Keyword Extraction from Tweets Using Weighted Graph

  • Saroj Kumar BiswasEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 768)


One of the most important tasks of sentiment analysis of twitter contents is automatic keyword extraction. Vector Space Model (VSM) is one of the most well-known keyword extraction techniques; however it has some limitation such as scalability and sparsity. Graph-based keyword extraction approach is used to overcome those limitations. This paper proposes an unsupervised graph-based keyword extraction method, called Keyword from Weighted Graph (KWG) which uses Node Edge (NE) rank centrality measure to calculate the importance of nodes closeness centrality measure to break the ties among the nodes. The proposed method is validated with two datasets: Uri Attack, and American Election. From the experimental results it is observed that the performances of the proposed method outperform the eigen vector centrality and the textrank centrality measures. The performances are shown in terms of precision, recall, and F-measure.


Extraction Sentiment analysis Graph-based model Centrality measure Vector space model 


  1. 1.
    Beliga, S., Mestrovic, A., Martincic-Ipsic, S.: An overview of graph-based keyword extraction methods and approaches. JIOS 39(1), 1–20 (2015)Google Scholar
  2. 2.
    Savita, D.B., Gore, D.: Sentiment Analysis on Twitter Data Using Support Vector Machine. Int. J. Comput. Sci. Trends Technol. (IJCST) 4(3), 365–370 (2016)Google Scholar
  3. 3.
    Hemalatha, I., Saradhi Varma, G.P., Govardhan, A.: Sentiment Analysis Tool using Machine Learning Algorithms. Int. J. Emerg. Trends Technol. Comput. Sci. (IJETTCS) 2(2), 105–109 (2013)Google Scholar
  4. 4.
    Salton, G., Yang, C.S., Yu, C.T.: A theory of term importance in automatic text analysis. J. Am. Soc. Inf. Sci. Technol. 26(1), 33–44 (1975)CrossRefGoogle Scholar
  5. 5.
    Russell, M.A.: Mining the social web: data mining Facebook, Twitter, LinkedIn, Google+, GitHub, and More. O’Reilly Media Inc. (2013)Google Scholar
  6. 6.
    Ediger, D., Jiang, K., Riedy, J., Bader, D.A., Corley, C., Farber, R., Reynolds, W.N.: Massive social network analysis: mining twitter for social good. In: 2010 39th international conference on parallel processing (ICPP), pp. 583–593, IEEE (2010)Google Scholar
  7. 7.
    Hulth, A.: Improved automatic keyword extraction given more linguistic knowledge. In Proceeding EMNLP ‘03 proceedings of the 2003 conference on Empirical methods in natural language processing, pp. 216–223 (2003)Google Scholar
  8. 8.
    Nguyen, T.D., Kan, M.Y.: Keyphrase Extraction in scientific publications. In: Proceeding ICADL’07 proceedings of the 10th international conference on Asian digital libraries: looking back 10 years and forging new frontiers, pp. 317–326 (2007)Google Scholar
  9. 9.
    Witten, I.H., Paynter, G.W., Frank, E., Gutwin, C., Nevill-Manning, C.G.: KEA: Practical automatic keyphrase extraction. In: Proceedings DL ‘99 proceedings of the fourth ACM conference on Digital libraries, pp. 254–255 (1999)Google Scholar
  10. 10.
    Zhang, K., Xu, H., Tang, J., Li, J.: Keyword extraction using support vector machine. In: Proceeding WAIM ‘06 proceedings of the 7th international conference on Advances in Web-Age information management, pp. 85–96 (2006)Google Scholar
  11. 11.
    Medelyan, O., Witten, I.H.: Thesaurus based automatic keyphrase indexing. In: Proceeding JCDL ‘06 proceedings of the 6th ACM/IEEE-CS joint conference on digital libraries, pp. 296–297 (2006)Google Scholar
  12. 12.
    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
  13. 13.
    Nagarajan, R., Nair, S.A.H., Aruna, P., Puviarasan, N.: Keyword extraction using graph based approach. Int. J. Adv. Res. Comput. Sci. Softw. Eng. 6(10), 25–29 (2016)Google Scholar
  14. 14.
    Song, H.J., Go, J., Park, S.B., Park, S.Y., Kim, K.Y.: A just-in-time keyword extraction from meeting transcripts using temporal and participant information. J. Intell. Inf. Syst. (Springer) 48(1), 117–140 (2017)CrossRefGoogle Scholar
  15. 15.
    Bellaachia, A., Al-Dhelaan, M.: NE-Rank: a novel graph-based key phrase extraction in twitter. In: Proceedings WI-IAT’12 proceedings of the 2012 IEEE/WIC/ACM international joint conferences on web intelligence and intelligent agent technology, vol. 1, pp. 372–379 (2012)Google Scholar
  16. 16.
    Mihalcea, R., Tarau, P.: TextRank: bringing order into texts. In: Lin, D. Wu, D. (eds.) Proceedings of the 2004 conference on empirical methods in natural language processing, Barcelona, pp. 404–411, Association for Computational Linguistics, Spain (2004)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringNational Institute of TechnologySilcharIndia

Personalised recommendations