@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{mishne06-autotag, abstract = {This paper describes AutoTag, a tool which suggests tags for weblog posts using collaborative filtering methods. An evaluation of AutoTag on a large collection of posts shows good accuracy; coupled with the blogger's final quality control, AutoTag assists both in simplifying the tagging process and in improving its quality.}, address = {New York, NY, USA}, author = {Mishne, Gilad}, booktitle = {WWW '06: Proceedings of the 15th International Conference on World Wide Web}, interhash = {62d370a3abfaed3469bd2ee6a8ef6473}, intrahash = {4094419a2f26ac85175ad48207311d61}, note = {paper presented at the poster track}, pages = {953--954}, publisher = {ACM Press}, title = {AutoTag: a collaborative approach to automated tag assignment for weblog posts}, url = {http://portal.acm.org/citation.cfm?id=1135777.1135961}, year = 2006 }