residing in non-disadvantaged neighborhoods are not sensitive to physical disorder in non-disadvantaged target neighborhoods, they strongly avoid disadvantaged neighborhoods with disorder. Conversely, offenders of neighborhoods with concentrated disadvantage act swiftly on street disorder in better-off neighborhoods but not in disadvantaged neighborhoods. These tendencies to react to physical disorder on the street are further amplified by burglars’ potential spatial familiarity with the target environment."}, {"__content__"=>"We highlight the importance of larger neighborhood structural characteristics and their interactions with spatial knowledge and environmental conditions such as visual signs of disorder, in burglary decision-making. Physical disorder is not uniformly indicative of decay across neighborhoods and offenders. Moreover, spatial knowledge is most effective in triggering or deterring actions in places that are categorically different from offenders’ residential spaces. We discuss the strengths and challenges of our multi-source computational approach for criminology research."}]}