%0 Journal Article
%T Labeling emotions in suicide notes: cost-sensitive learning with heterogeneous features
%J Biomedical informatics insights
%D 2012
%A Read, Jonathon
%A Velldal, Erik
%A Ovrelid, Lilja
%V 5
%N Suppl 1
%P 99-103
%X This paper describes a system developed for Track 2 of the 2011 Medical NLP Challenge on identifying emotions in suicide notes. Our approach involves learning a collection of one-versus-all classifiers, each deciding whether or not a particular label should be assigned to a given sentence. We explore a variety of features types-syntactic, semantic and surface-oriented. Cost-sensitive learning is used for dealing with the issue of class imbalance in the data.<p /> <p>Language: en</p>
%G en
%I Libertas Academica
%@ 1178-2226
%U http://dx.doi.org/10.4137/BII.S8930