ABSTRACT
Search engine switching describes the voluntarily transition from one Web search engine to another. In this paper we present a study of search engine switching behavior that combines large-scale log-based analysis and survey data. We characterize aspects of switching behavior, and develop and evaluate predictive models of switching behavior using features of the active query, the current session, and user search history. Our findings provide insight into the decision-making processes of search engine users and demonstrate the relationship between switching and factors such as dissatisfaction with the quality of the results, the desire for broader topic coverage or verification of encountered information, and user preferences. The findings also reveal sufficient consistency in users' search behavior prior to engine switching to afford accurate prediction of switching events. Predictive models may be useful for search engines who may want to modify the search experience if they can accurately anticipate a switch.
- Bartell, B.T., Cottrell, G.W., and Belew, R.K. (1994). Automatic combination of multiple ranked retrieval systems. Proc. SIGIR, 173--181. Google ScholarDigital Library
- Belkin, N., Cool, C., Croft, W., and Callan, J. (1993). The effect of multiple query representations on information retrieval system performance. Proc. SIGIR, 339--346. Google ScholarDigital Library
- Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123--140. Google ScholarCross Ref
- Carmel, D., Yom-Tov, E., Darlow, A., and Pelleg, D. (2006). What makes a query difficult? Proc. SIGIR, 390--397. Google ScholarDigital Library
- Cover, T.M. and Thomas, J.A. (1991). Elements of Information Theory. New York: John Wiley and Sons. Google ScholarDigital Library
- Cronen-Townsend, S., Zhou, Y. and Croft, W. B. (2002). Predicting query performance. Proc. SIGIR, 299--306. Google ScholarDigital Library
- Downey, D., Dumais, S.T., and Horvitz, E. (2007). Models of searching and browsing: Languages, studies and application. Proc. IJCAI, 2740--2747. Google ScholarDigital Library
- Downey, D., Dumais, S.T., Liebling, D., and Horvitz, E. (2008). Understanding the relationship between searchers' queries and information goals. Proc. CIKM, 449--458. Google ScholarDigital Library
- Fox, S., Karnawat, K., Mydland, M., Dumais, S.T., and White, T. (2005). Evaluating implicit measures to improve the search experience. ACM TOIS, 23(2), 147--168. Google ScholarDigital Library
- Grimes, C., Tang, D., and Russell, D. (2007). Query logs are not enough. Proc. Workshop on Query Log Analysis.Google Scholar
- Heath, A.P. and White, R.W. (2008). Defection detection: Predicting search engine switching. Proc. WWW, 1173--1174. Google ScholarDigital Library
- Hosmer, D.W. and Lemeshow, S. (2004). Applied Logistic Regression. New York: Wiley.Google Scholar
- Huntington P, Nicholas D, Jamali, H.R, and Watkinson A. (2006). Obtaining subject data from log files using deep log analysis: case study OhioLINK. J. Inf. Sci., 32(4): 299--308.Google ScholarCross Ref
- Juan, Y.F. and Chang, C.C. (2005). An analysis of search engine switching behavior using click streams. Proc. WWW, 1050--1051. Google ScholarDigital Library
- Laxman, S., Tankasali, V., and White, R.W. (2008). Stream prediction using a generative model based on frequent epi--sodes in event sequences. Proc. SIGKDD, 453--461. Google ScholarDigital Library
- Leskovec, J., Dumais, S., and Horvitz, E. (2007). Web projections: Learning from contextual subgraphs of the web. Proc. WWW, 471--480. Google ScholarDigital Library
- Ling, C. and Li, C. (1998). Data mining for direct marketing: Problems and solutions. Proc. SIGKDD, 73--79.Google Scholar
- Mukhopadhyay, T., Rajan, U., and Telang, R. (2004). Competition between internet search engines. Proc. HICSS. Google ScholarDigital Library
- Pew Internet and American Life Project. (2005). Search Engine Users. Accessed December 15, 2008.Google Scholar
- Teevan, J., Dumais, S., and Liebling, D. (2008). To personalize or not to personalize: Modeling queries with variation in user intent. Proc. SIGIR, 620--627. Google ScholarDigital Library
- Telang, R., Mukhopadhyay, T., and Wilcox, R. (1999). An empirical analysis of the antecedents of internet search engine choice. Proc. Wkshp on Info. Systems and Economics.Google Scholar
- White, R.W., Richardson, M., Bilenko, M., and Heath, A.P. (2008). Enhancing web search by promoting multiple search engine use. Proc. SIGIR, 43--50. Google ScholarDigital Library
- Zhou, Y. and Croft, W.B. (2007). Query performance prediction in web search environments. Proc. SIGIR, 543--550. Google ScholarDigital Library
Index Terms
- Characterizing and predicting search engine switching behavior
Recommendations
Search Engine Evaluation based on Search Engine Switching Prediction
SIGIR '15: Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information RetrievalIn this paper we present a novel application of the search engine switching prediction model for online evaluation. We propose a new metric pSwitch for A/B-testing, which allows us to evaluate the quality of search engines in different aspects such as ...
Search engine switching detection based on user personal preferences and behavior patterns
SIGIR '13: Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrievalSometimes, during a search task users may switch from one search engine to another for several reasons, e.g., dissatisfaction with the current search results or desire for broader topic coverage. Detecting the fact of switching is difficult but ...
Enhancing web search by promoting multiple search engine use
SIGIR '08: Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrievalAny given Web search engine may provide higher quality results than others for certain queries. Therefore, it is in users' best interest to utilize multiple search engines. In this paper, we propose and evaluate a framework that maximizes users' search ...
Comments