Abstract
The majority of techniques in socio-behavioral modelling tend to consider user-generated content in a bulk, which may ignore personal contributions of specific users to predictability of the system. We propose a novel user-based approach designed specifically to capture most predictive hidden variables which can be discovered in a context of specific individual only. User content is assessed to determine both the subset of best, “expert”, users able to reflect particular social trend of interest, and their transformation into feature space used for modelling. The technique is tested on a case study of Chicago crime rate trend prediction using historical tweets of selected citizens. We also propose a new user ranking approach which exploits the concept of user credibility.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Chainey, S., Tompson, L., Uhlig, S.: The utility of hotspot mapping for predicting spatial patterns of crime. Security Journal 21(1), 4–28 (2008)
Eck, J., Chainey, S., Cameron, J., Wilson, R.: Mapping crime: Understanding hotspots (2005)
Gerber, M.S.: Predicting crime using twitter and kernel density estimation. Decision Support Systems 61, 115–125 (2014)
Hipp, J.R., Butts, C.T., Acton, R., Nagle, N.N., Boessen, A.: Extrapolative simulation of neighborhood networks based on population spatial distribution: Do they predict crime? Social Networks 35(4), 614–625 (2013)
Pennebaker, J.W., Francis, M.E., Booth, R.J.: Linguistic inquiry and word count: Liwc 2001. Lawrence Erlbaum Associates, Mahway (2001)
Tita, G.E., Boessen, A.: Social networks and the ecology of crime: using social network data to understand the spatial distribution of crime. The SAGE Handbook of Criminological Research Methods, p. 128 (2011)
Wang, X., Brown, D.E.: The spatio-temporal modeling for criminal incidents. Security Informatics 1(1), 1–17 (2012)
Wang, X., Gerber, M.S., Brown, D.E.: Automatic crime prediction using events extracted from twitter posts. In: Yang, S.J., Greenberg, A.M., Endsley, M. (eds.) SBP 2012. LNCS, vol. 7227, pp. 231–238. Springer, Heidelberg (2012)
White, K., Li, G., Japkowicz, N.: Sampling online social networks using coupling from the past. In: 2012 IEEE 12th International Conference on Data Mining Workshops (ICDMW), pp. 266–272. IEEE (2012)
Xue, Y., Brown, D.E.: Spatial analysis with preference specification of latent decision makers for criminal event prediction. Decision Support Systems 41(3), 560–573 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Chepurna, I., Aghababaei, S., Makrehchi, M. (2015). How to Predict Social Trends by Mining User Sentiments. In: Agarwal, N., Xu, K., Osgood, N. (eds) Social Computing, Behavioral-Cultural Modeling, and Prediction. SBP 2015. Lecture Notes in Computer Science(), vol 9021. Springer, Cham. https://doi.org/10.1007/978-3-319-16268-3_29
Download citation
DOI: https://doi.org/10.1007/978-3-319-16268-3_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16267-6
Online ISBN: 978-3-319-16268-3
eBook Packages: Computer ScienceComputer Science (R0)