Causal relation of queries from temporal logs

ABSTRACT

In this paper, we study a new problem of mining causal relation of queries in search engine query logs. Causal relation between two queries means event on one query is the causation of some event on the other. We first detect events in query logs by efficient statistical frequency threshold. Then the causal relation of queries is mined by the geometric features of the events. Finally the Granger Causality Test (GCT) is utilized to further re-rank the causal relation of queries according to their GCT coefficients. In addition, we develop a 2-dimensional visualization tool to display the detected relationship of events in a more intuitive way. The experimental results on the MSN search engine query logs demonstrate that our approach can accurately detect the events in temporal query logs and the causal relation of queries is detected effectively.

REFERENCES

• 1: C. W. J. Granger, "Investigating Causal Relations by Econometric Models and Cross-spectral Methods", Econometrica, vol. 37, pp. 424--438, 1969
• 2: C. A. Sims, "Money, Income, and Causality", the American Economic Review, vol. 62, pp. 540--552, 1972.

INDEX TERMS

Primary Classification:
  G. Mathematics of Computing
  G.3 PROBABILITY AND STATISTICS
      Subjects: Time series analysis

General Terms:
Algorithms, Measurement

Keywords:
causal relation, search engine query log, time series