Advertisement

Applying Unsupervised and Supervised Machine Learning Methodologies in Social Media Textual Traffic Data

  • Konstantinos KokkinosEmail author
  • Eftihia Nathanail
  • Elpiniki Papageorgiou
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 879)

Abstract

Traffic increasingly shapes the trajectory of city growth and impacts on the climate change in modern cities. Traffic patterns’ monitoring can provide with innovative practices in understanding city traffic dynamics, especially via utilizing sensory and textual data analytics. State-of-the-art research recently has focused on processing voluminous real time data in vast quantities by capturing real time sensory observations and/or social network (textual) data regarding city traffic. In this paper, we investigate the feasibility of using Big Data produced by Twitter textual streams for extracting traffic related events. After describing a generic yet innovative application used for data capturing, we preprocess this data so they fit into the structuring of the machine learning models for clustering (unsupervised learning) and classification (supervised learning). For the case of clustering we use Apache Spark on a MapR sandbox with the use of KMeans algorithm. For the classification case we compare various machine learning methodologies including Multi-Layer Perceptron Neural Networks, (MLP-NN), Support Vector Machines, (SVM) and a Deep Convolutional Learning, (DCL) approach to contextualize citizen observations and responses via tweets. The criteria of precision, accuracy, recall and F-score are used as statistical metrics to determine the accuracy and performance of each model. Our experiments include clustering, a 2-class and a 3-class classification, where, MLP-NN gave accuracy of 89.6%, SVM 92.73% and DCL was inferior performing at 81.76%.

Keywords

Unsupervised Supervised Deep Learning Big Data Textual Traffic 

References

  1. 1.
    Liu, B., Hu, M., Cheng, J.: Opinion observer: analyzing and comparing opinions on the web. In: Proceedings of the 14th International Conference on World Wide Web, pp. 342–351. ACM (2005)Google Scholar
  2. 2.
    Cao, J., Zeng, K., Wang, H., Cheng, J., Qiao, F., Wen, D., Gao, Y.: Web-based traffic sentiment analysis: methods and applications. IEEE Trans. Intell. Transport. Syst. 15(2), 844–853 (2014)CrossRefGoogle Scholar
  3. 3.
    Kim, S.M., Hovy, E.: Extracting opinions, opinion holders, and topics expressed in online news media text. In: Proceedings of the Workshop on Sentiment and Subjectivity in Text. Association for Computational Linguistics, pp. 1–8 (2006)Google Scholar
  4. 4.
    Stieglitza, S., Mirbabaiea, M., Rossa, B., Neubergerb, C.: Social media analytics – challenges in topic discovery, data collection, and data preparation. Int. J. Inf. Manag. 39, 156–168 (2018)CrossRefGoogle Scholar
  5. 5.
    Atefeh, F., Khreich, W.: A survey of techniques for event detection in Twitter. Comput. Intell. 31(1), 132–164 (2015)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Ruchi, P., Kamalakar, K.: ET: events from tweets. In: Proceedings of the 22nd International Conference of World Wide Web Computing, Rio de Janeiro (2013)Google Scholar
  7. 7.
    Twitraffic Homepage. https://uk-traffic-news-twitraffic.soft112.com/. Accessed 10 Dec 2017
  8. 8.
    Carvalho, J., Rosa, H., Brogueira, G., Batista, F.: MISNIS: an intelligent platform for Twitter topic mining. Expert Syst. Appl. 89, 374–388 (2017)CrossRefGoogle Scholar
  9. 9.
    Arın, I., Erpam, M., Saygın, Y.: I-TWEC: interactive clustering tool for Twitter. Expert Syst. Appl. 96, 1–13 (2018)CrossRefGoogle Scholar
  10. 10.
    Liu, H., Ge, Y., Zheng, Q., Lin, R., Li, H.: Detecting global and local topics via mining Twitter data. Neurocomputing 273, 120–132 (2018)CrossRefGoogle Scholar
  11. 11.
    Alamy, I., Ahmedy, M., Alamy, M., Ulissesz, J., Faridy, D., Shatabday, S., Rossettiz, R.: Pattern mining from historical traffic Big Data. In: IEEE Region 10 Symposium (TENSYMP) (2017)Google Scholar
  12. 12.
    Guerreiro, G., Figueiras, P., Silva, R., Costa, R. Goncalves, R.: An architecture for Big Data processing on intelligent transportation systems. In: IEEE 8th International Conference on Intelligent Systems (2016). ISBN 978-1-5090-1354-8/16/$31.00Google Scholar
  13. 13.
    Guo, Y., Zhang, J., Zhang, Y.: A Method of traffic congestion state detection based on mobile Big Data. In: IEEE 2nd International Conference on Big Data Analysis (2017). ISBN 978-1-5090-3619-6/17/$31.00Google Scholar
  14. 14.
    Cosine Similarity. https://en.wikipedia.org/wiki/Cosine_similarity. Accessed 10 Dec 2017
  15. 15.
    Montazeri-Gh, M., Fotouhi, A.: Traffic condition recognition using the K-means clustering method. Trans. B Mech. Eng. Sci. Iran. 18(4), 930–937 (2011)Google Scholar
  16. 16.
    Zhong, S.: Efficient online spherical K-means clustering. In: Proceedings of IEEE International Joint Conference on Neural Networks. Published in IJCNN (2005)Google Scholar
  17. 17.
    Twitter4J: Java Library for Twitter Mining. http://twitter4j.org/en/. Accessed 17 Dec 2017
  18. 18.
    Habibi, M.: Real World Regular Expressions with Java 1.4. Springer, Berlin (2004)Google Scholar
  19. 19.
    Hotho, A., Nürnberger, A., Paaß, G.: A brief survey of text mining, LDV Forum-GLDV. J. Comput. Linguist. Lang. Technol. 20(1), 19–62 (2005)Google Scholar
  20. 20.
    Zhou, Y., Cao, Z.-W.: Research on the construction and filter method of stop-word list in text preprocessing. In: Proceedings of the 4th ICICTA, Shenzhen, vol. 1, pp. 217–221, (2011)Google Scholar
  21. 21.
    Porter, M.F.: An algorithm for suffix stripping. Program 14(3), 130–137 (1980). Program electronic library and information systemsCrossRefGoogle Scholar
  22. 22.
    Aiello, L.-C., Petkos, G., Martin, C., Corney, D., Papadopoulos, S., Skraba, R., Göker, A.: Sensing trending topics in Twitter. IEEE Trans. Multimed. 15(6), 1268–1282 (2013)CrossRefGoogle Scholar
  23. 23.
    APRIL-ANN Toolkit: https://github.com/april-org. Accessed 16 Nov 2017
  24. 24.
    Platt, J.: Fast training of support vector machines using sequential minimal optimization. In: Schoelkopf, B., Burges, C., Smola, A. (eds.) Advances in Kernel Methods: Support Vector Learning, pp 185–208. MIT Press, Cambridge (1999)Google Scholar
  25. 25.
    Severyn, A., Moschitti, A.: Twitter sentiment analysis with deep convolutional neural networks. In: Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2015, Santiago, pp. 950–962 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Konstantinos Kokkinos
    • 1
    Email author
  • Eftihia Nathanail
    • 2
  • Elpiniki Papageorgiou
    • 1
    • 3
  1. 1.Computer Science DepartmentUniversity of ThessalyLamiaGreece
  2. 2.Civil Engineering DepartmentUniversity of ThessalyVolosGreece
  3. 3.Electrical Engineering DepartmentUniversity of Applied Sciences, Technological Educational Institute of Central GreeceLamiaGreece

Personalised recommendations