1,165 Hits in 3.9 sec

Predicting web searcher satisfaction with existing community-based answers

Qiaoling Liu, Eugene Agichtein, Gideon Dror, Evgeniy Gabrilovich, Yoelle Maarek, Dan Pelleg, Idan Szpektor
2011 Proceedings of the 34th international ACM SIGIR conference on Research and development in Information - SIGIR '11  
To this end, we formulate a new problem of predicting the satisfaction of web searchers with CQA answers.  ...  Community-based Question Answering (CQA) sites, such as Yahoo! Answers, Baidu Knows, Naver, and Quora, have been rapidly growing in popularity.  ...  This paper proposes and addresses this new problem of predicting the satisfaction of Web searchers with existing CQA answers.  ... 
doi:10.1145/2009916.2009974 dblp:conf/sigir/LiuADGMPS11 fatcat:6xvvm44kundidpm4xwdjpmropq

When web search fails, searchers become askers

Qiaoling Liu, Eugene Agichtein, Gideon Dror, Yoelle Maarek, Idan Szpektor
2012 Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval - SIGIR '12  
While Web search has become increasingly effective over the last decade, for many users' needs the required answers may be spread across many documents, or may not exist on the Web at all.  ...  Our work develops novel insights into searcher intent and behavior that lead to asking questions to the community, providing a foundation for more effective integration of automated web search and social  ...  [18] argued that some of these needs can be satisfied with existing answers from CQA archives by harnessing the unique structure of such archives for detecting web searcher satisfaction.  ... 
doi:10.1145/2348283.2348390 dblp:conf/sigir/LiuADMS12 fatcat:jp6nx5svfvgazisv5g3hapoxim

On cognition, emotion, and interaction aspects of search tasks with different search intentions

Yashar Moshfeghi, Joemon M. Jose
2013 Proceedings of the 22nd international conference on World Wide Web - WWW '13  
Results show that we can learn a model that predicts the search task types with reasonable accuracy.  ...  Furthermore, we investigate whether we can predict these search tasks given user's interaction with the system.  ...  Finally, we discuss the predictability of search task types based on features derived from the user interaction with the system in Section 4.2.  ... 
doi:10.1145/2488388.2488469 dblp:conf/www/MoshfeghiJ13 fatcat:326qdtqma5bz3o2lj6l5iizwlq

The role of subjective factors in the information search process

Jacek Gwizdka, Irene Lopatovska
2009 Journal of the American Society for Information Science and Technology  
We examined relationships between subjective factors (happiness levels, satisfaction with and confidence in the search results, feeling lost during search, familiarity with and interest in the search topic  ...  Forty-eight participants each conducted six Web searches in a controlled setting.  ...  The measures based on Web page visit counts were calculated for each search task and, with the exception of the total number of pages visited, did not include revisits to Web pages.  ... 
doi:10.1002/asi.21183 fatcat:caqfidgq6nfdhjve24bevykh5a

Struggling and Success in Web Search

Daan Odijk, Ryen W. White, Ahmed Hassan Awadallah, Susan T. Dumais
2015 Proceedings of the 24th ACM International on Conference on Information and Knowledge Management - CIKM '15  
Web searchers sometimes struggle to find relevant information. Struggling leads to frustrating and dissatisfying search experiences, even if searchers ultimately meet their search objectives.  ...  We address this important issue using a mixed methods study using large-scale logs, crowd-sourced labeling, and predictive modeling.  ...  They provide important clues on what searchers might do next, such as switching to a different search engine [15, 41] or turning to a community question answering service [29] .  ... 
doi:10.1145/2806416.2806488 dblp:conf/cikm/OdijkWAD15 fatcat:av4dtkyftna3ljgixqvkrma35e

Improving search relevance for short queries in community question answering

Haocheng Wu, Wei Wu, Ming Zhou, Enhong Chen, Lei Duan, Heung-Yeung Shum
2014 Proceedings of the 7th ACM international conference on Web search and data mining - WSDM '14  
Relevant question retrieval and ranking is a typical task in community question answering (CQA). Existing methods mainly focus on long and syntactically structured queries.  ...  With these intent signals, we propose a new intent-based language model.  ...  [19] proposed predicting web searcher satisfaction with question-answers from CQA.  ... 
doi:10.1145/2556195.2556239 dblp:conf/wsdm/WuWZCDS14 fatcat:qcgoeb3ulbdgvlyvcd3tonlapi

Belief Dynamics and Biases in Web Search

Ryen W. White, Eric Horvitz
2015 ACM Transactions on Information Systems  
We investigate how beliefs about the efficacy of medical interventions are influenced by searchers' exposure to information on retrieved Web pages.  ...  ACM Transactions on Information Systems predictive models of belief updating. In Section 4 we report the findings of our studies, including the performance of the predictive models.  ...  How should actions be communicated with searchers, e.g., with options to reverse system interventions?  ... 
doi:10.1145/2746229 fatcat:qgajzmzf3zbc7lejfz4eh2fmwa

Training for Web search: Will it get you in shape?

Wendy Lucas, Heikki Topi
2004 Journal of the American Society for Information Science and Technology  
Given that time is money, Web searching can be a very expensive proposition.  ...  Two of the experimental treatments were based on the type of training the users received.  ...  Yet Web searchers are loath to take advantage of such features.  ... 
doi:10.1002/asi.20074 fatcat:cdaclsehcngmzeuetruqodfzkm

Semantifying queries over large-scale Web search engines

Ioannis Papadakis, Michalis Stefanidakis, Sofia Stamou, Ioannis Andreou
2012 Journal of Internet Services and Applications  
In this paper, we focus on the occasions when largescale web search engines find it difficult to cope with specific information-seeking behaviors and we accordingly introduce a query construction service  ...  In many situations, searching the web is synonymous to information seeking. Currently, web search engines are the most popular vehicle via which people get access to the web.  ...  Moreover, in many cases, popularity-based factors succeed in predicting the right suggestions.  ... 
doi:10.1007/s13174-012-0068-9 fatcat:romlt6wy25bhbeejuwfksxmdhi

Rain or shine? Forecasting search process performance in exploratory search tasks

Chirag Shah, Chathra Hendahewa, Roberto González-Ibáñez
2015 Journal of the Association for Information Science and Technology  
We propose a machine-learning-based method to dynamically evaluate and predict search performance several time-steps ahead at each given time point of the search process during an exploratory search task  ...  Importantly, the proposed approach is based on user processes and is independent of any IR system.  ...  Despite the existence of well-defined goals, searchers need to explore several sources before providing an answer.  ... 
doi:10.1002/asi.23484 fatcat:mtd244xxnzblteakt67lve357u

Predicting information seeker satisfaction in community question answering

Yandong Liu, Jiang Bian, Eugene Agichtein
2008 Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '08  
with the answers submitted by the community participants.  ...  We complement our results with a thorough investigation of the interactions and information seeking patterns in question answering communities that correlate with information seeker satisfaction.  ...  Answers team for allowing us extended use of the API, the Emory College Seed Fund for partially supporting this research, and the anonymous reviewers for valuable suggestions.  ... 
doi:10.1145/1390334.1390417 dblp:conf/sigir/LiuBA08 fatcat:lgk54rinkngftit3advpl5v4ky

Modeling information-seeker satisfaction in community question answering

Eugene Agichtein, Yandong Liu, Jiang Bian
2009 ACM Transactions on Knowledge Discovery from Data  
We investigate the problem of predicting information seeker satisfaction in collaborative question answering communities, where we attempt to predict whether a question author will be satisfied with the  ...  We complement our results with a thorough investigation of the interactions and information seeking patterns in question answering communities that correlate with information seeker satisfaction.  ...  Answers team for allowing us extended use of the API, the Emory College Seed Fund for partially supporting this research.  ... 
doi:10.1145/1514888.1514893 fatcat:lyx3b22pwnhn7ebei3uphokiei

Evaluation Challenges and Directions for Information-Seeking Support Systems

D. Kelly, S. Dumais, J.O. Pedersen
2009 Computer  
Particular evaluation measures indicate how well a search algorithm performs with respect to the number of relevant documents retrieved along with the position of these documents within a ranked list.  ...  automatic indexing studies pioneered by librarian and computer scientist Cyril Cleverdon at Cranfield University in the 1960s. 1 The basic IR evaluation model has been extended by efforts associated with  ...  While usability measures are based on searchers' responses to questionnaire items or their interactions with the system, performance measures are based on the number of relevant documents searchers find  ... 
doi:10.1109/mc.2009.82 fatcat:nfsg722l7bfbbokirote7m2qyu

Slow Search

Jaime Teevan, Kevyn Collins-Thompson, Ryen W. White, Susan T. Dumais, Yubin Kim
2013 Proceedings of the Symposium on Human-Computer Interaction and Information Retrieval - HCIR '13  
Research suggests that even slightly higher retrieval latency by Web search engines can lead to dramatic decreases in users' perceptions of result quality and engagement with the search results.  ...  This raises the important question: What would search look like if search engines were not constrained by existing expectations for speed?  ...  [39] describe an email based search engine where users in lowconnectivity communities can issue queries and receive responses via email.  ... 
doi:10.1145/2528394.2528395 dblp:conf/hcir/TeevanCWDK13 fatcat:3kt5j7fhhrgevkz3xiiviescia


1973 The Lancet  
Tuning should therefore use an unbiased sample of actual search requests, a judging process accurately modelling that of real searchers, and measures optimally correlated with real satisfaction.  ...  Intuitively, an important end goal of tuning should be to maximise satisfaction across the searchers who will use the facility.  ...  However, for simplicity, let us assume that publisher satisfaction coincides with overall searcher satisfaction.  ... 
doi:10.1016/s0140-6736(73)90676-4 fatcat:i2ifh6u7drajpfbnalymmukua4
« Previous Showing results 1 — 15 out of 1,165 results