Placer: semantic place labels from diary data

ABSTRACT

Semantic place labels are labels like "home", "work", and "school" given to geographic locations where a person spends time. Such labels are important both for giving understandable location information to people and for automatically inferring activities. Deployed products often compute semantic labels with heuristics, which are difficult to program reliably. In this paper, we develop Placer, an algorithm to infer semantic places labels. It uses data from two large, government diary studies to create a principled algorithm for labeling places based on machine learning. Our labeling reduces to a classification problem, where we classify locations into different label categories based on individual demographics, the timing of visits, and nearby businesses. Using these government studies gives us an unprecedented amount of training and test data. For instance, one of our experiments used training data from 87,600 place visits (from 10,372 distinct people) evaluated on 1,135,053 visits (from 124,517 distinct people). We show labeling accuracy for a number of experiments, including one that gives a 14 percentage point increase in accuracy when labeling is a function of nearby businesses in addition to demographic and time features. We also test on GPS data from 28 subjects.

References

1. Miluzzo, E., et al., CenceMe - Injecting Sensing Presence into Social Networking Applications in 2nd European Conference on Smart Sensing and Context (EuroSSC 2007)2007, Springer-Verlag. p. 1--28.
2. Ye, M., et al., On the Semantic Annotation of Places in Location-Based Social Networks, in The 17th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2011)201 p. 520--528.
3. Partridge, K. and P. Golle, On Using Existing Time-Use Study Data for Ubiquitous Computing Applications, in 10th International Conference on Ubiquitous Computing (UbiComp 08)2008, ACM. p. 144--153.
4. American Time Use Survey. Available from: http://www.bls.gov/tus/.
5. Zhu, Y., Y. Sun, and Y. Wang, Nokia Mobile Data Challenge: Predicting Semantic Place and Next Place via Mobile Data, in Mobile Data Challenge 2012 Workshop 2012.
6. Kim, D.H., K. Han, and D. Estrin, Employing User Feedback for Semantic Location Services in 13th International Conference on Ubiquitous Computing (UbiComp 2011)2011, ACM. p. 217--226.
7. Phithakkitnukoon, S., et al., Activity-Aware Map: Identifying Human Daily Activity Pattern Using Mobile Phone Data, in First International Workshop on Human Behavior Understanding (HBU 2010)2010, Springer-Verlag. p. 14--25.
8. Wolf, J., R. Guensler, and W. Bachman, Elimination of the Travel Diary: An Experiment to Derive Trip Purpose From GPS Travel Data. Transportation Research Record: Journal of the Transportation Research Board, 2001. 01(3255): p. 125--134.
9. Xie, R., et al., Pattern Mining, Semantic Label Identification and Movement Prediction Using Mobile Phone Data, in 8th International Conference on Advanced Data Mining and Applications (ADMA 2012)2012, Springer-Verlag. p. 419--430.
10. Lin Liao, D.F., Henry 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.
11. Chen, Z., et al., A Supervised Learning based Semantic Location Extraction Method using Mobile Phone Data, in 2012 IEEE International Conference on Computer Science and Automation Engineering (CSAE 2012)2012. p. 548--551.
12. Laurila, J.K., et al., The Mobile Data Challenge: Big Data for Mobile Computing Research, in Mobile Data Challenge 2012 Workshop 2012.
13. Montoliu, R., A. Martínez-Uso, and J. Martínez-Sotoca, Semantic place prediction by combining smart binary classifiers, in Mobile Data Challenge 2012 Workshop 2012.
14. Zhu, Y., et al., Feature Engineering for Place Category Classification, in Mobile Data Challenge 2012 Workshop 2012.
15. Huang, C.-M., J.J.-C. Ying, and V.S. Tseng, Mining Users' Behaviors and Environments for Semantic Place Prediction, in Mobile Data Challenge 2012 Workshop 2012.
16. Puget Sound 2006 Household Activity Survey. Available from: http://www.psrc.org/data/surveys/2006-household/.
17. Friedman, J.H., Greedy Function Approximation: A Gradient Boosting Machine. Annals of Statistics, 2001. 29(5): p. 1189--1232.
18. Marmasse, N. and C. Schmandt, Location-Aware Information Delivery with ComMotion, in Second International Symposium on Handheld and Ubiquitous Computing2000. p. 157--171.
19. Ashbrook, D. and T. Starner, Learning Significant Locations and Predicting User Movement with GPS, in Sixth International Symposium on Wearable Computers (ISWC 2002)2002. p. 101--108.
20. Kang, J.H., et al., Extracting Places from Traces of Locations, in 2nd ACM International Workshop on Wireless Mobile Applications and Services on WLAN Hotspots (WMASH 2004)2004. p. 110--118.
21. Hightower, J., et al., Learning and Recognizing the Places We Go, in 7th International Conference on Ubiquitous Computing (UbiComp 2005)2005, Springer. p. 159--176.
22. Caoy, X., G. Congy, and C.S. Jensen, Mining Significant Semantic Locations From GPS Data, in Proceedings of the VLDB Endowment 2010. p. 1009--1020.
23. Diggelen, F.v., GNSS Accuracy: Lies, Damn Lies, and Statistics, in GPS World2007. p. 26--3.
24. Weisstein, E.W. Normal Difference Distribution. Available from: http://mathworld.wolfram.com/NormalDifferenceDistribution.html.
25. Shaikh, S. and H. Kitagawa, Distance-Based Outlier Detection on Uncertain Data of Gaussian Distribution, in 14th Asia-Pacific Web Conference (APWeb 2012)2012, Springer. p. 109--121.

Index Terms

• Computing methodologies

  • Machine learning