Improving Tag Suggestion for Places using Digital Map Data

Martin Garbe

Abstract

Today, tagging photos and website bookmarks is widely used. Geographical data is an additional type of resource which can be tagged. Locations representing geographic information can be tagged depending on activities done there. In this paper we present an explorative study to answer the question whether geographical map data can be used to describe similarities between places. When map data can be used to identify similar places services like tag suggestion could be improved. For the study very detailed crowd-sourced map data was used. In a period of four month places were manually tagged with activities done. A measurement for finding places which are similar in the sense of tagging is also presented. To evaluate our idea, we trained three machine learning classifiers (Decision Tree, Support Vector Machine, Naive Bayes). With a precision of 73% and a recall of 65% Decision Tree performed best. Our results indicate that crowd-based map data can assist in tagging geographical resources and can improve tag suggestion services.

References

  1. Capocci, A. and Caldarelli, G. (2008). Folksonomies and clustering in the collaborative system citeulike. Journal of Physics A: Mathematical and Theoretical, 41(22):224016.
  2. Chawla, N. V. (2010). Data mining for imbalanced datasets: An overview. In Data Mining and Knowledge Discovery Handbook, pages 875-886.
  3. Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P. (2002). SMOTE: synthetic minority oversampling technique. Journal of Artificial Intelligence Research, 16:321-357.
  4. Ermes, M., Parkka, J., Mantyjarvi, J., and Korhonen, I. (2008). Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions. Information Technology in Biomedicine, IEEE Transactions on, 12(1):20 -26.
  5. Gutlein, M., Frank, E., Hall, M., and Karwath, A. (2009). Large-scale attribute selection using wrappers. In CIDM, pages 332-339.
  6. Liao, L., Fox, D., and Kautz, H. (2005). Location-based activity recognition using relational markov networks. In Proceedings of the 19th international joint conference on Artificial intelligence, IJCAI'05, pages 773- 778, San Francisco, CA, USA. Morgan Kaufmann Publishers Inc.
  7. Liao, L., Patterson, D. J., Fox, D., and Kautz, H. (2007). Learning and inferring transportation routines. Artif. Intell., 171:311-331.
  8. Lin, J., Xiang, G., Hong, J. I., and Sadeh, N. (2010). Modeling people's place naming preferences in location sharing. In Proceedings of the 12th ACM international conference on Ubiquitous computing, Ubicomp 7810, pages 75-84, New York, NY, USA. ACM.
  9. Moxley, E., Kleban, J., and Manjunath, B. S. (2008). Spirittagger: a geo-aware tag suggestion tool mined from flickr. In MIR 7808: Proceeding of the 1st ACM international conference on Multimedia information retrieval, pages 24-30, New York, NY, USA. ACM.
  10. Rattenbury, T. and Naaman, M. (2009). Methods for extracting place semantics from flickr tags. ACM Trans. Web, 3(1):1-30.
  11. Zheng, Y., Chen, Y., Li, Q., Xie, X., and Ma, W.-Y. (2010). Understanding transportation modes based on gps data for web applications. ACM Trans. Web, 4(1):1-36.
  12. Zheng, Y., Liu, L., Wang, L., and Xie, X. (2008). Learning transportation mode from raw gps data for geographic applications on the web. In Proceeding of the 17th international conference on World Wide Web, WWW 7808, pages 247-256, New York, NY, USA. ACM.
Download


Paper Citation


in Harvard Style

Garbe M. (2013). Improving Tag Suggestion for Places using Digital Map Data . In Proceedings of the 9th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST, ISBN 978-989-8565-54-9, pages 453-458. DOI: 10.5220/0004372104530458


in Bibtex Style

@conference{webist13,
author={Martin Garbe},
title={Improving Tag Suggestion for Places using Digital Map Data},
booktitle={Proceedings of the 9th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,},
year={2013},
pages={453-458},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004372104530458},
isbn={978-989-8565-54-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,
TI - Improving Tag Suggestion for Places using Digital Map Data
SN - 978-989-8565-54-9
AU - Garbe M.
PY - 2013
SP - 453
EP - 458
DO - 10.5220/0004372104530458