@inproceedings{jurczyk2007discovering,
  abstract = {Question-Answer portals such as Naver and Yahoo! Answers are quickly becoming rich sources of knowledge on many topics which are not well served by general web search engines. Unfortunately, the quality of the submitted answers is uneven, ranging from excellent detailed answers to snappy and insulting remarks or even advertisements for commercial content. Furthermore, user feedback for many topics is sparse, and can be insufficient to reliably identify good answers from the bad ones. Hence, estimating the authority of users is a crucial task for this emerging domain, with potential applications to answer ranking, spam detection, and incentive mechanism design. We present an analysis of the link structure of a general-purpose question answering community to discover authoritative users, and promising experimental results over a dataset of more than 3 million answers from a popular community QA site. We also describe structural differences between question topics that correlate with the success of link analysis for authority discovery.},
  acmid = {1321575},
  address = {New York, NY, USA},
  author = {Jurczyk, Pawel and Agichtein, Eugene},
  booktitle = {Proceedings of the sixteenth ACM conference on Conference on information and knowledge management},
  doi = {10.1145/1321440.1321575},
  interhash = {1c2953be3517384681b6ac831da2c766},
  intrahash = {35394620d2654db8543d5da60f6f00dc},
  isbn = {978-1-59593-803-9},
  location = {Lisbon, Portugal},
  numpages = {4},
  pages = {919--922},
  publisher = {ACM},
  title = {Discovering authorities in question answer communities by using link analysis},
  url = {http://doi.acm.org/10.1145/1321440.1321575},
  year = 2007
}

@inproceedings{agichtein2008finding,
  abstract = {The quality of user-generated content varies drastically from excellent to abuse and spam. As the availability of such content increases, the task of identifying high-quality content sites based on user contributions --social media sites -- becomes increasingly important. Social media in general exhibit a rich variety of information sources: in addition to the content itself, there is a wide array of non-content information available, such as links between items and explicit quality ratings from members of the community. In this paper we investigate methods for exploiting such community feedback to automatically identify high quality content. As a test case, we focus on Yahoo! Answers, a large community question/answering portal that is particularly rich in the amount and types of content and social interactions available in it. We introduce a general classification framework for combining the evidence from different sources of information, that can be tuned automatically for a given social media type and quality definition. In particular, for the community question/answering domain, we show that our system is able to separate high-quality items from the rest with an accuracy close to that of humans},
  acmid = {1341557},
  address = {New York, NY, USA},
  author = {Agichtein, Eugene and Castillo, Carlos and Donato, Debora and Gionis, Aristides and Mishne, Gilad},
  booktitle = {Proceedings of the international conference on Web search and web data mining},
  doi = {10.1145/1341531.1341557},
  interhash = {72c7bf5d1c983c47bfc3c6cc9084c26c},
  intrahash = {29c5c74d95dce215a9692b94fc619839},
  isbn = {978-1-59593-927-2},
  location = {Palo Alto, California, USA},
  numpages = {12},
  pages = {183--194},
  publisher = {ACM},
  title = {Finding high-quality content in social media},
  url = {http://doi.acm.org/10.1145/1341531.1341557},
  year = 2008
}

@inproceedings{ageev2011modeling,
  abstract = {A better understanding of strategies and behavior of successful searchers is crucial for improving the experience of all searchers. However, research of search behavior has been struggling with the tension between the relatively small-scale, but controlled lab studies, and the large-scale log-based studies where the searcher intent and many other important factors have to be inferred. We present our solution for performing controlled, yet realistic, scalable, and reproducible studies of searcher behavior. We focus on difficult informational tasks, which tend to frustrate many users of the current web search technology. First, we propose a principled formalization of different types of "success" for informational search, which encapsulate and sharpen previously proposed models. Second, we present a scalable game-like infrastructure for crowdsourcing search behavior studies, specifically targeted towards capturing and evaluating successful search strategies on informational tasks with known intent. Third, we report our analysis of search success using these data, which confirm and extends previous findings. Finally, we demonstrate that our model can predict search success more effectively than the existing state-of-the-art methods, on both our data and on a different set of log data collected from regular search engine sessions. Together, our search success models, the data collection infrastructure, and the associated behavior analysis techniques, significantly advance the study of success in web search.},
  acmid = {2009965},
  address = {New York, NY, USA},
  author = {Ageev, Mikhail and Guo, Qi and Lagun, Dmitry and Agichtein, Eugene},
  booktitle = {Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval},
  doi = {10.1145/2009916.2009965},
  interhash = {064c757a555505e59a082856eae1191f},
  intrahash = {1c59ff9abf5307d66a11d1c2667cc517},
  isbn = {978-1-4503-0757-4},
  location = {Beijing, China},
  numpages = {10},
  pages = {345--354},
  publisher = {ACM},
  title = {Find it if you can: a game for modeling different types of web search success using interaction data},
  url = {http://doi.acm.org/10.1145/2009916.2009965},
  year = 2011
}