Abstract
Segmenting user sessions in search engine query logs is important to perceive information needs and assess how they are satisfied, to enhance the quality of search engine rankings, and to better direct content to certain users. Most previous methods use human judgments to inform supervised learning algorithms, and/or use global thresholds on temporal proximity and on simple lexical similarity metrics. This paper proposes a novel unsupervised method that improves the current state-of-art, leveraging additional heuristics and similarity metrics derived from word embeddings. We specifically extend a previous approach based on combining temporal and lexical similarity measurements, integrating semantic similarity components that use pre-trained FastText embeddings. The paper reports on experiments with an AOL query dataset used in previous studies, containing a total of 10,235 queries, with 4,253 sessions, 2.4 queries per session, and 215 unique users. The results attest to the effectiveness of the proposed method, which outperforms a large set of baselines, also corresponding to unsupervised techniques.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Feild, H., Allan, J., Jones, R.: Predicting searcher frustration. In: Proceedings of the ACM Conference on Research and Development in Information Retrieval (2010)
Hassan, A., Shi, X., Craswell, N., Ramsey, B.: Beyond clicks: query reformulation as a predictor of search satisfaction. In: Proceedings of the ACM Conference on Information and Knowledge Management (2013)
Jiang, J., Awadallah, A.H., Shi, X., White, R.W.: Understanding and predicting graded search satisfaction. In: Proceedings of the ACM Conference on Web Search and Data Mining (2015)
Kim, Y., Hassan, A., White, R.W., Zitouni, I.: Modeling dwell time to predict click-level satisfaction. In: Proceedings of the ACM Conference on Web Search and Data Mining (2014)
Mehrotra, R., et al.: Deep sequential models for task satisfaction prediction. In: Proceedings of the ACM on Conference on Information and Knowledge Management (2017)
Mayr, P., Kacem, A.: A complete year of user retrieval sessions in a social sciences academic search engine. In: Kamps, J., Tsakonas, G., Manolopoulos, Y., Iliadis, L., Karydis, I. (eds.) TPDL 2017. LNCS, vol. 10450, pp. 560–565. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-67008-9_46
Hagen, M., Stein, B., Rüb, T.: Query session detection as a cascade. In: Proceedings of the ACM Conference on Information and Knowledge Management (2011)
Jones, R., Klinkner, K.L.: Beyond the session timeout: automatic hierarchical segmentation of search topics in query logs. In: Proceedings of the ACM Conference on Information and Knowledge Management (2008)
Mehrzadi, D., Feitelson, D.G.: On extracting session data from activity logs. In: Proceedings of the Annual International Systems and Storage Conference (2012)
Gayo-Avello, D.: A survey on session detection methods in query logs and a proposal for future evaluation. Inf. Sci. 179(12), 1822–1843 (2009)
Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135–146 (2017)
Pass, G., Chowdhury, A., Torgeson, C.: A picture of search. In: Proceedings of the International Conference on Scalable Information Systems (2006)
Downey, D., Dumais, S.T., Horvitz, E.: Models of searching and browsing: languages, studies, and application. In: Proceedings of the International Joint Conference on Artificial Intelligence (2007)
He, D., Göker, A.: Detecting session boundaries from web user logs. In: Proceedings of the BCS-IRSG Annual Colloquium on Information Retrieval Research (2000)
Radlinski, F., Joachims, T.: Query chains: learning to rank from implicit feedback. In: Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (2005)
Catledge, L.D., Pitkow, J.E.: Characterizing browsing strategies in the world wide web. Comput. Network ISDN Syst. 27(6), 1065–1073 (1995)
Jansen Bernard, J., Spink, A., Blakely, C., Koshman, S.: Defining a session on web search engines. J. Am. Soc. Inform. Sci. Technol. 58(6), 862–871 (2007)
Lucchese, C., Orlando, S., Perego, R., Silvestri, F., Tolomei, G.: Identifying task-based sessions in search engine query logs. In: Proceedings of the ACM Conference on Web Search and Data Mining (2011)
Jaccard, P.: The distribution of the flora in the alpine zone. New Phytol. 11(2), 37–50 (1912)
Gabrilovich, E., Markovitch, S.: Computing semantic relatedness using Wikipedia-based explicit semantic analysis. In: Proceedings of the International Joint Conference on Artificial Intelligence (2007)
Ozmutlu, S., Cenk Ozmutlu, H., Spink, A.: Automatic new topic identification in search engine transaction logs? Using multiple linear regression. In: Proceedings of the Hawaii International Conference on System Sciences (2008)
Kusner, M., Sun, Y., Kolkin, N., Weinberger, K.: From word embeddings to document distances. In: Proceedings of the International Conference on Machine Learning (2015)
Santos, R., Murrieta-Flores, P.: Learning to combine multiple string similarity metrics for effective toponym matching. Int. J. Digit. Earth 11(9), 913–938 (2018)
Santos, R., Murrieta-Flores, P., Calado, P., Martins, B.: Toponym matching through deep neural networks. Int. J. Geographical Inf. Sci. 32(2), 324–348 (2018)
Gan, Z., et al.: Character-level deep conflation for business data analytics. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (2017)
Acknowledgements
This work was supported by Fundação para a Ciência e Tecnologia (FCT), through project GoLocal (CMUP-ERI/TIC/0046/2014) and also through the INESC-ID multi-annual funding from the PIDDAC program (UID/CEC/50021/2019).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Gomes, P., Martins, B., Cruz, L. (2019). Segmenting User Sessions in Search Engine Query Logs Leveraging Word Embeddings. In: Doucet, A., Isaac, A., Golub, K., Aalberg, T., Jatowt, A. (eds) Digital Libraries for Open Knowledge. TPDL 2019. Lecture Notes in Computer Science(), vol 11799. Springer, Cham. https://doi.org/10.1007/978-3-030-30760-8_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-30760-8_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30759-2
Online ISBN: 978-3-030-30760-8
eBook Packages: Computer ScienceComputer Science (R0)