Filters








19,037 Hits in 6.7 sec

Identifying task-based sessions in search engine query logs

Claudio Lucchese, Salvatore Orlando, Raffaele Perego, Fabrizio Silvestri, Gabriele Tolomei
2011 Proceedings of the fourth ACM international conference on Web search and data mining - WSDM '11  
The research challenge addressed in this paper is to devise effective techniques for identifying task-based sessions, i.e. sets of possibly non contiguous queries issued by the user of a Web Search Engine  ...  In order to evaluate and compare different approaches, we built, by means of a manual labeling process, a ground-truth where the queries of a given query log have been grouped in tasks.  ...  Authors also thank Franco Maria Nardini for the help provided in adapting the original Query Flow Graph implementation.  ... 
doi:10.1145/1935826.1935875 dblp:conf/wsdm/LuccheseOPST11 fatcat:kfxt4tsakzg3npkllpkeevyxca

How do users grow up along with search engines?

Jian Liu, Yiqun Liu, Min Zhang, Shaoping Ma
2013 Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13  
The findings have implications for how Web search engines should better support users' information seeking process by tackling complex search tasks and complicated query formulations.  ...  With a stronger reliance on search engines in our daily life, a large number of studies have investigated user behavior characteristics in Web search.  ...  [3] analyzed individual queries, query duplication, and query sessions based on an AltaVista Search Engine query log.  ... 
doi:10.1145/2505515.2505650 dblp:conf/cikm/LiuLZM13 fatcat:ubkavtwihne3zpu5vwijwesnl4

Enhancing personalization via search activity attribution

Adish Singla, Ryen W. White, Ahmed Hassan, Eric Horvitz
2014 Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval - SIGIR '14  
Using logs containing both person and machine identifiers, and logs from a popular commercial search engine, we learn models that accurately assign observed search behaviors to each of different users.  ...  However, shared machine usage is common, and in these cases, the activities of multiple users may be generated under a single identifier, creating a potentially noisy signal for applications such as search  ...  We consider assignment based on the first query of the search session, and all of the session-based features can be computed by limiting the session to a single query.  ... 
doi:10.1145/2600428.2609510 dblp:conf/sigir/SinglaWHH14 fatcat:ofhm43dx3fbchnefqvz2cn2kfi

Identifying the Names of Complex Search Tasks with Task-Related Entities

Ting-Xuan Wang, Wen-Hsiang Lu
2016 International Journal of Computational Linguistics and Chinese Language Processing  
Conventional search engines usually consider a search query corresponding only to a simple task.  ...  To understand and improve user behavior when searching a complex task, we propose an entity-driven complex task model (ECTM) based on exploiting microblogs and query logs.  ...  Nevertheless, a single user's search session from query logs may not be sufficient in identifying complex search tasks since complex tasks may cross search sessions or be interleaved in a single search  ... 
dblp:journals/ijclclp/WangL16 fatcat:ipuc62ri5fggrns7rgmct52ocq

Identifying Real-Life Complex Task Names with Task-Intrinsic Entities from Microblogs

Ting-Xuan Wang, Kun-Yu Tsai, Wen-Hsiang Lu
2014 Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
A complex task thus needs to submit several queries in order to seeking each of entities.  ...  Understanding complex tasks can allow a search engine to suggest related entities and help users explicitly assign their ongoing tasks.  ...  Lucchese et al. (2011) tried to identify task-based sessions in query logs by semantic-based features extracted from Wiktionary and Wikipedia to overcome lack of semantic information.  ... 
doi:10.3115/v1/p14-2077 dblp:conf/acl/WangTL14 fatcat:aj42tp7hmjgwtk4f32er4pip3i

A Multilingual Approach for Unsupervised Search Task Identification

Luis Lugo, Jose G. Moreno, Gilles Hubert
2020 Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval  
Search engine logs contain queries in multiple languages, but most existing methods for search task identification are not multilingual.  ...  Query logs registered by search engines enable the automatic identification of the search tasks that users perform to fulfill their information needs.  ...  Mining query logs from search engines enable the automatic modeling of search tasks.  ... 
doi:10.1145/3397271.3401258 dblp:conf/sigir/LugoMH20a fatcat:uuw6eugy7bc2jp3r6re6mzfoee

Beyond the session timeout

Rosie Jones, Kristina Lisa Klinkner
2008 Proceeding of the 17th ACM conference on Information and knowledge mining - CIKM '08  
Keywords query log segmentation, query session, query session boundary detection, search goal  ...  However, users query search engines in order to accomplish tasks at a variety of granularities, issuing multiple queries as they attempt to accomplish tasks.  ...  RELATED WORK In library search systems, "sessions" were easy to identify: users logged in for a single task then logged out again, so login IDs could be used.  ... 
doi:10.1145/1458082.1458176 dblp:conf/cikm/JonesK08 fatcat:4twwavgcprfercfjn7gtja7pze

How medical expertise influences web search interaction

Ryen W. White, Susan Dumais, Jaime Teevan
2008 Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '08  
In this poster we present findings from a log-based study into how medical domain experts search the Web for information related to their expertise, as compared with non-experts.  ...  We find differences in sites visited, query vocabulary, and search behavior.  ...  To address this concern we developed two methods to identify comparable tasks. For one, we identified search sessions that began with the same query.  ... 
doi:10.1145/1390334.1390506 dblp:conf/sigir/WhiteDT08 fatcat:2vlof5cqxzabjadhr2qzpbudem

Predicting implicit search behaviors usinglog analysis

L LeemaPriyadharshini, S Florence, K Prema, C Shyamala Kumari
2018 International Journal of Engineering & Technology  
Search engines provide ranked information based on the query given by the user. Understanding user search behavior is an important task for satisfaction of the users with the needed information.  ...  These details will be available in the dataset of web search log.  ...  Web search logs contain user activities towards search engines, such as queries, reading time and clicks. Search trails store the prints left by users of search engines in their search processes.  ... 
doi:10.14419/ijet.v7i1.7.9582 fatcat:x5bzqwhu4vdi7osarrvid3bisy

A Survey on Feedback Session for Inferring User Search Query with CAP

2016 International Journal of Science and Research (IJSR)  
to search to by their query to explain their recognized uncertain in sequence search engines does not give correct result of user required query and does not satisfy the request hence it is necessary to  ...  the proposed feedback session .feedback session buit/ construct from user click through logs consist the information about different user search information.  ...  User Search task for query Though users query search engines in order to achieve tasks at a diversity of granularities, issue numerous query as they effort to accomplish tasks .R Jones and K.L linker  ... 
doi:10.21275/v5i1.nov152863 fatcat:bsipuv6kdrbjdjn5sikblsv5ki

Characterizing and predicting search engine switching behavior

Ryen W. White, Susan T. Dumais
2009 Proceeding of the 18th ACM conference on Information and knowledge management - CIKM '09  
In this paper we present a study of search engine switching behavior that combines largescale 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.  ...  Any personally identifiable information was removed from the logs prior to analysis. From these logs we extracted search sessions. Every session began with a query issued to Google, Yahoo!  ... 
doi:10.1145/1645953.1645967 dblp:conf/cikm/WhiteD09 fatcat:oje6tlxb6zhk3kqi5sbz5cx6fi

Discovering tasks from search engine query logs

Claudio Lucchese, Salvatore Orlando, Raffaele Perego, Fabrizio Silvestri, Gabriele Tolomei
2013 ACM Transactions on Information Systems  
First, we identify user tasks from individual user sessions stored in search engine query logs.  ...  In our vision, a user task is a set of possibly noncontiguous queries (within a user search session), which refer to the same need.  ...  Research Labs in Barcelona, Spain, for providing us their query-flow graph implementation, and Franco Maria Nardini for adapting this implementation to our needs.  ... 
doi:10.1145/2493175.2493179 fatcat:2tu3ckionnf3thjk7uetqhddkq

Analyzing Web Search Behavior for Software Engineering Tasks [article]

Nikitha Rao, Chetan Bansal, Thomas Zimmermann, Ahmed Hassan Awadallah, Nachiappan Nagappan
2020 arXiv   pre-print
In this work, we present the first large-scale analysis of web search behavior for SE tasks using the search query logs from Bing, a commercial web search engine.  ...  Subsequently, we propose a taxonomy of intents to identify the various contexts in which web search is used in software engineering.  ...  WEB SEARCH LOGS In this study, we use the search query logs from Bing, a commercial web search engine. The logs comprise of a rich set of metadata associated with each user query.  ... 
arXiv:1912.09519v3 fatcat:bdah3un2uneoxprepiyvmf4j3e

Task Trail Based Enhanced User Experience in Customer Facing Website using Automatic Facet Construction Techniques

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
Finally we proposed a novel method of improving end user search experience by combining the task trail based user behavior and Automatic facet searching.  ...  Our scopes of work will predominately combining the Automatic facets with the user behavior from the task trail and adding product based standardization to improve the end search experience.  ...  The queries may sometime interleave with in the time threshold. The session based logs are further segmented based on the task according to semantic relationship between the user search queries.  ... 
doi:10.35940/ijitee.i3172.0789s319 fatcat:uxrzx565srat5i6ep765wbmzyq

Modeling and analysis of cross-session search tasks

Alexander Kotov, Paul N. Bennett, Ryen W. White, Susan T. Dumais, Jaime Teevan
2011 Proceedings of the 34th international ACM SIGIR conference on Research and development in Information - SIGIR '11  
The information needs of search engine users vary in complexity, depending on the task they are trying to accomplish.  ...  We focus on two problems: (i) given a user query, identify all related queries from previous sessions that the user has issued, and (ii) given a multi-query task for a user, predict whether the user will  ...  In this paper we focus on tasks that extend across sessions. There has been some work on characterizing such tasks using log or survey data, and on automatically identifying queries on the same task.  ... 
doi:10.1145/2009916.2009922 dblp:conf/sigir/KotovBWDT11 fatcat:aswkmg3555eo7hmdr7ifvode34
« Previous Showing results 1 — 15 out of 19,037 results