{"title":"从警方自由文本数据中无监督识别犯罪问题","authors":"Daniel Birks, Alex Coleman, David Jackson","doi":"10.1186/s40163-020-00127-4","DOIUrl":null,"url":null,"abstract":"We present a novel exploratory application of unsupervised machine-learning methods to identify clusters of specific crime problems from unstructured modus operandi free-text data within a single administrative crime classification. To illustrate our proposed approach, we analyse police recorded free-text narrative descriptions of residential burglaries occurring over a two-year period in a major metropolitan area of the UK. Results of our analyses demonstrate that topic modelling algorithms are capable of clustering substantively different burglary problems without prior knowledge of such groupings. Subsequently, we describe a prototype dashboard that allows replication of our analytical workflow and could be applied to support operational decision making in the identification of specific crime problems. This approach to grouping distinct types of offences within existing offence categories, we argue, has the potential to support crime analysts in proactively analysing large volumes of modus operandi free-text data—with the ultimate aims of developing a greater understanding of crime problems and supporting the design of tailored crime reduction interventions.","PeriodicalId":37844,"journal":{"name":"Crime Science","volume":null,"pages":null},"PeriodicalIF":3.1000,"publicationDate":"2020-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Unsupervised identification of crime problems from police free-text data\",\"authors\":\"Daniel Birks, Alex Coleman, David Jackson\",\"doi\":\"10.1186/s40163-020-00127-4\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We present a novel exploratory application of unsupervised machine-learning methods to identify clusters of specific crime problems from unstructured modus operandi free-text data within a single administrative crime classification. To illustrate our proposed approach, we analyse police recorded free-text narrative descriptions of residential burglaries occurring over a two-year period in a major metropolitan area of the UK. Results of our analyses demonstrate that topic modelling algorithms are capable of clustering substantively different burglary problems without prior knowledge of such groupings. Subsequently, we describe a prototype dashboard that allows replication of our analytical workflow and could be applied to support operational decision making in the identification of specific crime problems. This approach to grouping distinct types of offences within existing offence categories, we argue, has the potential to support crime analysts in proactively analysing large volumes of modus operandi free-text data—with the ultimate aims of developing a greater understanding of crime problems and supporting the design of tailored crime reduction interventions.\",\"PeriodicalId\":37844,\"journal\":{\"name\":\"Crime Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.1000,\"publicationDate\":\"2020-10-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Crime Science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1186/s40163-020-00127-4\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"CRIMINOLOGY & PENOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Crime Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1186/s40163-020-00127-4","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CRIMINOLOGY & PENOLOGY","Score":null,"Total":0}
Unsupervised identification of crime problems from police free-text data
We present a novel exploratory application of unsupervised machine-learning methods to identify clusters of specific crime problems from unstructured modus operandi free-text data within a single administrative crime classification. To illustrate our proposed approach, we analyse police recorded free-text narrative descriptions of residential burglaries occurring over a two-year period in a major metropolitan area of the UK. Results of our analyses demonstrate that topic modelling algorithms are capable of clustering substantively different burglary problems without prior knowledge of such groupings. Subsequently, we describe a prototype dashboard that allows replication of our analytical workflow and could be applied to support operational decision making in the identification of specific crime problems. This approach to grouping distinct types of offences within existing offence categories, we argue, has the potential to support crime analysts in proactively analysing large volumes of modus operandi free-text data—with the ultimate aims of developing a greater understanding of crime problems and supporting the design of tailored crime reduction interventions.
期刊介绍:
Crime Science is an international, interdisciplinary, peer-reviewed journal with an applied focus. The journal''s main focus is on research articles and systematic reviews that reflect the growing cooperation among a variety of fields, including environmental criminology, economics, engineering, geography, public health, psychology, statistics and urban planning, on improving the detection, prevention and understanding of crime and disorder. Crime Science will publish theoretical articles that are relevant to the field, for example, approaches that integrate theories from different disciplines. The goal of the journal is to broaden the scientific base for the understanding, analysis and control of crime and disorder. It is aimed at researchers, practitioners and policy-makers with an interest in crime reduction. It will also publish short contributions on timely topics including crime patterns, technological advances for detection and prevention, and analytical techniques, and on the crime reduction applications of research from a wide range of fields. Crime Science publishes research articles, systematic reviews, short contributions and theoretical articles. While Crime Science uses the APA reference style, the journal welcomes submissions using alternative reference styles on a case-by-case basis.