A Tweet Classification Model Based on Dynamic and Static Component Topic Vectors

  • Parma Nand
  • Rivindu Perera
  • Gisela Klette
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9457)


This paper presents an unsupervised architecture for retrieving and ranking conceptually related tweets which can be used in real time. We present a model for ranking tweets with respect to topic relevance in order to improve the accuracy of information extraction.

The proposed architecture uses concept enrichment from a knowledge source in order to expand the concept beyond the search keywords. The enriched concept is used to determine similarity levels between tweets and the given concept followed by a ranking of those tweets based on different similarity values. Tweets above a certain similarity threshold are considered as useful for providing relevant information (this is not part of this paper). We obtained precision values up to 0.81 and F values up to 0.61 for a tweet corpus of 2400 Tweets on the topic related to 2014 NZ general elections.


Topic modeling Natural language processing Text mining Social media 


  1. 1.
    Luo, Z., Osborne, M., Petrovic, S., Wang, T.: Improving twitter retrieval by exploiting structural information. In: AAAI (2012)Google Scholar
  2. 2.
    Dong, A., Zhang, R., Kolari, P., Bai, J.: Time is of the essence: improving recency ranking using twitter data. In: Proceedings of the 19th International Conference on World Wide Web (2010)Google Scholar
  3. 3.
    Han, Z., Li, X., Yang, M., Qi, H., Li, S., Zhao, T.: Hit at trec 2012 microblog track. In: Proceedings of Text Retrieval Conference (2012)Google Scholar
  4. 4.
    Efron, M., Golovchinsky, G.: Estimation methods for ranking recent information. In: SIGIR Conference on Research and Development in Information Retrieval (2011)Google Scholar
  5. 5.
    Luo, Z., Osborne, M., Tang, J., Wang, T.: Who will retweet me? finding retweeters in Twitter. In: Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval (2013)Google Scholar
  6. 6.
    Luo, Z., Osborne, M., Saša, P.: Improving twitter retrieval by exploiting structural information. In: AAAI Proceeding, pp. 22–26, T.W (2012)Google Scholar
  7. 7.
    Duan, Y., Jiang, L., Qin, T., Zhou, M., Shum, H.Y.: An empirical study on learning to rank of tweets. In: Proceedings of the 23rd International Conference on Computational Linguistics, pp. 295–303 (2010)Google Scholar
  8. 8.
    Nagmoti, R., Teredesai, A., De Cock, M.: Ranking approaches for microblog search. In: 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, vol. 1, pp. 153–157. IEEE (2010)Google Scholar
  9. 9.
    Massoudi, K., Tsagkias, M., de Rijke, M., Weerkamp, W.: Incorporating query expansion and quality indicators in searching microblog posts. In: Clough, P., Foley, C., Gurrin, C., Jones, G.J.F., Kraaij, W., Lee, H., Mudoch, V. (eds.) ECIR 2011. LNCS, vol. 6611, pp. 362–367. Springer, Heidelberg (2011) CrossRefGoogle Scholar
  10. 10.
    Perera, R., Nand, P.: The role of linked data in content selection. In: Pham, D.-N., Park, S.-B. (eds.) PRICAI 2014. LNCS, vol. 8862, pp. 573–586. Springer, Heidelberg (2014) Google Scholar
  11. 11.
    Perera, R., Nand, P.: Real text-cs- corpus based domain independent content selection model. In: IEEE 26th International Conference on Tools with Artificial Intelligence (ICTAI), pp. 599–606 (2014)Google Scholar
  12. 12.
    Nand, P., Perera, R., Sreekumar, A., Lingmin, H.: A multi-strategy approach for location mining in tweets: AUT NLP group entry for ALTA-2014 shared task. In: Proceedings of the Australasian Language Technology Association Workshop 2014, pp. 163–170, Brisbane, Australia (2014)Google Scholar
  13. 13.
    Nand, P., Lal, R., Perera, R.: A HMM POS tagger for micro-blogging type texts. In: Proceedings of the 13th Pacific Rim International Conference on Artificial Intelligence (PRICAI 2014) (2014)Google Scholar
  14. 14.
    Nand, P., Perera, R.: An evaluation of POS tagging for tweets using HMM modeling. In: 38th Australasian Computer Science Conference (2015)Google Scholar
  15. 15.
    Chapman, S.: Simmetrics. Simmetrics is a similarity metric library, eg from edit distances (Levenshtein, Gotoh, Jaro etc) to other metrics,(eg Soundex, Chapman). Work provided by UK Sheffield University funded by (AKT) an IRC sponsored by EPSRC, grant number GR N 15764 (2009). URL
  16. 16.
    O’Connor, B., Krieger, M., Ahn, D.: TweetMotif: exploratory search and topic summarization for Twitter. In: ICWSM (2010)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.School of Computer and Mathematical ScienceAuckland University of TechnologyAucklandNew Zealand

Personalised recommendations