Spatial Statistics of Term Co-occurrences for Location Prediction of Tweets

  • Ozer OzdikisEmail author
  • Heri Ramampiaro
  • Kjetil Nørvåg
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10772)


Predicting the locations of non-geotagged tweets is an active research area in geographical information retrieval. In this work, we propose a method to detect term co-occurrences in tweets that exhibit spatial clustering or dispersion tendency with significant deviation from the underlying single-term patterns, and use these co-occurrences to extend the feature space in probabilistic language models. We observe that using term pairs that spatially attract or repel each other yields significant increase in the accuracy of predicted locations. The method we propose relies purely on statistical approaches and spatial point patterns without using external data sources or gazetteers. Evaluations conducted on a large set of multilingual tweets indicate higher accuracy than the existing state-of-the-art methods.


Location prediction Tweet localization Spatial point patterns Feature extraction 


  1. 1.
    Li, W., Eickhoff, C., de Vries, A.P.: Geo-spatial domain expertise in microblogs. In: de Rijke, M., Kenter, T., de Vries, A.P., Zhai, C.X., de Jong, F., Radinsky, K., Hofmann, K. (eds.) ECIR 2014. LNCS, vol. 8416, pp. 487–492. Springer, Cham (2014). CrossRefGoogle Scholar
  2. 2.
    Paraskevopoulos, P., Palpanas, T.: Where has this tweet come from? Fast and fine-grained geolocalization of non-geotagged tweets. Soc. Netw. Anal. Min. 6(1), 89 (2016)CrossRefGoogle Scholar
  3. 3.
    Melo, F., Martins, B.: Automated geocoding of textual documents: a survey of current approaches. Trans. GIS 21(1), 3–38 (2017)CrossRefGoogle Scholar
  4. 4.
    Zheng, X., Han, J., Sun, A.: A survey of location prediction on Twitter. CoRR abs/1705.03172 (2017)Google Scholar
  5. 5.
    Han, B., Cook, P., Baldwin, T.: Text-based Twitter user geolocation prediction. J. Artif. Int. Res. 49(1), 451–500 (2014)Google Scholar
  6. 6.
    Priedhorsky, R., Culotta, A., Del Valle, S.Y.: Inferring the origin locations of tweets with quantitative confidence. In: Proceedings of CSCW 2014 (2014)Google Scholar
  7. 7.
    Han, B., Rahimi, A., Derczynski, L., Baldwin, T.: Twitter geolocation prediction shared task of the 2016 workshop on noisy user-generated text. In: Proceedings of W-NUT (2016)Google Scholar
  8. 8.
    Cheng, Z., Caverlee, J., Lee, K.: A content-driven framework for geolocating microblog users. ACM Trans. Intell. Syst. Technol. 4(1), 2:1–2:27 (2013)CrossRefGoogle Scholar
  9. 9.
    Van Laere, O., Quinn, J., Schockaert, S., Dhoedt, B.: Spatially aware term selection for geotagging. IEEE Trans. Knowl. Data Eng. 26(1), 221–234 (2014)CrossRefGoogle Scholar
  10. 10.
    Dredze, M., Osborne, M., Kambadur, P.: Geolocation for Twitter: timing matters. In: Proceedings of HLT-NAACL (2016)Google Scholar
  11. 11.
    Hauff, C., Houben, G.J.: Placing images on the world map: a microblog-based enrichment approach. In: Proceedings of ACM SIGIR 2012, 691–700 (2012)Google Scholar
  12. 12.
    Backstrom, L., Sun, E., Marlow, C.: Find me if you can: improving geographical prediction with social and spatial proximity. In: Proceedings of WWW 2010, pp. 61–70 (2010)Google Scholar
  13. 13.
    Eisenstein, J., O’Connor, B., Smith, N.A., Xing, E.P.: A latent variable model for geographic lexical variation. In: Proceeding of EMNLP 2010, pp. 1277–1287 (2010)Google Scholar
  14. 14.
    Miura, Y., Taniguchi, M., Taniguchi, T., Ohkuma, T.: A simple scalable neural networks based model for geolocation prediction in Twitter. In: Proceedings of W-NUT (2016)Google Scholar
  15. 15.
    O’Hare, N., Murdock, V.: Modeling locations with social media. Inf. Retr. 16(1), 30–62 (2013)CrossRefGoogle Scholar
  16. 16.
    Yang, Y., Pedersen, J.O.: A comparative study on feature selection in text categorization. In: Proceedings of ICML 1997 (1997)Google Scholar
  17. 17.
    Ripley, B.D.: Modelling spatial patterns. J. Roy. Stat. Soc.: Ser. B (Methodol.) 39(2), 172–212 (1977)MathSciNetGoogle Scholar
  18. 18.
    Ruocco, M., Ramampiaro, H.: Geo-temporal distribution of tag terms for event-related image retrieval. Inf. Process. Manage. 51(1), 92–110 (2015)CrossRefGoogle Scholar
  19. 19.
    Lee, K., Caverlee, J., Webb, S.: Uncovering social spammers: social honeypots + machine learning. In: Proceedings of ACM SIGIR 2010, pp. 435–442 (2010)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Ozer Ozdikis
    • 1
    Email author
  • Heri Ramampiaro
    • 1
  • Kjetil Nørvåg
    • 1
  1. 1.Norwegian University of Science and TechnologyTrondheimNorway

Personalised recommendations