Advertisement

Mobility Based Machine Learning Modeling for Event Mining in Social Networks

  • Radhia ToujaniEmail author
  • Zeineb Dhouioui
  • Jalel Akaichi
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 76)

Abstract

Social networks sounds to be a rich source to discover events mobility and analyzing their trends. Hence, the mobility of events refers to the movement of users’ opinions, location, velocity and the continuous change over time. Despite the ability of existing methods to deal with the event mobility and evolution. To the best of our knowledge, there is no research able to show the relation between mobility and social interactions. In this work, we associate mobility into event mining issue. We also describe the movement of opinions in social network and we aim at extracting useful information from tweeter posts, especially during the economic and political event “TUNISIA 2020”. To achieve this task, we focused on the use of machine learning techniques to analyze tunisian tweeter posts and classify their opinions temporally about this event for each Tunisian region. We introduced decision tree method to model and analyze event mobility and to predict the change of opinions from its spatial and temporal co-occurrence. Therefore, an entropy measure has been proposed based on spatio-temporal attributes as branching attributes. Finally, in order to validate our solution, we used real data and we performed some comparative experiments to show the effectiveness of our method.

Keywords

Social networks Event detection Opinion change Temporal mobility Spatial mobility Machine learning Decision tree Spatio-temporal attributes Entropy 

References

  1. 1.
    Kaymak, U., Hogenboom, F., Frasincar, F., Jong, F.D.: An overview of event extraction from text. In: Workshop on Detection, Representation, and Exploitation of Events in the Semantic Web (DeRiVE 2011), CEUR Workshop Proceedings at Tenth International Semantic Web Conference, (ISWC 2011), CEURWS.org (2011)Google Scholar
  2. 2.
    Hogenboom, F., IJntema, W., Sangers, J., Frasincar, F.: A lexico-semantic pattern language for learning ontology instances from text. J. Web Sem. 15, 37–50 (2012)CrossRefGoogle Scholar
  3. 3.
    Lee, R., Sumiya, K.: Measuring geographical regularities of crowd behaviors for twitter-based geo-social event detection. In: Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Location Based Social Networks, CEUR Workshop Proceedings, CEURWS.org. San Jose, California, vol. 779 (2010)Google Scholar
  4. 4.
    Benferhat, S., Amor, N.B., Elouedi, Z.: Decision trees as possibilistic classifiers. Int. J. Approximate Reasoning 48(3), 784–807 (2008)CrossRefGoogle Scholar
  5. 5.
    Chen, L., Zhou, D., He, Y.: A simple bayesian modelling approach to event extraction from twitter. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, vol. 2, pp. 700–705, June 2014. Association for Computational Linguistics, Baltimore, Maryland (2014)Google Scholar
  6. 6.
    Okamoto, M.M., Kikuchi, M.: Discovering volatile events in your neighborhood: Local-area topic extraction from blog entries, vol. 5839. Springer (2009)Google Scholar
  7. 7.
    Xiang, L., Chen, X., Liu, M., Liu, Y., Yang, Q.: Extracting key entities and significant events from online daily news. In: 9th International Conference on Intelligent Data Engineering and Automated Learning - IDEAL 2008, South Korea, pp. 201–209, 2–5 November 2008Google Scholar
  8. 8.
    Zhang, Y., Lei, Z., Wu, L.-D., Liu, Y.-C.: A system for detecting and tracking internet news event, vol. 3767. Springer (2005)Google Scholar
  9. 9.
    Suh Hecht, B., Hong, L., Chi, E.H.: Tweets from justin bieber’s heart: The dynamics of the “location” field in user profiles. In: Proceedings of the ACM Conference on Human Factors in Computing Systems, South Korea, 2–5 November 2011Google Scholar
  10. 10.
    Lavie, A., Sagae, K., MacWhinney, B.: Combining rule-based and data-driven techniques for grammatical relation extraction in spoken language. In: Proceedings of the Eighth International Workshop in Parsing, pp. pp. 153–162 (2003)Google Scholar
  11. 11.
    Okazaki, M., Sakaki, T., Matsuo, Y.: Earthquake shakes twitter users: Real-time event detection by social sensors. In: Proceedings of the 19th International Conference on World Wide Web, pp. pp. 851–860. ACM, New York (2010)Google Scholar
  12. 12.
    Wakamiya, S., Lee, R., Sumiya, K.: Discovery of unusual regional social activities using geo-tagged microblogs. In: Proceedings of the 19th International Conference on World Wide Web, pp. 1–29 (2011)Google Scholar
  13. 13.
    Caverlee, J., Cheng, Z., Lee, K.: You are where you tweet: A content based approach to geo-locating twitter users. In: Proceedings of the 19th ACM International Conference on Information and knowledge management, Toronto, Canada, pp. 759–768 (2011)Google Scholar
  14. 14.
  15. 15.
    Helmut.: TC project (1994). http://www.cis.uni-muenchen.de/schmid/tools/TreeTagger/. Accessed 19 Apr 2015
  16. 16.
    Dhouioui, R., Toujani, Z., Akaichi, J.: Sentiment analysis in social networks using machine learning and metaheuristic. In: Proceedings of the 11th Edition of the Metaheuristics International Conference (MIC 2015), Agadir, Morocco, 7–10th June 2015Google Scholar
  17. 17.
    Quinlan, J.: C4.5: Programs for Machine Learning. Morgan Kaufmann, San Mateo (1993). CA editionGoogle Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Radhia Toujani
    • 1
    Email author
  • Zeineb Dhouioui
    • 1
  • Jalel Akaichi
    • 2
  1. 1.BESTMOD Department, Higher Institute of ManagementUniversity of TunisTunisTunisia
  2. 2.Department of Information Systems, College of Computer ScienceKing Khaled University AbhaAbhaKingdom of Saudi Arabia

Personalised recommendations