TweetCount: urban insights by counting tweets

ABSTRACT

This paper characterizes an urban region using time series of geotagged tweet counts. Time series are constructed for each cell in a rectangular grid. We show how simple, anonymous tweet counts in the cells can be used to classify the cells into urban land use profiles based on the number of residences and businesses. We discover that Twitter activity for a certain short time of day is especially indicative of a region's profile. We go on to analyze the cells and profiles in a novel way by looking at their ability to predict tweet counts in other parts of the region.

References

1. Handy, S.L., et al., How the built environment affects physical activity: views from urban planning. American journal of preventive medicine, 2002. 23(2): p. 64--73.
2. Ewing, R., et al., Relationship between urban sprawl and physical activity, obesity, and morbidity, in Urban Ecology. 2008, Springer. p. 567--582.
3. Smith, A., U.S. Smartphone Use in 2015, 2015, Pew Research Center.
4. Froehlich, J., et al., Voting with your feet: An investigative study of the relationship between place visit behavior and preference, in Eighth International Conference on Ubiquitous Computing (UbiComp 2006)2006, Springer: Orange County, California, USA. p. 333--350.
5. Liao, L., D. Fox, and H. Kautz, Extracting places and activities from gps traces using hierarchical conditional random fields. The International Journal of Robotics Research, 2007. 26(1): p. 119--134.
6. Krumm, J., R. Caruana, and S. Counts, Learning likely locations, in Twenty-First Conference on User Modeling, Adaptation and Personalization (UMAP 2013)2013, Springer: Rome, Italy. p. 64--76.
7. Pan, G., et al., Land-use classification using taxi GPS traces. Intelligent Transportation Systems, IEEE Transactions on, 2013. 14(1): p. 113--123.
8. Hossain, N., et al., Precise Localization of Homes and Activities: Detecting Drinking-While-Tweeting Patterns in Communities, in 10th International AAAI Conference on Web and Social Media (ICWSM-16)2016. Cologne, Germany.
9. Sadilek, A., et al. Deploying nEmesis: Preventing Foodborne Illness by Data Mining Social Media. in Twenty-Eighth Annual Conference on Innovative Applications of Artificial Intelligence (IAAI 2016). 2016. Phoenix, Arizona USA.
10. Sadilek, A., H.A. Kautz, and V. Silenzio. Predicting disease transmission from geo-tagged micro-blog data. in Twenty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2012). 2012. Toronto, Ontario, Canada.
11. Abdelhaq, H., C. Sengstock, and M. Gertz, Eventweet: Online localized event detection from twitter. Proceedings of the VLDB Endowment, 2013. 6(12): p. 1326--1329.
12. Krumm, J. and E. Horvitz, Eyewitness: identifying local events via space-time signals in Twitter feeds, in Twenty-Third International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2015)2015: Seattle, Washington USA.
13. Steiger, E., et al., Twitter as an indicator for whereabouts of people? Correlating Twitter with UK census data. Computers, Environment and Urban Systems, 2015. 54: p. 255--265.
14. Arribas-Bel, D., et al., Cyber Cities: Social Media as a Tool for Understanding Cities. Applied Spatial Analysis and Policy, 2015. 8(3): p. 231--247.
15. Cranshaw, J. and T. Yano. Seeing a home away from the home: Distilling proto-neighborhoods from incidental data with latent topic modeling. in CSSWC Workshop at NIPS. 2010.
16. Cranshaw, J., et al. The livehoods project: Utilizing social media to understand the dynamics of a city. in 6th International AAAI Conference on Weblogs and Social Media. 2012. Dublin, Ireland.
17. Noulas, A., et al., Exploiting semantic annotations for clustering geographic areas and users in location-based social networks, in AAAI Workshop on the Social Mobile Web2011. p. 32--35.
18. Ferrari, L., et al. Extracting urban patterns from location-based social networks. in 3rd ACM SIGSPATIAL International Workshop on Location-Based Social Networks. 2011. Chicago, Illinois USA: ACM.
19. Morstatter, F., et al., Is the sample good enough? comparing data from twitter's streaming api with twitter's firehose, in Seventh International AAAI Conference on Weblogs and Social Media (ICWSM 2013)2013: Boston, Massachusetts, USA.
20. Watanabe, K., et al. Jasmine: a real-time local-event detection system based on geolocation information propagated to microblogs. in Proceedings of the 20th ACM international conference on Information and knowledge management. 2011. ACM.
21. Friedman, J.H., Greedy function approximation: a gradient boosting machine. Annals of Statistics, 2001. 29(5): p. 1189--1232.
22. Min, W. and L. Wynter, Real-time road traffic prediction with spatio-temporal correlations. Transportation Research Part C: Emerging Technologies, 2011. 19(4): p. 606--616.
23. Barthélemy, M., B. Gondran, and E. Guichard, Large scale cross-correlations in Internet traffic. Physical Review E, 2002. 66(5): p. 056110.
24. Lütkepohl, H., New introduction to multiple time series analysis. 2005: Springer Science & Business Media.

Index Terms

• Applied computing

  • Law, social and behavioral sciences