Crime Alert! Crime Typification in News Based on Text Mining

In this paper we detailed a multinomial classification-based methodology that combines different algorithms (SVM and MLP) with document representations (Tf Idf vectorization and Doc2vec embedding) and: (i) can distinguish between crime-related news and not-crime related news and; (ii) allows the assignment of each crime-related news to its corresponding crime type. With a F1-score of 84% achieved by the MLP with Doc2vec approach, it can be concluded that it is possible to answer the question of how the crimes are committed (what types of crime are perpetrated) and, in this way, offer a thermometer to citizens about criminal activity in a given territory, as reported by news articles.

[1]  Hussein Zedan,et al.  Crime Type Document Classification from Arabic Corpus , 2009, 2009 Second International Conference on Developments in eSystems Engineering.

[2]  Hanan Samet,et al.  Geotagging with local lexicons to build indexes for textually-specified spatial data , 2010, 2010 IEEE 26th International Conference on Data Engineering (ICDE 2010).

[3]  Indika Perera,et al.  Crime analytics: Analysis of crimes through newspaper articles , 2015, 2015 Moratuwa Engineering Research Conference (MERCon).

[4]  Wang Jing,et al.  Analysis of decision tree classification algorithm based on attribute reduction and application in criminal behavior , 2011, 2011 3rd International Conference on Computer Research and Development.

[5]  Hsinchun Chen,et al.  COPLINK Center: Information and Knowledge Management for Law Enforcement , 2004, DG.O.

[6]  Mansi Ghodsi,et al.  A review of data mining applications in crime , 2016, Stat. Anal. Data Min..

[7]  Yuen-Hsien Tseng,et al.  Name entity extraction based on POS tagging for criminal information analysis and relation visualization , 2012, 2012 6th International Conference on New Trends in Information Science, Service Science and Data Mining (ISSDM2012).

[8]  Craig A. Knoblock,et al.  From Text to Geographic Coordinates: The Current State of Geocoding , 2007 .

[9]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[10]  Chih Hao Ku,et al.  Crime Information Extraction from Police and Witness Narrative Reports , 2008, 2008 IEEE Conference on Technologies for Homeland Security.

[11]  Aziz Nasridinov,et al.  A Decision Tree-Based Classification Model for Crime Prediction , 2013, ITCS.

[12]  Aida Mustapha,et al.  An experimental study of classification algorithms for crime prediction. , 2013 .

[13]  Hanan Samet,et al.  CrimeStand: spatial tracking of criminal activity , 2016, SIGSPATIAL/GIS.

[14]  Gang Wang,et al.  Crime data mining: a general framework and some examples , 2004, Computer.

[15]  Vladia Pinheiro,et al.  Natural Language Processing based on Semantic inferentialism for extracting crime information from text , 2010, 2010 IEEE International Conference on Intelligence and Security Informatics.

[16]  Gondy Leroy,et al.  A decision support system: Automated crime report analysis and classification for e-government , 2014, Gov. Inf. Q..

[17]  Hsinchun Chen,et al.  Extracting Meaningful Entities from Police Narrative Reports , 2002, DG.O.

[18]  Gondy Leroy,et al.  Natural language processing and e-Government: crime information extraction from heterogeneous data sources , 2008, DG.O.

[19]  Gondy Leroy,et al.  A crime reports analysis system to identify related crimes , 2011, J. Assoc. Inf. Sci. Technol..

[20]  Yang Li,et al.  Improving Geocoding Rates in Preparation for Crime Data Analysis , 2007 .

[21]  Jochen L. Leidner,et al.  Grounding spatial named entities for information extraction and question answering , 2003, HLT-NAACL 2003.

[22]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[23]  Gerard Salton,et al.  Term-Weighting Approaches in Automatic Text Retrieval , 1988, Inf. Process. Manag..