Advertisement

Extracting Semantic Knowledge from Twitter

  • Peter Teufl
  • Stefan Kraxberger
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6847)

Abstract

Twitter is the second largest social network after Facebook and currently 140 millions Tweets are posted on average each day. Tweets are messages with a maximum number of 140 characters and cover all imaginable stories ranging from simple activity updates over news coverage to opinions on arbitrary topics. In this work we argue that Twitter is a valuable data source for e-Participation related projects and describe other domains were Twitter has already been used. We then focus on our own semantic-analysis framework based on our previously introduced Semantic Patterns concept. In order to highlight the benefits of semantic knowledge extraction for Twitter related e-Participation projects, we apply the presented technique to Tweets covering the protests in Egypt starting at January 25 th and resulting in the ousting of Hosni Mubarak on February 11 th 2011. Based on these results and the lessons learned from previous knowledge extraction tasks, we identify key requirements for extracting semantic knowledge from Twitter.

Keywords

Semantic Patterns Twitter Mining e-Participation Semantic Analysis Trend Analysis Semantic Search Machine Learning Social Network Analysis 

References

  1. 1.
    Bifet, A., Frank, E.: Sentiment Knowledge Discovery in Twitter Streaming Data. Cswaikatoacnz, 1–15 (2010), http://www.cs.waikato.ac.nz/~eibe/pubs/Twitter-crc.pdf
  2. 2.
    Burns, A., Eltham, B.: Twitter Free Iran: an Evaluation of Twitter’s Role in Public Diplomacy and Information Operations in Iran’s 2009 Election Crisis. In: Papandrea, F., Armstrong, M. (eds.) Proceedings of Communications Policy Research Forum, pp. 298–310. Network Insight Institute, University of Technology, Sydney (2009), http://eprints.vu.edu.au/15230/ Google Scholar
  3. 3.
    Earle, P.: Earthquake Twitter. Nature Geoscience 3(4), 221–222 (2010), http://dx.doi.org/10.1038/ngeo832 CrossRefGoogle Scholar
  4. 4.
    Ediger, D., Jiang, K., Riedy, J., Bader, D.A., Corley, C.: Massive Social Network Analysis: Mining Twitter for Social Good. In: 2010 39th International Conference on Parallel Processing, pp. 583–593 (2010), http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5599247
  5. 5.
    Go, A., Huang, L., Bhayani, R.: Twitter Sentiment Analysis. Entropy, p. 17 (2009), http://nlp.stanford.edu/courses/cs224n/2009/fp/3.pdf
  6. 6.
    Halpin, H., Robu, V., Shepherd, H.: The complex dynamics of collaborative tagging. In: Proceedings of the 16th International Conference on World Wide Web, WWW 2007, vol. 07(1), p. 211 (2007), http://portal.acm.org/citation.cfm?doid=1242572.1242602
  7. 7.
    Lackner, G., Teufl, P., Weinberger, R.: User Tracking based on Behavioral Fingerprints. In: Heng, S.-H., Wright, R.N., Goi, B.-M. (eds.) CANS 2010. LNCS, vol. 6467, pp. 76–95. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  8. 8.
    Okazaki, M., Matsuo, Y.: Semantic Twitter: Analyzing Tweets for Real-Time Event Notification. In: Breslin, J.G., Burg, T.N., Kim, H.-G., Raftery, T., Schmidt, J.-H. (eds.) Recent Trends and Developments in Social Software. LNCS, vol. 6045, pp. 63–74. Springer, Heidelberg (2010), http://www.springerlink.com/index/R40045K20743206J.pdf CrossRefGoogle Scholar
  9. 9.
    Phuvipadawat, S., Murata, T.: Breaking News Detection and Tracking in Twitter. In: 2010 IEEEWICACM International Conference on Web Intelligence and Intelligent Agent Technology, pp. 120–123 (2010), http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5616930
  10. 10.
    Quincey, E.D., De Quincey, E., Jawaheer, G.: The Potential of Twitter for Early Warning and Outbreak Detection, 2009–2009. City (August 2009), http://www.registration.akm.ch/2010eccmid_einsicht.php?XNABSTRACT_ID=102356&XNSPRACHE_ID=2&XNKONGRESS_ID=114&XNMASKEN_ID=900
  11. 11.
    Ritterman, J., Osborne, M., Klein, E.: Using Prediction Markets and Twitter to Predict a Swine Flu Pandemic. Forecast (2004), 1–9 (2009), http://www.iccs.inf.ed.ac.uk/~miles/papers/swine09.pdf
  12. 12.
    Scanfeld, D., Scanfeld, V., Larson, E.L.: Dissemination of health information through social networks: Twitter and antibiotics. American Journal of Infection Control 38(3), 182–188 (2010), http://www.ncbi.nlm.nih.gov/pubmed/20347636 CrossRefGoogle Scholar
  13. 13.
    Teufl, P., Payer, U., Parycek, P., Macintosh, A., Tambouris, E.: Automated Analysis of e-Participation Data by Utilizing Associative Networks, Spreading Activation and Unsupervised Learning. In: Macintosh, A., Tambouris, E. (eds.) ePart 2009. LNCS, vol. 5694, pp. 139–150. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  14. 14.
    Tumasjan, A., Sprenger, T.O., Sandner, P.G., Welpe, I.M.: Predicting Elections with Twitter: What 140 Characters Reveal about Political Sentiment (2010), http://www.aaai.org/ocs/index.php/ICWSM/ICWSM10/paper/viewFile/1441/1852
  15. 15.
    Wolfram, M.S.A.: Modelling the Stock Market using Twitter. Iccsinformaticsedacuk (2010), http://www.iccs.informatics.ed.ac.uk/~miles/msc-projects/wolfram.pdf

Copyright information

© IFIP International Federation for Information Processing 2011

Authors and Affiliations

  • Peter Teufl
    • 1
  • Stefan Kraxberger
    • 1
  1. 1.IAIKGraz University of TechnologyGrazAustria

Personalised recommendations