Measurement of incompatible probability in information retrieval: A case study with user clicks

Abstract

The incompatible probability represents an important non-classical phenomenon, and it describes conflicting observed marginal probabilities, which cannot be satisfied with a joint probability. First, the incompatibility of random variables was defined and discussed via the non-positive semi-definiteness of their covariance matrixes. Then, a method was proposed to verify the existence of incompatible probability for variables. A hypothesis testing was also applied to reexamine the likelihood of the observed marginal probabilities being integrated into a joint probability space, thus showing the statistical significance of incompatible probability cases. A case study with user click-through data provided the initial evidence of the incompatible probability in information retrieval (IR), particularly in user interaction. The experiments indicate that both incompatible and compatible cases can be found in IR data, and informational queries are more likely to be compatible than navigational queries. The results inspire new theoretical perspectives of modeling the complex interactions and phenomena in IR.

Keywords

incompatible probability / semi-definiteness / hypothesis testing / information retrieval / user clicks

References

[1] Singhal Amit.. Modern information retrieval: A brief overview [J]. Bulletin of the IEEE Computer Society Technical Committee on Data Engineering, 2001, 24(4): 35-43.

[2] Maron M. E., Kuhns J. L.. On relevance, probabilistic indexing, and information retrieval [J]. JACM, 1960, 7(3): 216-244.

[3] Sparck Jones K., Walker S., Robertson S. E.. A probabilistic model of information retrieval: Development and comparative experiments. Parts 1 and 2 [J]. IP&M, 2000, 36(6): 779-808.

[4] Ross S. M.. A First Course in Probability [M]. 2006, USA: Pearson Prentice Hall.

[5] Grinstead Charles M., Laurie Snell J.. Introduction to Probability [M]. 1997, USA: American Mathematical Society.

[6] Rice J.. Mathematical Statistics and Data Analysis [M]. 2006, USA: Duxbury Press.

[7] Ripley B. D.. Pattern Recognition and Neural Networks [M]. 1996, UK: Cambridge University Press.

[8] Gudder S. P.. Quantum Probability [M]. 1988, USA: Academic Press.

[9] Khrennivov A.. Classical and quantum mechanics on information spaces with applications to cognitive, psychological, social, and anomalous phenomena [J]. Foundations of Physics, 1999, 29(7): 1065 1098

[10] Albert E., Podolsky B., Rosen N.. Can quantummechanical description of physical reality be considered complete? [J]. Physical Review, 1935, 47(10): 777-780.

[11] Bell J. S.. On the Einstein-Podolsky-Rosen Paradox [J]. Physics, 1964, 1, 195-200.

[12] Khrennikov A.. Can quantum information be processed by macroscopic systems ? [J]. Quantum Information Processing, 2007, 6(6): 401 429

[13] Khrennikov A. Y.. Contextual Approach to Quantum Formalism (Fundamental Theories of Physics)[M]. 2009, Heidelberg-Berlin-New York: Springer.

[14] Tsallis C.. Possible generalization of Boltzmann-Gibbs statistics [J]. Journal of Statistical Physics, 1988, 52(1/2): 479 487