%0 Conference Paper %1 Agichtein:2008:FHC:1341531.1341557 %A Agichtein, Eugene %A Castillo, Carlos %A Donato, Debora %A Gionis, Aristides %A Mishne, Gilad %B Proceedings of the 2008 International Conference on Web Search and Data Mining %C New York, NY, USA %D 2008 %I ACM %K content quality scienceontwitter socialMedia twitterScholar %P 183--194 %R 10.1145/1341531.1341557 %T Finding high-quality content in social media %U http://doi.acm.org/10.1145/1341531.1341557 %X 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 %@ 978-1-59593-927-2

@inproceedings{Agichtein:2008:FHC:1341531.1341557, 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}, added-at = {2013-06-25T17:05:36.000+0200}, address = {New York, NY, USA}, author = {Agichtein, Eugene and Castillo, Carlos and Donato, Debora and Gionis, Aristides and Mishne, Gilad}, biburl = {https://www.bibsonomy.org/bibtex/268d0d45fe46992344b38f22932c751b4/asmelash}, booktitle = {Proceedings of the 2008 International Conference on Web Search and Data Mining}, description = {Finding high-quality content in social media}, doi = {10.1145/1341531.1341557}, interhash = {72c7bf5d1c983c47bfc3c6cc9084c26c}, intrahash = {68d0d45fe46992344b38f22932c751b4}, isbn = {978-1-59593-927-2}, keywords = {content quality scienceontwitter socialMedia twitterScholar}, location = {Palo Alto, California, USA}, numpages = {12}, pages = {183--194}, publisher = {ACM}, series = {WSDM '08}, timestamp = {2013-06-25T17:05:36.000+0200}, title = {Finding high-quality content in social media}, url = {http://doi.acm.org/10.1145/1341531.1341557}, year = 2008 }