Extraction and Sequencing of Keywords from Twitter

  • Harkirat Singh
  • Mukesh Kumar
  • Preeti Aggarwal
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 701)


Social media has been the game changer of this generation much like telephony was for the previous. The amount of information available on this platform is huge. This information if extracted and analyzed, can be an immensely helpful source of news and latest developments around the world. As a source and sink of information, it is much faster than traditional news channels and media platforms. This paper uses Twitter data to extract keywords and then sequence them to give useful information. Keywords are extracted from graph constructed from users’ posts by heaviest k-subgraph problem. We then proposed a method to sequence extracted keywords in a particular order to get some meaningful information by using Edmonds’ algorithm.


  1. 1.
    Letsios, M., Balalau, O.D., Danisch, M., Orsini, E., Sozio, M.: Finding heaviest k- subgraphs and events in social media. In: 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW), Barcelona, pp. 113–120 (2016)Google Scholar
  2. 2.
    Angel, A., Koudas, N., Sarkas, N., Srivastava, D., Svendsen, M., Tirthapura, S.: Dense subgraph maintenance under streaming edge weight updates for real-time story identification. VLDB J. 23(2), 175–199 (2014)CrossRefGoogle Scholar
  3. 3.
    Edmonds, J.: Optimum branchings. J. Res. Nat. Bur. Stand. 71B, 233–240 (1967)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Ohsawa, Y., Benson, N.E., Yachida, M.: KeyGraph: automatic indexing by co-occurrence graph based on building construction metaphor. In: Proceedings of the Advances in Digital Libraries Conference, ADL ’98, p. 12, Washington, DC, USA (1998)Google Scholar
  5. 5.
    Palshikar, G.K.: Keyword extraction from a single document using centrality measures. Pattern Recogn. Mach. Intell. LNCS 4815, 503–510 (2007)CrossRefGoogle Scholar
  6. 6.
    Tsatsaronis, G., Varlamis, I., Nørvag, K.: SemanticRank: ranking keywords and sentences using semantic graphs. In: Proceedings of the 23rd International Conference on Computational Linguistics, pp. 1074–1082, Beijing, China (2010)Google Scholar
  7. 7.
    Abilhoa, W.D., de Castro, L.N.: A keyword extraction method from twitter messages represented as graphs. Appl. Math. Comput. 240, 308–325 (2014)Google Scholar
  8. 8.
    Litvak, M., Last, M., Aizenman, H., Gobits, I., Kandel, A.: DegExt—a language-independent graph-based keyphrase extractor. In: Advances in Intelligent Web Mastering—3, vol. 86, pp. 121–130. AISC (2011)Google Scholar
  9. 9.
    Turney, P.D.: Learning to extract keyphrases from text. Technical Report ERB-1057, National Research Council of Canada, Institute for Information Technology, 1999Google Scholar
  10. 10.
    Mihalcea, R., Tarau, P.: TextRank: bringing order into texts. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2004), pp. 104–411, Barcelona, Spain, July 2004Google Scholar
  11. 11.
    Zhou, Z., Zou, X., Lv, X., Hu, J.: Research on weighted complex network based keywords extraction. Chin. Lex. Semant. LNCS 8229, 442–452 (2013)CrossRefGoogle Scholar
  12. 12.
    Lahiri, S., Choudhury, S.R., Caragea, C.: Keyword and keyphrase extraction using centrality measures on collocation networks, Cornell University Library (2014). arXiv:1401.6571
  13. 13.
    Xu, S., Guo, J., Chen, X.: Extracting topic keywords from Sina Weibo text sets. In: 2016 International Conference on Audio, Language and Image Processing (ICALIP), Shanghai, pp. 668–673 (2016)Google Scholar
  14. 14.
    Suzek, Tugba: Using latent semantic analysis for automated keyword extraction from large document corpora. Turkish J. Electr. Eng. Comput. Sci. 25, 1784–1794 (2017). Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Computer Science and Engineering, University Institute of Engineering and TechnologyPanjab UniversityChandigarhIndia

Personalised recommendations