%0 Conference Paper %1 lipka2010identifying %A Lipka, Nedim %A Stein, Benno %B Proceedings of the 19th international conference on World wide web %C New York, NY, USA %D 2010 %I ACM %K featured-articles mt quality wikipedia writing-style %P 1147--1148 %R http://doi.acm.org/10.1145/1772690.1772847 %T Identifying featured articles in wikipedia: writing style matters %U http://doi.acm.org/10.1145/1772690.1772847 %X Wikipedia provides an information quality assessment model with criteria for human peer reviewers to identify featured articles. For this classification task “Is an article featured or not?” we present a machine learning approach that exploits an article’s character tri- gram distribution. Our approach differs from existing research in that it aims to writing style rather than evaluating meta features like the edit history. The approach is robust, straightforward to im- plement, and outperforms existing solutions. We underpin these claims by an experiment design where, among others, the domain transferability is analyzed. The achieved performances in terms of the F-measure for featured articles are 0.964 within a single Wikipedia domain and 0.880 in a domain transfer situation. %@ 978-1-60558-799-8

@inproceedings{lipka2010identifying, abstract = {Wikipedia provides an information quality assessment model with criteria for human peer reviewers to identify featured articles. For this classification task “Is an article featured or not?” we present a machine learning approach that exploits an article’s character tri- gram distribution. Our approach differs from existing research in that it aims to writing style rather than evaluating meta features like the edit history. The approach is robust, straightforward to im- plement, and outperforms existing solutions. We underpin these claims by an experiment design where, among others, the domain transferability is analyzed. The achieved performances in terms of the F-measure for featured articles are 0.964 within a single Wikipedia domain and 0.880 in a domain transfer situation.}, acmid = {1772847}, added-at = {2012-03-05T23:57:44.000+0100}, address = {New York, NY, USA}, author = {Lipka, Nedim and Stein, Benno}, biburl = {https://www.bibsonomy.org/bibtex/25161a2689da01dd63b3471e3c437ab1b/muehlburger}, booktitle = {Proceedings of the 19th international conference on World wide web}, doi = {http://doi.acm.org/10.1145/1772690.1772847}, interhash = {7c77a1223903702da383baa61dd4ebe6}, intrahash = {5161a2689da01dd63b3471e3c437ab1b}, isbn = {978-1-60558-799-8}, keywords = {featured-articles mt quality wikipedia writing-style}, location = {Raleigh, North Carolina, USA}, numpages = {2}, pages = {1147--1148}, publisher = {ACM}, series = {WWW '10}, timestamp = {2012-03-06T15:11:23.000+0100}, title = {Identifying featured articles in wikipedia: writing style matters}, url = {http://doi.acm.org/10.1145/1772690.1772847}, year = 2010 }