@InProceedings{alkhereyf-rambow:2017:TextGraphs-11,
  author    = {Alkhereyf, Sakhar  and  Rambow, Owen},
  title     = {Work Hard, Play Hard: Email Classification on the Avocado and Enron Corpora},
  booktitle = {Proceedings of TextGraphs-11: the Workshop on Graph-based Methods for Natural Language Processing},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {57--65},
  abstract  = {In this paper, we present an empirical study of email classification into
	  two main categories ``Business" and ``Personal".  We train on the Enron
	  email corpus, and test on the Enron and Avocado email corpora. We show
	  that information from the email exchange networks improves the
	  performance of classification. We represent the email exchange networks
	  as social networks with
	  graph structures. For this classification task, we extract social
	  networks features from the graphs in addition to lexical features from
	  email content and we compare the performance of SVM and Extra-Trees
	  classifiers using these features.  Combining graph features with lexical
	  features improves the performance on both classifiers. We also provide
	  manually annotated sets of the Avocado and Enron email corpora as
	  a supplementary contribution.},
  url       = {http://www.aclweb.org/anthology/W17-2408}
}