While conventional crime prediction methods rely on historical crime records and geographical information of the location of interest, we pursue the question of whether a social media context can provide socio-behavior “signals” for a crime prediction problem. The hypothesis is that crowd publicly available data in Twitter may include predictive variables which can indicate changes in crime rates without being only limited to the availability of historical crime records of specific locations. We developed a prediction model for crime trend prediction, where the objective is to employ Twitter content to predict crime rate directions in a prospective time-frame. The model employs content, sentiment, and topics, as the predictive indicators to infer the changes of crime indexes. Since our problem has a sequential order, we propose a temporal topic detection model to infer predictive topics over time. The main challenge of topic detection over time is information evolution, in which data are more related when they are close in time rather than further apart. Our proposed topic detection model builds a dynamic vocabulary to detect emerging topics rather than considering a vocabulary in bulk. We applied our model on data collected from Chicago for crime trend prediction using historical tweets. The results have revealed the correlation between features extracted from the content as content-based features and the crime trends. Moreover, the results indicate the feasibility of our proposed temporal topic detection model in identifying the most predictive features over time compared to a static model without time consideration. We also studied the contribution of socio-economic indexes and temporal features as auxiliary features. The experiment shows the content-based features improve the prediction performance significantly compared to the auxiliary features. Overall, the study provides a deep insight into the correlation between language and crime trends and the impact of social data as an extra resource in providing predictive indicators.
WeinbergS.K., Theories of criminality and problems of prediction, The Journal of Criminal Law, Criminology, and Police Science (1954), 412–424.
3.
EckJ.ChaineyS.CameronJ. and WilsonR., Mapping crime: Understanding hotspots, 2005.
4.
MarwickA.E. et al., I tweet honestly, i tweet passionately: Twitter users, context collapse, and the imagined audience, New Media & Society13(1) (2011), 114–133.
5.
WaldR.KhoshgoftaarT.M.NapolitanoA. and SumnerC., Using twitter content to predict psychopathy, in Machine Learning and Applications (ICMLA), 2012 11th International Conference on, vol. 2. IEEE, 2012, pp. 394–401.
6.
KıcımanE., Language differences and metadata features on twitter, in Web N-gram Workshop, 2010, p. 47.
7.
WakamiyaS.LeeR. and SumiyaK., Crowd-based urban characterization: Extracting crowd behavioral patterns in urban areas from twitter, in Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Location-Based Social Networks. ACM, 2011, pp. 77–84.
8.
AchrekarH.GandheA.LazarusR.YuS.-H. and LiuB., Twitter improves seasonal influenza prediction, in HEALTHINF, 2012, pp. 61–70.
9.
WangX.GerberM.S. and BrownD.E., Automatic crime prediction using events extracted from twitter posts, in Social Computing, Behavioral-Cultural Modeling and Prediction. Springer, 2012, pp. 231–238.
10.
LatanéB., The psychology of social impact, American Psychologist36(4) (1981), 343.
11.
AhmedA. and XingE.P., Timeline: A dynamic hierarchical dirichlet process model for recovering birth/death and evolution of topics in text stream, arXiv preprint arXiv:1203.3463, 2012.
12.
AlSumaitL.BarbaráD. and DomeniconiC., On-line lda: Adaptive topic models for mining text streams with applications to topic detection and tracking, in Data Mining, 2008. ICDM’08. Eighth IEEE International Conference on, IEEE, 2008, pp. 3–12.
13.
ChaineyS.TompsonL. and UhligS., The utility of hotspot mapping for predicting spatial patterns of crime, Security Journal21(1) (2008), 4–28.
14.
WangX. and BrownD.E., The spatio-temporal modeling for criminal incidents, Security Informatics1(1) (2012), 1–17.
15.
XueY. and BrownD.E., Spatial analysis with preference specification of latent decision makers for criminal event prediction, Decision Support Systems41(3) (2006), 560–573.
16.
MohlerG.O.ShortM.B.BrantinghamP.J.SchoenbergF.P. and TitaG.E., Self-exciting point process modeling of crime, Journal of the American Statistical Association106(493) (2011).
17.
GeorgeA.B. and TitaE., 9 social networks and the ecology of crime: Using social network data to understand the spatial distribution of crime, 2012, pp. 128–143.
18.
HippJ.R.ButtsC.T.ActonR.NagleN.N. and BoessenA., Extrapolative simulation of neighborhood networks based on population spatial distribution: Do they predict crime? Social Networks35(4) (2013), 614–625.
19.
BogomolovA.LepriB.StaianoJ.OliverN.PianesiF. and PentlandA., Once upon a crime: Towards crime prediction from demographics and mobile data, in Proceedings of the 16th International Conference on Multimodal Interaction. ACM, 2014, pp. 427–434.
20.
TraunmuellerM.QuattroneG. and CapraL., Mining mobile phone data to investigate urban crime theories at scale, in Social Informatics, Springer, 2014, pp. 396–411.
21.
WeisburdD. and GreenL., Defining the street-level drug market, 1994.
22.
SakakiT.OkazakiM. and MatsuoY., Earthquake shakes twitter users: real-time event detection by social sensors, in Proceedings of the 19th International Conference on World Wide Web. ACM, 2010, pp. 851–860.
23.
WengJ. and LeeB.-S., Event detection in twitter, ICWSM11 (2011), 401–408.
24.
ChenY.ZhouY.ZhuS. and XuH., Detecting offensive language in social media to protect adolescent online safety, in Privacy, Security, Risk and Trust (PASSAT), 2012 International Conference on and 2012 International Confernece on Social Computing (SocialCom). IEEE, 2012, pp. 71–80.
25.
BollenJ.MaoH. and ZengX., Twitter mood predicts the stock market, Journal of Computational Science2(1) (2011), 1–8.
26.
HaleS.GaffneyD. and GrahamM., Where in the world are you? geolocation and language identification in twitter, Proceedings of ICWSM’12 (2012), 518–521.
27.
MallesonN. and AndresenM.A., The impact of using social media data in crime rate calculations: shifting hot spots and changing spatial patterns, Cartography and Geographic Information Science42(2) (2015), 112–121.
28.
GerberM.S., Predicting crime using twitter and kernel density estimation, Decision Support Systems61 (2014), 115–125.
29.
ChenX.ChoY. and JangS.Y., Crime prediction using twitter sentiment and weather, in Systems and Information Engineering Design Symposium (SIEDS), 2015. IEEE, 2015, pp. 63–68.
30.
MishraS., Crime drop of the 1990s, The Encyclopedia of Criminology and Criminal Justice, 2014.
31.
WhiteK.LiG. and JapkowiczN., Sampling online social networks using coupling from the past, in Data Mining Workshops (ICDMW), 2012 IEEE 12th International Conference on. IEEE, 2012, pp. 266–272.
32.
PennebakerJ.W.FrancisM.E. and BoothR.J., Linguistic inquiry and word count: Liwc 2001, Mahway: Lawrence Erlbaum Associates71 (2001), 2001.
33.
MakrehchiM., Social link recommendation by learning hidden topics, in Proceedings of the Fifth ACM Conference on Recommender Systems. ACM, 2011, pp. 189–196.
34.
ChuangJ.ManningC.D. and HeerJ., Termite: Visualization techniques for assessing textual topic models, in Proceedings of the International Working Conference on Advanced Visual Interfaces. ACM, 2012, pp. 74–77.
35.
BleiD.M.NgA.Y. and JordanM.I., Latent dirichlet allocation, the Journal of Machine Learning Research3 (2003), 993–1022.
36.
WeiX. and CroftW.B., Lda-based document models for ad-hoc retrieval, in Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2006, pp. 178–185.
37.
MeiQ.LingX.WondraM.SuH. and ZhaiC., Topic sentiment mixture: modeling facets and opinions in weblogs, in Proceedings of the 16th International Conference on World Wide Web. ACM, 2007, pp. 171–180.
38.
HindleA.GodfreyM.W. and HoltR.C., What’s hot and what’s not: Windowed developer topic analysis, in Software Maintenance, 2009. ICSM 2009. IEEE International Conference on. IEEE, 2009, pp. 339–348.
39.
StiloG. and VelardiP., Time makes sense: Event discovery in twitter using temporal similarity, in Proceedings of the 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT)-Volume 02. IEEE Computer Society, 2014, pp. 186–193.
40.
MikolovT.ChenK.CorradoG. and DeanJ., Efficient estimation of word representations in vector space, arXiv preprint arXiv:1301.3781, 2013.
41.
GuoX.XiangY.ChenQ.HuangZ. and HaoY., Lda-based online topic detection using tensor factorization, Journal of Information Science (2013), 0165551512473066.
42.
LauJ.H.CollierN. and BaldwinT., On-line trend analysis with topic models:n # twitter trends detection topic model online. in COLING. Citeseer, 2012, pp. 1519–1534.
43.
FanR.-E.ChangK.-W.HsiehC.-J.WangX.-R. and LinC.-J., Liblinear: A library for large linear classification, The Journal of Machine Learning Research9 (2008), 1871–1874.
44.
ChangC.-C. and LinC.-J., Libsvm: a library for support vector machines, ACM Transactions on Intelligent Systems and Technology (TIST)2(3) (2011), 27.
45.
HoffmanM.BachF.R. and BleiD.M., Online learning for latent dirichlet allocation, in Advances in Neural Information Processing Systems, 2010, pp. 856–864.
46.
BlumA.KalaiA. and LangfordJ., Beating the hold-out: Bounds for k-fold and progressive cross-validation, in Proceedings of the Twelfth Annual Conference on Computational Learning Theory. ACM, 1999, pp. 203–208.
47.
AndersonC.A., Temperature and aggression: effects on quarterly, yearly, and city rates of violent and nonviolent crime, Journal of Personality and Social Psychology52(6) (1987), 1161.
48.
RaphaelS. and Winter-EbmerR., Identifying the effect of unemployment on crime, Journal of Law and Economics44(1) (2001), 259–283.
49.
CohenL.E. and FelsonM., Social change and crime rate trends: A routine activity approach, American sociological review, 1979, pp. 588–608.
