Skip to main content

Travel topic analysis: a mutually reinforcing method for geo-tagged photos

Abstract

Sharing personal activities on social networks is very popular nowadays, where the activities include updating status, uploading dining photos, sharing video clips, etc. Finding travel interests hidden in these vast social activities is an interesting but challenging problem. In this work, we attempt to discover travel interests based on the spatial and temporal information of geo-tagged photos. Obviously the visit sequence of a traveler can be approximately captured by her shared photos based on the timestamps and geo-locations. To extract underlying travel topics from abundant visit sequences, we study a novel mixture model to estimate the visiting probability of regions of attractions (ROAs). Such travel topics can be used in different applications, such as advertisements, promotion strategies, and city planning. To enhance the estimation result, we propose a mutual reinforcement framework to improve the quality of ROAs. Finally, we thoroughly evaluate and demonstrate our findings by the photo sharing activities collected from Flickr TM.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17

Notes

  1. 1.

    It should be noted that all trajectories (including t 1,t 2, and t 5) are taken into consideration. This is intuitive to the real world scenario, where a traveler may have multiple travel interests so that her tour can be partitioned into several travel topics.

  2. 2.

    To simplify our evaluation, we use minimum bounded rectangle to assign the photos into the ROA of \(\mathbb {M}\).

  3. 3.

    Yang et al. [40] is a parameter free technique.

  4. 4.

    This is because the travel topics discovered by PLSA do not necessarily follow the Dirichlet distribution.

References

  1. 1.

    Ayala G, Sebastián R, Díaz E, Zoncu R, Toomre D (2006) Analysis of spatially and temporally overlapping events with application to image sequences. IEEE TPAMI 28(10):1707–1712

    Article  Google Scholar 

  2. 2.

    Bezahaf M, Iannone L, de Amorim MD, Fdida S (2011) Lord: Tracking mobile clients in a real mesh. Ad Hoc Networks 9(8):1461–1475

    Article  Google Scholar 

  3. 3.

    Blei DM, Lafferty JD (2006) Dynamic topic models. In: ICML, pp 113–120

  4. 4.

    Blei DM, Ng AY, Jordan MI (2003) Latent dirichlet allocation. J Mach Learn Res 3:993–1022

    Google Scholar 

  5. 5.

    Chellappa RK, Sin RG (2005) Personalization versus privacy: An empirical examination of the online consumer’s dilemma. Inf Technol Manag 6(2-3):181–202

    Article  Google Scholar 

  6. 6.

    Cheng AJ, Chen YY, Huang YT, Hsu WH, Liao HYM (2011) Personalized travel recommendation by mining people attributes from community-contributed photos. In: ACM Multimedia , pp 83–92

  7. 7.

    Cheng Y (1995) Mean shift, mode seeking, and clustering. IEEE Trans Pattern Anal Mach Intell 17(8):790–799

    Article  Google Scholar 

  8. 8.

    Cho E, Myers SA, Leskovec J (2011) Friendship and mobility: user movement in location-based social networks. In: KDD, pp 1082–1090

  9. 9.

    Choudhury MD, Feldman M, Amer-Yahia S, Golbandi N, Lempel R, Yu C (2010) Constructing travel itineraries from tagged geo-temporal breadcrumbs. In: WWW, pp 1083–1084

  10. 10.

    Cranor LF, Reagle J, Ackerman MS (2000) Beyond concern: Understanding net users’ attitudes about online privacy. MA: MIT Press, Cambridge

    Google Scholar 

  11. 11.

    Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the em algorithm. J R Stat Soc Ser B 39(1):1–38

    Google Scholar 

  12. 12.

    Giannotti F, Nanni M, Pinelli F, Pedreschi D (2007) Trajectory pattern mining. In: KDD, pp 330– 339

  13. 13.

    Han J, Pei J, Yin Y (2000) Mining frequent patterns without candidate generation. In: Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, May 16-18, 2000, Dallas, Texas, USA. doi:10.1145/342009.335372, pp 1–12

  14. 14.

    Hao Q, Cai R, Wang C, Xiao R, Yang JM, Pang Y, Zhang L (2010) Equip tourists with knowledge mined from travelogues. In: WWW, pp 401–410

  15. 15.

    Hofmann T (1999) Probabilistic latent semantic indexing. In: SIGIR, pp 50–57

  16. 16.

    Jeung H, Shen HT, Zhou X (2007) Mining trajectory patterns using hidden markov models. In: DaWaK, pp 470–480

  17. 17.

    Jeung H, Yiu ML, Jensen CS (2011) Trajectory pattern mining, Computing with Spatial Trajectories. Springer, pp 143–177

  18. 18.

    Jo Y, Hopcroft JE, Lagoze C (2011) The web of topics: discovering the topology of topic evolution in a corpus. In: WWW, pp 257–266

  19. 19.

    Kalnis P, Mamoulis N, Bakiras S (2005) On discovering moving clusters in spatio-temporal data. In: SSTD, pp 364–381

  20. 20.

    Kennedy LS, Naaman M (2008) Generating diverse and representative image search results for landmarks. In: WWW, pp 297–306

  21. 21.

    Kisilevich S, Mansmann F, Keim D A (2010) P-dbscan: a density based clustering algorithm for exploration and analysis of attractive areas using collections of geo-tagged photos. In: COM.Geo

  22. 22.

    Kleinberg JM (1999) Hubs, authorities, and communities. ACM Comput Surv 31(4es):5

    Article  Google Scholar 

  23. 23.

    Kodama K, Iijima Y, Guo X, Ishikawa Y (2009) Skyline queries based on user locations and preferences for making location-based recommendations. In: GIS-LBSN, pp 9–16

  24. 24.

    Kullback S, Leibler RA (1951) On information and sufficiency. Ann Math Stat 22:49–86

    Article  Google Scholar 

  25. 25.

    Kurashima T, Iwata T, Irie G, Fujimura K (2010) Travel route recommendation using geotags in photo sharing sites. In: CIKM, pp 579–588

  26. 26.

    Lee JG, Han J, Whang KY (2007) Trajectory clustering: a partition-and-group framework. In: SIGMOD Conference, pp 593–604

  27. 27.

    Levandoski JJ, Sarwat M, Eldawy A, Mokbel MF (2012) Lars: A location-aware recommender system. In: ICDE, pp 450–461

  28. 28.

    Lin J (1991) Divergence measures based on the shannon entropy. IEEE TIT 37:145–151

    Google Scholar 

  29. 29.

    Lo E, Kao B, Ho WS, Lee SD, Chui CK, Cheung DW (2008) Olap on sequence data. In: SIGMOD Conference, pp 649–660

  30. 30.

    Monreale A, Pinelli F, Trasarti R, Giannotti F (2009) Wherenext: a location predictor on trajectory pattern mining. In: KDD, pp 637–646

  31. 31.

    Park MH, Hong JH, Cho SB (2007) Location-based recommendation system using bayesian user’s preference model in mobile devices. In: UIC, pp 1130–1139

  32. 32.

    Popescu A, Grefenstette G (2009) Deducing trip related information from flickr. In: WWW, pp 1183–1184

  33. 33.

    Popescu A, Grefenstette G (2011) Mining social media to create personalized recommendations for tourist visits. In: COM.Geo, p 37

  34. 34.

    Rattenbury T, Good N, Naaman M (2007) Towards automatic extraction of event and place semantics from flickr tags. In: SIGIR, pp 103–110

  35. 35.

    Shi Y, Serdyukov P, Hanjalic A, Larson M (2011) Personalized landmark recommendation based on geotags from photo sharing sites. In: ICWSM

  36. 36.

    Team TYLW I3 - yahoo flickr creative commons 100m. Accessed: 2014-09-30

  37. 37.

    Wei LY, Zheng Y, Peng WC (2012) Constructing popular routes from uncertain trajectories. In: KDD, pp 195–203

  38. 38.

    Xia J C, Zeephongsekul P, Arrowsmith C (2009) Modelling spatio-temporal movement of tourists using finite markov chains. Math Comput Simul 79(5):1544–1553. doi:10.1016/j.matcom.2008.06.007

    Article  Google Scholar 

  39. 39.

    Yang Y, Gong Z, ULH (2011) Identifying points of interest by self-tuning clustering. In: SIGIR, pp 883–892

  40. 40.

    Yin Z, Cao L, Han J, Zhai C, Huang TS (2011) Geographical topic discovery and comparison. In: WWW, pp 247–256

  41. 41.

    Zhai C, Velivelli A, Yu B (2004) A cross-collection mixture model for comparative text mining. In: KDD, pp 743–748

  42. 42.

    Zheng Y, Zhang L, Ma Z, Xie X, Ma WY (2011) Recommending friends and locations based on individual location history. TWEB 5(1):5

    Article  Google Scholar 

  43. 43.

    Zheng Y, Zhang L, Xie X, Ma WY (2009) Mining interesting locations and travel sequences from gps trajectories. In: WWW, pp 791–800

  44. 44.

    Zheng YT, Zha ZJ, Chua TS (2012) Mining travel patterns from geotagged photos. ACM TIST 3(3):56

    Google Scholar 

Download references

Acknowledgments

This project was supported by grants SRG007-FST11-LHU, MYRG188-FST11-GZG, MYRG109(Y1-L3)-FST12-ULH from University of Macau RC and grant FDCT/106/2012/A3 from Macau FDCT.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Leong Hou U.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Kou, N.M., U, L.H., Yang, Y. et al. Travel topic analysis: a mutually reinforcing method for geo-tagged photos. Geoinformatica 19, 693–721 (2015). https://doi.org/10.1007/s10707-015-0226-x

Download citation

Keywords

  • Web images
  • Travel analysis
  • Regions of attraction
  • Mixture models