Webpage Mining for Inflation Emergency Early Warning

  • Yan Qu
  • Wei Shang
  • Shouyang Wang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7901)


Serious inflation turbulence is a signal of potential financial crisis and social economic emergencies. Macroeconomic early warning of inflation and other major economic indicators is critical to discover potential crisis in advance. Traditional early warning methods are based on official economic statistics which are usually either released at least one month later than the economic activities actually occur or lack of flexibility to cope with fast business changes. With proper extraction and aggregation, huge amount of Internet data can serve as a new complementarity source to facilitate more timely and accurate emergency early warning. This research innovatively adopts web data processing techniques and text mining methods to extract useful information from huge amount of Internet news reports. Based on the extracted information, a price sentiment index is proposed to detect turning points of inflation efficiently. Empirical evaluation proved that the price sentiment index is efficient in inflation emergency early warning.


sentiment analysis web mining macroeconomic early warning Consumer Price Index 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Devitt, A., Ahmad, K.: Sentiment Polarity Identification in Financial News: A Cohesion-based Approach. In: 45th Annual Meeting of the Association of Computational Linguistics, pp. 984–991 (2007)Google Scholar
  2. 2.
    Davis, A.K., Piger, J.M., Sedor, L.M.: Beyond the numbers: An analysis of optimistic and pessimistic language in earnings press releases. Technical report, Federal Reserve Bank of St Louis (2006)Google Scholar
  3. 3.
    Humphrey, B.D.: Forecasting Existing Home Sales using Google Search Engine Queries,
  4. 4.
    Pang, B., Lee, L., Vaithyanathan, S.: Thumbs up? Sentiment Classification Using Machine Learning Techniques. In: The Conference on Empirical Methods in Natural Language Processing (EMNLP 2002), Philadelphia, Pennsylvania, pp. 79–86 (2002)Google Scholar
  5. 5.
    Wuthrich, B., Permunetilleke, D., Leung, S., Cho, V., Zhang, J., Lam, W.: Daily Prediction of Major Stock Indices from textual WWW Data. In: 4th International Conference on Knowledge Discovery and Data Mining, pp. 364–368 (1998)Google Scholar
  6. 6.
    Oh, C., Sheng, O.R.L.: Investigating Predictive Power of Stock Micro Blog Sentiment in Forecasting Future Stock Price Directional Movement. In: ICIS (2011)Google Scholar
  7. 7.
    Findley, D.F., Monsell, B.C.: New capabilities and Methods of the X-12-ARIMA Seasonal Adjustment Program. Journal of Business and Economic Statistics (1998)Google Scholar
  8. 8.
    Kaufer, D., Mellon, C.: Flaming: A White Paper,
  9. 9.
    Riloff, E., Wiebe, J.: Learning Extraction Patterns for Subjective Expressions. In: The Conference on Empirical Methods in Natural Language Processing (EMNLP 2003), Sapporo, Japan, pp. 105–112 (2003)Google Scholar
  10. 10.
    Bry, G., Boschan, C.: Cyclical Analysis of Time Series: Selected Procedures and Computer Programs. Columbia University Press for the NBER (1981)Google Scholar
  11. 11.
    Zhang, H.P., Yu, H.K., Xiong, D.Y., Liu, Q.: HHMM-based Chinese lexical analyzer ICTCLAS. In: SIGHAN Workshop (2003)Google Scholar
  12. 12.
    Wiebe, J., Wilson, T., Bell, M.: Identifying Collocations for Recognizing Opinions. In: The ACL 2001 Workshop on Collocation: Computational Extraction, Analysis, and Exploitation, Toulouse, France, pp.24–31 (2001)Google Scholar
  13. 13.
    Doms, M., Morin, N.: Consumer Sentiment, the Economy, and the News Media. FRB of San Francisco Working Paper, No. 2004-09 (2004)Google Scholar
  14. 14.
    Askitas, N., Zimmermann, K.: Google Econometrics and Unemployment Forecasting. Technical report, SSRN 899 (2009)Google Scholar
  15. 15.
    Turney, P.D.: Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. In: 40th Annual Meeting on Association for Computational Linguistics (2002)Google Scholar
  16. 16.
    Feldman, R., Sanger, J.: The Text Mining Handbook: Advanced Approaches in Analyzing Unstructured Data. Cambridge University Press (2006)Google Scholar
  17. 17.
    Engle, R.F., Granger, C.W.J.: Co-integration and Error Correction: Representation, Estimation, and Testing. Journal of the Econometric Society 55, 251–276 (1987)MathSciNetzbMATHCrossRefGoogle Scholar
  18. 18.
    Schumaker, R.P., Chen, H.: Textual Analysis of Stock Market Prediction Using Breaking Financial News: The AZFinText System. ACM Transactions on Information Systems 27(2) (2009)Google Scholar
  19. 19.
    Das, S.R., Chen, M.Y.: Yahoo! for Amazon: Sentiment extraction from small talk on the web. Management Science 53(9), 1375–1388 (2007)CrossRefGoogle Scholar
  20. 20.
    Sabherwal, S., Sarkar, S., Zhang, Y.: Online talk: does it matter? Managerial Finance 34(6), 423–436 (2008)CrossRefGoogle Scholar
  21. 21.
    Vosen, S., Schmidt, T.: Forecasting private consumption: survey-based indicators vs. Google trends. Journal of Forecasting 30, 565–578 (2011)MathSciNetzbMATHCrossRefGoogle Scholar
  22. 22.
    Schmidt, T., Vosen, S.: A monthly consumption indicator for Germany based on internet search query data. Ruhr Economic Papers No. 208 (2010)Google Scholar
  23. 23.
    Antweiler, W., Frank, M.Z.: Is all that talk just noise? The information content of internet stock message boards. Journal of Finance 59(3), 1259–1295 (2004)CrossRefGoogle Scholar
  24. 24.
    Dang, Y., Zhang, Y., Chen, H.: A lexicon-enhanced method for sentiment classification: An experiment on online product reviews. In: IEEE Intelligent Systems, pp. 46–53 (July-August 2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Yan Qu
    • 1
  • Wei Shang
    • 1
  • Shouyang Wang
    • 1
  1. 1.Academy of Mathematics and Systems ScienceChinese Academy of ScienceBeijingChina

Personalised recommendations