%0 Book Section %1 Hensinger2010 %A Hensinger, Elena %A Flaounas, Ilias %A Cristianini, Nello %B Artificial Intelligence Applications and Innovations %C Berlin, Heidelberg %D 2010 %E Papadopoulos, Harris %E Andreou, Andreas %E Bramer, Max %I Springer Boston %K data-analysis data-mining networks news svm %P 179--186 %R 10.1007/978-3-642-16239-8\_25 %T Learning the Preferences of News Readers with SVM and Lasso Ranking %V 339 %X We attack the task of predicting which news-stories are more appealing to a given audience by comparing 'most popular stories', gathered from various online news outlets, over a period of seven months, with stories that did not become popular despite appearing on the same page at the same time. We cast this as a learning-to-rank task, and train two different learning algorithms to reproduce the preferences of the readers, within each of the outlets. The first method is based on Support Vector Machines, the second on the Lasso. By just using words as features, SVM ranking can reach significant accuracy in correctly predicting the preference of readers for a given pair of articles. Furthermore, by exploiting the sparsity of the solutions found by the Lasso, we can also generate lists of keywords that are expected to trigger the attention of the outlets' readers. %& 25

@incollection{Hensinger2010, abstract = {We attack the task of predicting which news-stories are more appealing to a given audience by comparing 'most popular stories', gathered from various online news outlets, over a period of seven months, with stories that did not become popular despite appearing on the same page at the same time. We cast this as a learning-to-rank task, and train two different learning algorithms to reproduce the preferences of the readers, within each of the outlets. The first method is based on Support Vector Machines, the second on the Lasso. By just using words as features, {SVM} ranking can reach significant accuracy in correctly predicting the preference of readers for a given pair of articles. Furthermore, by exploiting the sparsity of the solutions found by the Lasso, we can also generate lists of keywords that are expected to trigger the attention of the outlets' readers.}, added-at = {2011-05-31T13:29:09.000+0200}, address = {Berlin, Heidelberg}, author = {Hensinger, Elena and Flaounas, Ilias and Cristianini, Nello}, biburl = {https://www.bibsonomy.org/bibtex/28a067de5ef0e3bef1e4803717540e61e/rincedd}, booktitle = {Artificial Intelligence Applications and Innovations}, chapter = 25, doi = {10.1007/978-3-642-16239-8\_25}, editor = {Papadopoulos, Harris and Andreou, Andreas and Bramer, Max}, file = {Hensinger2010 - Learning the Preferences of News Readers with SVM and Lasso Ranking.pdf:Hensinger2010 - Learning the Preferences of News Readers with SVM and Lasso Ranking.pdf:PDF}, groups = {public}, interhash = {607e75fe15b4b9aae3fa04e53a1c0118}, intrahash = {8a067de5ef0e3bef1e4803717540e61e}, keywords = {data-analysis data-mining networks news svm}, pages = {179--186}, publisher = {Springer Boston}, series = {IFIP Advances in Information and Communication Technology}, timestamp = {2011-05-31T13:30:52.000+0200}, title = {Learning the Preferences of News Readers with {SVM} and Lasso Ranking}, username = {rincedd}, volume = 339, year = 2010 }