ABSTRACT
Web search has been a reactive scenario for decades which often starts by users issuing queries. By studying the user behavior in search engine logs, we have discovered that many of the search tasks such as stock-price checking, news reading exhibit strong repeated patterns from day to day. In addition, users exhibit even stronger repetition on mobile devices. This provides us chances to perform proactive recommendations without user issuing queries. In this work, we aim at discovering and characterizing these types of tasks so that we can automatically predict when and what types of tasks will be repeated by the users in the future, through analyzing search logs from a commercial Web search engine and user interaction logs from a mobile App that offers proactive recommendations. We first introduce a set of novel features that can accurately capture task repetition. We then propose a novel deep learning framework that learns user preferences and makes automatic predictions. Our framework is capable of learning both user-independent global models as well as catering personalized models via model adaptation. The model we developed significantly outperforms other state-of-the-art predictive models by large margins. We also demonstrate the power of our model and features through an application to improve the recommendation quality of the mobile App. Results indicate a significant relevance improvement over the current production system.
- E. Adar, J. Teevan, and S. T. Dumais. Large scale analysis of web revisitation patterns. In CHI '08, pages 1197--1206. Google ScholarDigital Library
- E. Adar, J. Teevan, and S. T. Dumais. Resonance on the web: Web dynamics and revisitation patterns. In CHI '09, pages 1381--1390, New York, NY, USA, 2009. ACM. Google ScholarDigital Library
- E. Agichtein, R. W. White, S. T. Dumais, and P. N. Bennet. Search, interrupted: Understanding and predicting search task continuation. In SIGIR '12, pages 315--324. Google ScholarDigital Library
- A. Aula, N. Jhaveri, and M. Kaki. Information search and re-access strategies of experienced web users. In WWW '05, pages 583--592, New York, NY, USA, 2005. ACM. Google ScholarDigital Library
- M.-W. Chang and W. tau Yih. Dual coordinate descent algorithms for efficient large margin structured prediction. TACL, 1:207--218, May 2013.Google ScholarCross Ref
- C. L. Giles, S. Lawrence, and A. C. Tsoi. Noisy time series prediction using recurrent neural networks and grammatical inference. Mach. Learn., 44(1--2):161--183, July 2001. Google ScholarDigital Library
- R. Guha, V. Gupta, V. Raghunathan, and R. Srikant. User modeling for a personal assistant. In WSDM '15, pages 275--284, 2015. Google ScholarDigital Library
- Q. Guo, H. Jin, D. Lagun, S. Yuan, and E. Agichtein. Mining touch interaction data on mobile devices to predict web search result relevance. In SIGIR '13, pages 153--162. Google ScholarDigital Library
- A. Hassan Awadallah, R. W. White, P. Pantel, S. T. Dumais, and Y.-M. Wang. Supporting complex search tasks. In CIKM '14, pages 829--838, 2014. Google ScholarDigital Library
- E. Herder. Characterizations of user web revisit behavior. In ABIS 2005, 2005.Google Scholar
- D. Lagun, C.-H. Hsieh, D. Webster, and V. Navalpakkam. Towards better measurement of attention and satisfaction in mobile search. In SIGIR '14, pages 113--122, 2014. Google ScholarDigital Library
- J. Langford, L. Li, and T. Zhang. Sparse online learning via truncated gradient. J. Mach. Learn. Res., 10:777--801, 2009. Google ScholarDigital Library
- S. Lawrence. Context in web search. IEEE Data Engineering Bulletin, pages 3--25, 2000.Google Scholar
- Z. Liao, Y. Song, Y. Huang, L. wei He, and Q. He. Task trail: An effective segmentation of user search behavior. TKDE, 2014.Google ScholarCross Ref
- C. Lucchese, S. Orlando, R. Perego, F. Silvestri, and G. Tolomei. Discovering tasks from search engine query logs. ACM Trans. Inf. Syst., 31(3), Aug. 2013. Google ScholarDigital Library
- C. Lucchese, S. Orlando, R. Perego, F. Silvestri, and G. Tolomei. Modeling and predicting the task-by-task behavior of search engine users. In OAIR '13, pages 77--84, 2013. Google ScholarDigital Library
- C. Sheng, J. Zhao, Y. Liu, and W. Wang. Prediction for noisy nonlinear time series by echo state network based on dual estimation. Neurocomput., 82:186--195, Apr. 2012. Google ScholarDigital Library
- M. Shokouhi and Q. Guo. From queries to cards: Re-ranking proactive card recommendations based on reactive search history. In SIGIR '15, 2015. Google ScholarDigital Library
- Y. Song, H. Ma, H. Wang, and K. Wang. Exploring and exploiting user search behavior on mobile and tablet devices to improve search relevance. In WWW '13, pages 1201--1212, 2013. Google ScholarDigital Library
- Y. Song, H. Wang, and X. He. Adapting deep ranknet for personalized search. In WSDM '14, pages 83--92, 2014. Google ScholarDigital Library
- H. Wang, X. He, M.-W. Chang, Y. Song, R. W. White, and W. Chu. Personalized ranking model adaptation for web search. In SIGIR '13, pages 323--332, 2013. Google ScholarDigital Library
- H. Wang, Y. Song, M.-W. Chang, X. He, R. W. White, and W. Chu. Learning to extract cross-session search tasks. In WWW '13, pages 1353--1364, 2013. Google ScholarDigital Library
- Y. Wang, X. Huang, and R. W. White. Characterizing and supporting cross-device search tasks. In WSDM '13, pages 707--716, New York, NY, USA, 2013. ACM. Google ScholarDigital Library
- R. W. White, P. Bailey, and L. Chen. Predicting user interests from contextual information. In SIGIR '09, pages 363--370, New York, NY, USA, 2009. ACM. Google ScholarDigital Library
- R. W. White, W. Chu, A. Hassan, X. He, Y. Song, and H. Wang. Enhancing personalized search by mining and modeling task behavior. In WWW '13, pages 1411--1420. Google ScholarDigital Library
- J. Yan, W. Chu, and R. W. White. Cohort modeling for enhanced personalized search. In SIGIR '14, pages 505--514, New York, NY, USA, 2014. ACM. Google ScholarDigital Library
- J. Yang, R. Yan, and A. G. Hauptmann. Cross-domain video concept detection using adaptive svms. In MULTIMEDIA '07, pages 188--197, 2007. Google ScholarDigital Library
- M. Yang. Statistical models for count time series with excess zeros. PhD thesis, University of Iowa, 2012.Google ScholarCross Ref
- R. Zhang, Y. Konda, A. Dong, P. Kolari, Y. Chang, and Z. Zheng. Learning recurrent event queries for web search. In EMNLP '10, pages 1129--1139, 2010. Google ScholarDigital Library
Index Terms
- Query-Less: Predicting Task Repetition for NextGen Proactive Search and Recommendation Engines
Recommendations
Mining query subtopics from search log data
SIGIR '12: Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrievalMost queries in web search are ambiguous and multifaceted. Identifying the major senses and facets of queries from search log data, referred to as query subtopic mining in this paper, is a very important issue in web search. Through search log analysis, ...
A Method of Query Recommendation Based on User Behavior
ICITEE '18: Proceedings of the International Conference on Information Technology and Electrical Engineering 2018Search engine query recommendation method based on the logs is that recommend query according to the behavior popularity, this method ignores the differences in search requirements that causes by individual user backgrounds. To reduce the risk of query ...
Predicting query reformulation type from user behavior
SAC '13: Proceedings of the 28th Annual ACM Symposium on Applied ComputingThis paper proposes a method to discover how a user's search intent changes using his/her behavior during a Web search. A Web search user has a particular search intent and formulates search queries according to that intent. It is, however, a difficult ...
Comments