ABSTRACT
The importance of e-commerce platforms has driven forward a growing body of research work on e-commerce search. We present the first large-scale and in-depth study of query reformulations performed by users of e-commerce search; the study is based on the query logs of eBay's search engine. We analyze various factors including the distribution of different types of reformulations, changes of search result pages retrieved for the reformulations, and clicks and purchases performed upon the retrieved results. We then turn to address a novel challenge in the e-commerce search realm: predicting whether a user will reformulate her query before presenting her the search results. Using a suite of prediction features, most of which are novel to this study, we attain high prediction quality. Some of the features operate prior to retrieval time, whereas others rely on the retrieved results. While the latter are substantially more effective than the former, we show that the integration of these two types of features is of merit. We also show that high prediction quality can be obtained without considering information from the past about the user or the query she posted. Nevertheless, using these types of information can further improve prediction quality.
Supplemental Material
- Martin Arlitt. 2000. Characterizing web user sessions. SIGMETRICS Perform. Eval. Rev., Vol. 28, 2 (2000), 50--63.Google ScholarDigital Library
- Ahmed Hassan Awadallah, Ranjitha Gurunath Kulkarni, Umut Ozertem, and Rosie Jones. 2015. Characterizing and predicting voice query reformulation. In Proc. of CIKM. 543--552.Google Scholar
- Ahmed Hassan Awadallah, Xiaolin Shi, Nick Craswell, and Bill Ramsey. 2013. Beyond clicks: query reformulation as a predictor of search satisfaction. In Proc. of CIKM. 2019--2028.Google Scholar
- Ahmed Hassan Awadallah, Ryen W. White, Susan T. Dumais, and Yi-Min Wang. 2014. Struggling or exploring?: disambiguating long search sessions. In Proc. of WSDM. 53--62.Google Scholar
- Yoshua Bengio, Ian Goodfellow, and Aaron Courville. 2017. Deep learning.Google Scholar
- Paolo Boldi, Francesco Bonchi, Carlos Castillo, Debora Donato, Aristides Gionis, and Sebastiano Vigna. 2008. The query-flow graph: model and applications. In Proc. of CIKM. 609--618.Google ScholarDigital Library
- Leo Breiman. 2001. Random forests. Machine learning, Vol. 45, 1 (2001), 5--32.Google ScholarDigital Library
- Eliot Brenner, Jun Zhao, Aliasgar Kutiyanawala, and Zheng Yan. 2018. End-to-end neural ranking for eCommerce product search: An application of task models and textual embeddings. In The SIGIR 2018 Workshop On eCommerce.Google Scholar
- David Carmel and Elad Yom-Tov. 2010. Estimating the query difficulty for information retrieval. Morgan & Claypool Publishers.Google Scholar
- Chih-Chung Chang and Chih-Jen Lin. 2011. LIBSVM: A library for support vector machines. ACM TIST, Vol. 2, 3 (2011), 27.Google Scholar
- Tianqi Chen and Carlos Guestrin. 2016. Xgboost: A scalable tree boosting system. In Proc. of KDD. 785--794.Google ScholarDigital Library
- Corinna Cortes and Vladimir Vapnik. 1995. Support-vector networks. Machine Learning, Vol. 20, 3 (1995), 273--297.Google ScholarCross Ref
- Steve Cronen-Townsend, Yun Zhou, and W. Bruce Croft. 2002. Predicting query performance. In Proc. of SIGIR. 299--306.Google Scholar
- Ronan Cummins, Joemon M. Jose, and Colm O'Riordan. 2011. Improved query performance prediction using standard deviation. In Proc. of SIGIR. 1089--1090.Google ScholarDigital Library
- Rotem Dror, Gili Baumer, Segev Shlomov, and Roi Reichart. 2018. The hitchhiker's guide to testing statistical significance in natural language processing. In Proc. of ACL. 1383--1392.Google ScholarCross Ref
- Joseph L Fleiss. 1971. Measuring nominal scale agreement among many raters. Psychological bulletin, Vol. 76, 5 (1971), 378--382.Google Scholar
- Jerome H Friedman. 2001. Greedy function approximation: A gradient boosting machine. Annals of statistics (2001), 1189--1232.Google Scholar
- Katharina C Furtner, Thomas Mandl, and Christa Womser-Hacker. 2015. Effects of Auto-Suggest on the Usability of Search in eCommerce.. In ISI. 178--190.Google Scholar
- Sreenivas Gollapudi, Samuel Ieong, and Anitha Kannan. 2012. Structured query reformulations in commerce search. In Proc. of CIKM. 1890--1894.Google ScholarDigital Library
- Ido Guy and Kira Radinsky. 2017. Structuring the unstructured: From startup to making sense of eBay's huge eCommerce inventory. In Proc. of SIGIR. 1351.Google ScholarDigital Library
- Christophe Van Gysel, Maarten de Rijke, and Evangelos Kanoulas. 2018. Mix'n match: Integrating text matching and product substitutability within product search. In Proc. of CIKM. 1373--1382.Google Scholar
- Claudia Hauff, Leif Azzopardi, and Djoerd Hiemstra. 2009. The combination and evaluation of query performance prediction methods. In Proc. of ECIR. 301--312.Google ScholarDigital Library
- Yujing Hu, Qing Da, Anxiang Zeng, Yang Yu, and Yinghui Xu. 2018. Reinforcement learning to rank in e-Commerce search engine: Formalization, analysis, and application. In Proc. of SIGKDD. 368--377.Google ScholarDigital Library
- Jeff Huang and Efthimis N. Efthimiadis. 2009. Analyzing and evaluating query reformulation strategies in web search logs. In Proc. of CIKM. 77--86.Google Scholar
- Bernard J. Jansen, Danielle L. Booth, and Amanda Spink. 2009. Patterns of query reformulation during Web searching. JASIST, Vol. 60, 7 (2009), 1358--1371.Google ScholarDigital Library
- Jiepu Jiang, Ahmed Hassan Awadallah, Xiaolin Shi, and Ryen W. White. 2015. Understanding and predicting graded search satisfaction. In Proc. of WSDM. 57--66.Google Scholar
- Jyun-Yu Jiang, Yen-Yu Ke, Pao-Yu Chien, and Pu-Jen Cheng. 2014. Learning user reformulation behavior for query auto-completion. In Proc. of SIGIR. 445--454.Google ScholarDigital Library
- Rosie Jones and Kristina Lisa Klinkner. 2008. Beyond the session timeout: automatic hierarchical segmentation of search topics in query logs. In Proc. of CIKM. 699--708.Google ScholarDigital Library
- Li-Jen Kao and Yo-Ping Huang. 2017. Predicting purchase intention according to fan page users' sentiment. In Proc. of SMC. 831--835.Google ScholarDigital Library
- Elad Kravi, Ido Guy, Avihai Mejer, David Carmel, Yoelle Maarek, Dan Pelleg, and Gilad Tsur. 2016. One Query, Many Clicks: Analysis of Queries with Multiple Clicks by the Same User. In Proc. of CIKM. 1423--1432.Google ScholarDigital Library
- Rohan Kumar, Mohit Kumar, Neil Shah, and Christos Faloutsos. 2018. Did we get it right? predicting query performance in e-Commerce search. In The SIGIR 2018 Workshop On eCommerce.Google Scholar
- Or Levi, Ido Guy, Fiana Raiber, and Oren Kurland. 2018. Selective Cluster Presentation on the Search Results Page. ACM TOIS, Vol. 36, 3, Article 28 (2018), 42 pages.Google ScholarDigital Library
- Saurav Manchanda, Mohit Sharma, and George Karypis. 2019. Intent term selection and refinement in e-commerce queries. CoRR, Vol. abs/1908.08564 (2019).Google Scholar
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Proc. of NIPS. 3111--3119.Google ScholarDigital Library
- Eric W Noreen. 1989. Computer-intensive methods for testing hypotheses. Wiley New York.Google Scholar
- Daan Odijk, Ryen W. White, Ahmed Hassan Awadallah, and Susan T. Dumais. 2015. Struggling and success in web search. In Proc. of CIKM. 1551--1560.Google Scholar
- Jay M. Ponte and W. Bruce Croft. 1998. A language modeling approach to information retrieval. In Proc. of SIGIR. 275--281.Google Scholar
- Fiana Raiber and Oren Kurland. 2014. Query-performance prediction: setting the expectations straight. In Proc. of SIGIR. 13--22.Google ScholarDigital Library
- Hadas Raviv, Oren Kurland, and David Carmel. 2014. Query performance prediction for entity retrieval. In Proc. of SIGIR. 1099--1102.Google ScholarDigital Library
- Stephen E. Robertson, Steve Walker, Susan Jones, Micheline Hancock-Beaulieu, and Mike Gatford. 1994. Okapi at TREC-3. In Proc. of TREC-3.Google Scholar
- Haggai Roitman, Shai Erera, Oren Sar Shalom, and Bar Weiner. 2017. Enhanced mean retrieval score estimation for query performance prediction. In Proc. of ICTIR. 35--42.Google ScholarDigital Library
- Shubhra Kanti Karmaker Santu, Parikshit Sondhi, and ChengXiang Zhai. 2017. On application of learning to rank for e-Commerce search. In Proc. of SIGIR. 475--484.Google ScholarDigital Library
- Nikos Sarkas, Stelios Paparizos, and Panayiotis Tsaparas. 2010. Structured annotations of web queries. In Proc. of SIGMOD. 771--782.Google ScholarDigital Library
- Humphrey Sheil, Omer Rana, and Ronan Reilly. 2018. Predicting purchasing intent: Automatic feature learning using recurrent neural networks. In The SIGIR 2018 Workshop On eCommerce.Google Scholar
- Anna Shtok, Oren Kurland, and David Carmel. 2016. Query performance prediction using reference lists. ACM Trans. Inf. Syst., Vol. 34, 4 (2016), 19:1--19:34.Google ScholarDigital Library
- Anna Shtok, Oren Kurland, David Carmel, Fiana Raiber, and Gad Markovits. 2012. Predicting query performance by query-drift estimation. ACM Transactions on Information Systems, Vol. 30, 2 (2012), 11.Google ScholarDigital Library
- Gyanit Singh, Nish Parikh, and Neel Sundaresn. 2011. User behavior in zero-recall ecommerce queries. In Proc. of SIGIR. 75--84.Google ScholarDigital Library
- Parikshit Sondhi, Mohit Sharma, Pranam Kolari, and ChengXiang Zhai. 2018. A taxonomy of queries for e-Commerce search. In Proc. of SIGIR. 1245--1248.Google ScholarDigital Library
- Ning Su, Jiyin He, Yiqun Liu, Min Zhang, and Shaoping Ma. 2018. User Intent, behaviour, and perceived satisfaction in product search. In Proc. of WSDM. 547--555.Google ScholarDigital Library
- Zehong Tan, Canran Xu, Mengjie Jiang, Hua Yang, and Xiaoyuan Wu. 2017. Query rewrite for null and low search results in eCommerce. In The SIGIR 2017 Workshop On eCommerce.Google Scholar
- Yongquan Tao and Shengli Wu. 2014. Query performance prediction by considering score magnitude and variance together. In Proc. of CIKM. 1891--1894.Google ScholarDigital Library
- Arthur Toth, Louis Tan, Giuseppe Di Fabbrizio, and Ankur Datta. 2017. Predicting shopping behavior with mixture of RNNs. In The SIGIR 2017 Workshop On eCommerce.Google Scholar
- Hen Tzaban, Ido Guy, Asnat Greenstein-Messica, Arnon Dagan, Lior Rokach, and Bracha Shapira. 2020. Product Bundle Identification using Semi-Supervised Learning. In Proc. of SIGIR.Google ScholarDigital Library
- Teng Xiao, Jiaxin Ren, Zaiqiao Meng, Huan Sun, and Shangsong Liang. 2019. Dynamic bayesian metric learning for personalized product search. In Proc. of CIKM. 1693--1702.Google ScholarDigital Library
- Yingwei Xin, Ethan Hart, Vibhuti Mahajan, and Jean-David Ruvini. 2018. Learning better internal structure of words for sequence labeling. In Proc. of EMNLP. 2584--2593.Google ScholarCross Ref
- Yuan Zhang, Dong Wang, and Yan Zhang. 2019. Neural IR meets graph embedding: A ranking model for product search. In Proc. of WWW. 2390--2400.Google ScholarDigital Library
- Ying Zhao, Falk Scholer, and Yohannes Tsegay. 2008. Effective pre-retrieval query performance prediction using similarity and variability evidence. In Proc. of ECIR. 52--64.Google ScholarCross Ref
- Yun Zhou and W. Bruce Croft. 2007. Query performance prediction in web search environments. In Proc. of SIGI. 543--550.Google Scholar
Index Terms
- Query Reformulation in E-Commerce Search
Recommendations
Towards a Better Understanding of Query Reformulation Behavior in Web Search
WWW '21: Proceedings of the Web Conference 2021As queries submitted by users directly affect search experiences, how to organize queries has always been a research focus in Web search studies. While search request becomes complex and exploratory, many search sessions contain more than a single ...
Examining collaborative query reformulation: a case of travel information searching
SIGIR '14: Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrievalUsers often reformulate or modify their queries when they engage in searching information particularly when the search task is complex and exploratory. This paper investigates query reformulation behavior in collaborative tourism information searching ...
Location-aware query reformulation for search engines
Query reformulation, including query recommendation and query auto-completion, is a popular add-on feature of search engines, which provide related and helpful reformulations of a keyword query. Due to the dropping prices of smartphones and the ...
Comments