Real-Time Relevance Matching of News and Tweets

  • Sei Onishi
  • Yuto Yamaguchi
  • Hiroyuki Kitagawa
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9415)


Given a news article, how many tweets are relevant to it in Twitter? Can we continuously collect only such tweets in real-time? In this paper, we propose a method for matching news articles and tweets in real-time. By collecting tweets relevant to news articles, we can get reactions to news articles such as sentiments and opinions from Twitter users. Our contributions are two-fold: (a) flexibility: our method collects the appropriate number of tweets for various kinds of news articles, each of which has the different number of tweets that mention it. (b) efficiency: our method can reduce the update time of an inverted index which is used for efficient matching of news articles and tweets. Also, we experimentally demonstrate the effectiveness of our method on streams of news articles and tweets from Yahoo!News and Twitter, respectively. We use the area under the ROC curve (AUC) to compare the accuracy of our method and that of baselines. The comparison shows that the AUC of our method is higher than that of the baselines by up to 22.7%. Furthermore, our method can update its index about 10 times faster compared to the existing technique.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Agarwal, A., Xie, B., Vovsha, I., Rambow, O., Passonneau, R.: Sentiment analysis of twitter data. In: LSM, pp. 30–38 (2011)Google Scholar
  2. 2.
    Amati, G., Bianchi, M., Marcone, G.: Sentiment estimation on twitter. In: IIR, pp. 39–50 (2014)Google Scholar
  3. 3.
    Canneyt, S.V., Feys, M., Schockaert, S., Demeester, T., Develder, C., Dhoedt, B.: Detecting newsworthy topics in twitter. In: SNOW-DC@WWW, pp. 25–32 (2014)Google Scholar
  4. 4.
    Chakrabarti, D., Punera, K.: Event summarization using tweets. In: ICWSM (2011)Google Scholar
  5. 5.
    Fawcett, T.: An introduction to ROC analysis. Pattern Recognition Letters 27(8), 861–874 (2006)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Hu, M., Liu, S., Wei, F., Wu, Y., Stasko, J.T., Ma, K.L.: Breaking news on twitter. In: CHI, pp. 2751–2754 (2012)Google Scholar
  7. 7.
    Kwak, H., Lee, C., Park, H., Moon, S.B.: What is twitter, a social network or a news media? In: WWW, pp. 591–600 (2010)Google Scholar
  8. 8.
    Luo, Z., Osborne, M., Wang, T.: Opinion retrieval in twitter. In: ICWSM (2012)Google Scholar
  9. 9.
    Nichols, J., Mahmud, J., Drews, C.: Summarizing sporting events using twitter. In: IUI, pp. 189–198 (2012)Google Scholar
  10. 10.
    Osborne, M., Dredze, M.: Facebook, twitter and google plus for breaking news: is there a winner? In: ICWSM (2014)Google Scholar
  11. 11.
    Pak, A., Paroubek, P.: Twitter as a corpus for sentiment analysis and opinion mining. In: LREC (2010)Google Scholar
  12. 12.
    Petrovic, S., Osborne, M., McCreadie, R., Macdonald, C., Ounis, I., Shrimpton, L.: Can twitter replace newswire for breaking news? In: ICWSM (2013)Google Scholar
  13. 13.
    Sharifi, B., Hutton, M.A., Kalita, J.K.: Experiments in microblog summarization. In: SocialCom/PASSAT, pp. 49–56 (2010)Google Scholar
  14. 14.
    Shi, B., Ifrim, G., Hurley, N.: Be in the know: Connecting news articles to relevant twitter conversations. CoRR, Vol. abs/1405.3117 (2014)Google Scholar
  15. 15.
    Shraer, A., Gurevich, M., Fontoura, M., Josifovski, V.: Top-k publish-subscribe for social annotation of news. PVLDB 6(6), 385–396 (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Graduate School of Systems and Information EngineeringUniversity of TsukubaTsukubaJapan
  2. 2.Center for Computational SciencesUniversity of TsukubaTsukubaJapan
  3. 3.Faculty of Engineering Information and SystemsUniversity of TsukubaTsukubaJapan

Personalised recommendations